Najim Dehak

Jaejin Cho, Raghavendra Pappagari, Piotr Żelasko et al. · nvidia

Considering the abundance of unlabeled speech data and the high labeling costs, unsupervised learning methods can be essential for better system development. One of the most successful methods is contrastive self-supervised methods, which require negative sampling: sampling alternative samples to contrast with the current sample (anchor). However, it is hard to ensure if all the negative samples belong to classes different from the anchor class without labels. This paper applies a non-contrastive self-supervised learning method on an unlabeled speech corpus to learn utterance-level embeddings. We used DIstillation with NO labels (DINO), proposed in computer vision, and adapted it to the speech domain. Unlike the contrastive methods, DINO does not require negative sampling. These embeddings were evaluated on speaker verification and emotion recognition. In speaker verification, the unsupervised DINO embedding with cosine scoring provided 4.38% EER on the VoxCeleb1 test trial. This outperforms the best contrastive self-supervised method by 40% relative in EER. An iterative pseudo-labeling training pipeline, not requiring speaker labels, further improved the EER to 1.89%. In emotion recognition, the DINO embedding performed 60.87, 79.21, and 56.98% in micro-f1 score on IEMOCAP, Crema-D, and MSP-Podcast, respectively. The results imply the generality of the DINO embedding to different speech applications.

Junhyeok Lee, Xiluo He, Jihwan Lee et al.

Neural audio codecs optimized for mel-spectrogram reconstruction often fail to preserve intelligibility. While semantic encoder distillation improves encoded representations, it does not guarantee content preservation in reconstructed speech. In this work, we demonstrate that self-supervised representation reconstruction (SSRR) loss fundamentally improves codec training and performance. First, SSRR significantly accelerates convergence, enabling competitive results using only a single GPU. Second, it enhances intelligibility by reconstructing distilled self-supervised representations from codec outputs. Third, SSRR enables high intelligibility without additional lookahead in streaming Transformer-based codecs, allowing a zero-lookahead architecture for real-time deployment. As a result, our JHCodec achieves state-of-the-art performance while maintaining minimal latency and reduced training cost. We open-source the full implementation, training pipeline, and demo on Github https://github.com/jhcodec843/jhcodec.

Helin Wang, Bowen Shi, Andros Tjandra et al.

The performance evaluation remains a complex challenge in audio separation, and existing evaluation metrics are often misaligned with human perception, course-grained, relying on ground truth signals. On the other hand, subjective listening tests remain the gold standard for real-world evaluation, but they are expensive, time-consuming, and difficult to scale. This paper addresses the growing need for automated systems capable of evaluating audio separation without human intervention. The proposed evaluation metric, SAM Audio Judge (SAJ), is a multimodal fine-grained reference-free objective metric, which shows highly alignment with human perceptions. SAJ supports three audio domains (speech, music and general sound events) and three prompt inputs (text, visual and span), covering four different dimensions of evaluation (recall, percision, faithfulness, and overall). SAM Audio Judge also shows potential applications in data filtering, pseudo-labeling large datasets and reranking in audio separation models. We release our code and pre-trained models at: https://github.com/facebookresearch/sam-audio.

Jaejin Cho, Jes'us Villalba, Laureano Moro-Velazquez et al.

In recent studies, self-supervised pre-trained models tend to outperform supervised pre-trained models in transfer learning. In particular, self-supervised learning (SSL) of utterance-level speech representation can be used in speech applications that require discriminative representation of consistent attributes within an utterance: speaker, language, emotion, and age. Existing frame-level self-supervised speech representation, e.g., wav2vec, can be used as utterance-level representation with pooling, but the models are usually large. There are also SSL techniques to learn utterance-level representation. One of the most successful is a contrastive method, which requires negative sampling: selecting alternative samples to contrast with the current sample (anchor). However, this does not ensure that all the negative samples belong to classes different from the anchor class without labels. This paper applies a non-contrastive self-supervised method to learn utterance-level embeddings. We adapted DIstillation with NO labels (DINO) from computer vision to speech. Unlike contrastive methods, DINO does not require negative sampling. We compared DINO to x-vector trained in a supervised manner. When transferred to down-stream tasks (speaker verification, speech emotion recognition (SER), and Alzheimer's disease detection), DINO outperformed x-vector. We studied the influence of several aspects during transfer learning such as dividing the fine-tuning process into steps, chunk lengths, or augmentation. During fine-tuning, tuning the last affine layers first and then the whole network surpassed fine-tuning all at once. Using shorter chunk lengths, although they generate more diverse inputs, did not necessarily improve performance, implying speech segments at least with a specific length are required for better performance per application. Augmentation was helpful in SER.

Henry Li Xinyuan, Sonal Joshi, Thomas Thebaud et al.

Poisoning backdoor attacks involve an adversary manipulating the training data to induce certain behaviors in the victim model by inserting a trigger in the signal at inference time. We adapted clean label backdoor (CLBD)-data poisoning attacks, which do not modify the training labels, on state-of-the-art speech recognition models that support/perform a Spoken Language Understanding task, achieving 99.8% attack success rate by poisoning 10% of the training data. We analyzed how varying the signal-strength of the poison, percent of samples poisoned, and choice of trigger impact the attack. We also found that CLBD attacks are most successful when applied to training samples that are inherently hard for a proxy model. Using this strategy, we achieved an attack success rate of 99.3% by poisoning a meager 1.5% of the training data. Finally, we applied two previously developed defenses against gradient-based attacks, and found that they attain mixed success against poisoning.

Trevor Meyer, Camden Shultz, Najim Dehak et al.

Time series data is often composed of information at multiple time scales, particularly in biomedical data. While numerous deep learning strategies exist to capture this information, many make networks larger, require more data, are more demanding to compute, and are difficult to interpret. This limits their usefulness in real-world applications facing even modest computational or data constraints and can further complicate their translation into practice. We present a minimal, computationally efficient Time Scale Network combining the translation and dilation sequence used in discrete wavelet transforms with traditional convolutional neural networks and back-propagation. The network simultaneously learns features at many time scales for sequence classification with significantly reduced parameters and operations. We demonstrate advantages in Atrial Dysfunction detection including: superior accuracy-per-parameter and accuracy-per-operation, fast training and inference speeds, and visualization and interpretation of learned patterns in atrial dysfunction detection on ECG signals. We also demonstrate impressive performance in seizure prediction using EEG signals. Our network isolated a few time scales that could be strategically selected to achieve 90.9% accuracy using only 1,133 active parameters and consistently converged on pulsatile waveform shapes. This method does not rest on any constraints or assumptions regarding signal content and could be leveraged in any area of time series analysis dealing with signals containing features at many time scales.

Martin Sustek, Samik Sadhu, Lukas Burget et al.

The recently proposed Joint Energy-based Model (JEM) interprets discriminatively trained classifier $p(y|x)$ as an energy model, which is also trained as a generative model describing the distribution of the input observations $p(x)$. The JEM training relies on "positive examples" (i.e. examples from the training data set) as well as on "negative examples", which are samples from the modeled distribution $p(x)$ generated by means of Stochastic Gradient Langevin Dynamics (SGLD). Unfortunately, SGLD often fails to deliver negative samples of sufficient quality during the standard JEM training, which causes a very unbalanced contribution from the positive and negative examples when calculating gradients for JEM updates. As a consequence, the standard JEM training is quite unstable requiring careful tuning of hyper-parameters and frequent restarts when the training starts diverging. This makes it difficult to apply JEM to different neural network architectures, modalities, and tasks. In this work, we propose a training procedure that stabilizes SGLD-based JEM training (ST-JEM) by balancing the contribution from the positive and negative examples. We also propose to add an additional "regularization" term to the training objective -- MI between the input observations $x$ and output labels $y$ -- which encourages the JEM classifier to make more certain decisions about output labels. We demonstrate the effectiveness of our approach on the CIFAR10 and CIFAR100 tasks. We also consider the task of classifying phonemes in a speech signal, for which we were not able to train JEM without the proposed stabilization. We show that a convincing speech can be generated from the trained model. Alternatively, corrupted speech can be de-noised by bringing it closer to the modeled speech distribution using a few SGLD iterations. We also propose and discuss additional applications of the trained model.

Thomas Thebaud, Anna Favaro, Casey Chen et al.

Motor dysfunction is a common sign of neurodegenerative diseases (NDs) such as Parkinson's disease (PD) and Alzheimer's disease (AD), but may be difficult to detect, especially in the early stages. In this work, we examine the behavior of a wide array of interpretable features extracted from the handwriting signals of 113 subjects performing multiple tasks on a digital tablet, as part of the Neurological Signals dataset. The aim is to measure their effectiveness in characterizing NDs, including AD and PD. To this end, task-agnostic and task-specific features are extracted from 14 distinct tasks. Subsequently, through statistical analysis and a series of classification experiments, we investigate which features provide greater discriminative power between NDs and healthy controls and amongst different NDs. Preliminary results indicate that the tasks at hand can all be effectively leveraged to distinguish between the considered set of NDs, specifically by measuring the stability, the speed of writing, the time spent not writing, and the pressure variations between groups from our handcrafted interpretable features, which shows a statistically significant difference between groups, across multiple tasks. Using various binary classification algorithms on the computed features, we obtain up to 87% accuracy for the discrimination between AD and healthy controls (CTL), and up to 69% for the discrimination between PD and CTL.

Thomas Thebaud, Yuzhe Wang, Laureano Moro-Velazquez et al.

Speech-aware large language models (LLMs) can accept speech inputs, yet their training objectives largely emphasize linguistic content or specific fields such as emotions or the speaker's gender, leaving it unclear whether they encode speaker identity. First, we propose a model-agnostic scoring protocol that produces continuous verification scores for both API-only and open-weight models, using confidence scores or log-likelihood ratios from the Yes/No token probabilities. Using this protocol, we benchmark recent speech-aware LLMs and observe weak speaker discrimination (EERs above 20% on VoxCeleb1). Second, we introduce a lightweight augmentation that equips an LLM with ASV capability by injecting frozen ECAPA-TDNN speaker embeddings through a learned projection and training only LoRA adapters. On TinyLLaMA-1.1B, the resulting ECAPA-LLM achieves 1.03% EER on VoxCeleb1-E, approaching a dedicated speaker verification system while preserving a natural-language interface.

Tianyu Cao, Helin Wang, Ari Frummer et al.

Recent advances in generative models, such as diffusion and flow matching, have shown strong performance in audio tasks. However, speech enhancement (SE) models are typically trained on limited datasets and evaluated under narrow conditions, limiting real-world applicability. To address this, we propose DiT-Flow, a flow matching-based SE framework built on the latent Diffusion Transformer (DiT) backbone and trained for robustness across diverse distortions, including noise, reverberation, and compression. DiT-Flow operates on compact variational auto-encoders (VAEs)-derived latent features. We validated our approach on StillSonicSet, a synthetic yet acoustically realistic dataset composed of LibriSpeech, FSD50K, FMA, and 90 Matterport3D scenes. Experiments show that DiT-Flow consistently outperforms state-of-the-art generative SE models, demonstrating the effectiveness of flow matching in multi-condition speech enhancement. Despite ongoing efforts to expand synthetic data realism, a persistent bottleneck in SE is the inevitable mismatch between training and deployment conditions. By integrating LoRA with the MoE framework, we achieve both parameter-efficient and high-performance training for DiT-Flow robust to multiple distortions with using 4.9% percentage of the total parameters to obtain a better performance on five unseen distortions.

Kaavya Chaparala, Thomas Thebaud, Jesús Villalba López et al.

There are not enough established benchmarks for the task fo speech summarization. Creating new benchmarks demands human annotation, as LLMs could embed systemic errors and bias into datasets. We test ten annotation workflows varying input modality (audio, transcript, or both) and the inclusion of editing (self or peer-editing) to investigate potential quality tradeoffs from using human annotators to summarize audio. We compare human audio-based summaries to human transcript-based summaries to track the impact of the different information modalities on summary quality. We also compare the human outputs against four LLM benchmarks (three text, one audio) to examine whether human-written summaries are less informative than highly fluent automated outputs. We find that audio-based summaries are less informative and more compressed than transcript summaries. However, iterative peer-editing with audio mitigates this difference, enabling audio-based summaries to be as informative as their transcript counterparts and LLM summaries. These findings validate iterative peer-editing among human annotators for the creation of benchmarks informed by both lexical and prosodic information. This enables crucial dataset collection even in setting where transcripts are unavailable.

Sarah Laouedj, Yuzhe Wang, Jesus Villalba et al.

In this study, we explored the use of spectrograms to represent handwriting signals for assessing neurodegenerative diseases, including 42 healthy controls (CTL), 35 subjects with Parkinson's Disease (PD), 21 with Alzheimer's Disease (AD), and 15 with Parkinson's Disease Mimics (PDM). We applied CNN and CNN-BLSTM models for binary classification using both multi-channel fixed-size and frame-based spectrograms. Our results showed that handwriting tasks and spectrogram channel combinations significantly impacted classification performance. The highest F1-score (89.8%) was achieved for AD vs. CTL, while PD vs. CTL reached 74.5%, and PD vs. PDM scored 77.97%. CNN consistently outperformed CNN-BLSTM. Different sliding window lengths were tested for constructing frame-based spectrograms. A 1-second window worked best for AD, longer windows improved PD classification, and window length had little effect on PD vs. PDM.

Helin Wang, Jiarui Hai, Dading Chong et al.

Recent advancements in generative artificial intelligence have significantly transformed the field of style-captioned text-to-speech synthesis (CapTTS). However, adapting CapTTS to real-world applications remains challenging due to the lack of standardized, comprehensive datasets and limited research on downstream tasks built upon CapTTS. To address these gaps, we introduce CapSpeech, a new benchmark designed for a series of CapTTS-related tasks, including style-captioned text-to-speech synthesis with sound events (CapTTS-SE), accent-captioned TTS (AccCapTTS), emotion-captioned TTS (EmoCapTTS), and text-to-speech synthesis for chat agent (AgentTTS). CapSpeech comprises over 10 million machine-annotated audio-caption pairs and nearly 0.36 million human-annotated audio-caption pairs. In addition, we introduce two new datasets collected and recorded by a professional voice actor and experienced audio engineers, specifically for the AgentTTS and CapTTS-SE tasks. Alongside the datasets, we conduct comprehensive experiments using both autoregressive and non-autoregressive models on CapSpeech. Our results demonstrate high-fidelity and highly intelligible speech synthesis across a diverse range of speaking styles. To the best of our knowledge, CapSpeech is the largest available dataset offering comprehensive annotations for CapTTS-related tasks. The experiments and findings further provide valuable insights into the challenges of developing CapTTS systems.

Yuchen Yang, Thomas Thebaud, Najim Dehak

This paper introduces a general classifier based on WavLM features, to infer demographic characteristics, such as age, gender, native language, education, and country, from speech. Demographic feature prediction plays a crucial role in applications like language learning, accessibility, and digital forensics, enabling more personalized and inclusive technologies. Leveraging pretrained models for embedding extraction, the proposed framework identifies key acoustic and linguistic fea-tures associated with demographic attributes, achieving a Mean Absolute Error (MAE) of 4.94 for age prediction and over 99.81% accuracy for gender classification across various datasets. Our system improves upon existing models by up to relative 30% in MAE and up to relative 10% in accuracy and F1 scores across tasks, leveraging a diverse range of datasets and large pretrained models to ensure robustness and generalizability. This study offers new insights into speaker diversity and provides a strong foundation for future research in speech-based demographic profiling.

Helin Wang, Jiarui Hai, Dongchao Yang et al.

Target Speech Extraction (TSE) aims to isolate a target speaker's voice from a mixture of multiple speakers by leveraging speaker-specific cues, typically provided as auxiliary audio (a.k.a. cue audio). Although recent advancements in TSE have primarily employed discriminative models that offer high perceptual quality, these models often introduce unwanted artifacts, reduce naturalness, and are sensitive to discrepancies between training and testing environments. On the other hand, generative models for TSE lag in perceptual quality and intelligibility. To address these challenges, we present SoloSpeech, a novel cascaded generative pipeline that integrates compression, extraction, reconstruction, and correction processes. SoloSpeech features a speaker-embedding-free target extractor that utilizes conditional information from the cue audio's latent space, aligning it with the mixture audio's latent space to prevent mismatches. Evaluated on the widely-used Libri2Mix dataset, SoloSpeech achieves the new state-of-the-art intelligibility and quality in target speech extraction while demonstrating exceptional generalization on out-of-domain data and real-world scenarios.

Yen-Ju Lu, Jing Liu, Thomas Thebaud et al.

We introduce Condition-Aware Self-Supervised Learning Representation (CA-SSLR), a generalist conditioning model broadly applicable to various speech-processing tasks. Compared to standard fine-tuning methods that optimize for downstream models, CA-SSLR integrates language and speaker embeddings from earlier layers, making the SSL model aware of the current language and speaker context. This approach reduces the reliance on input audio features while preserving the integrity of the base SSLR. CA-SSLR improves the model's capabilities and demonstrates its generality on unseen tasks with minimal task-specific tuning. Our method employs linear modulation to dynamically adjust internal representations, enabling fine-grained adaptability without significantly altering the original model behavior. Experiments show that CA-SSLR reduces the number of trainable parameters, mitigates overfitting, and excels in under-resourced and unseen tasks. Specifically, CA-SSLR achieves a 10% relative reduction in LID errors, a 37% improvement in ASR CER on the ML-SUPERB benchmark, and a 27% decrease in SV EER on VoxCeleb-1, demonstrating its effectiveness.

Yaohan Guan, Pristina Wang, Najim Dehak et al.

In many science papers, "Figure 1" serves as the primary visual summary of the core research idea. These figures are visually simple yet conceptually rich, often requiring significant effort and iteration by human authors to get right, highlighting the difficulty of science visual communication. With this intuition, we introduce GENFIG1, a benchmark for generative AI models (e.g., Vision-Language Models). GENFIG1 evaluates models for their ability to produce figures that clearly express and motivate the central idea of a paper (title, abstract, introduction, and figure caption) as input. Solving GENFIG1 requires more than producing visually appealing graphics: the task entails reasoning for text-to-image generation that couples scientific understanding with visual synthesis. Specifically, models must (i) comprehend and grasp the technical concepts of the paper, (ii) identify the most salient ones, and (iii) design a coherent and aesthetically effective graphic that conveys those concepts visually and is faithful to the input. We curate the benchmark from papers published at top deep-learning conferences, apply stringent quality control, and introduce an automatic evaluation metric that correlates well with expert human judgments. We evaluate a suite of representative models on GENFIG1 and demonstrate that the task presents significant challenges, even for the best-performing systems. We hope this benchmark serves as a foundation for future progress in multimodal AI.

Alexandrine Fortier, Sonal Joshi, Thomas Thebaud et al.

In this work, we propose a multi-target backdoor attack against speaker identification using position-independent clicking sounds as triggers. Unlike previous single-target approaches, our method targets up to 50 speakers simultaneously, achieving success rates of up to 95.04%. To simulate more realistic attack conditions, we vary the signal-to-noise ratio between speech and trigger, demonstrating a trade-off between stealth and effectiveness. We further extend the attack to the speaker verification task by selecting the most similar training speaker - based on cosine similarity - as a proxy target. The attack is most effective when target and enrolled speaker pairs are highly similar, reaching success rates of up to 90% in such cases.

Sonal Joshi, Thomas Thebaud, Jesús Villalba et al.

Adversarial examples have proven to threaten speaker identification systems, and several countermeasures against them have been proposed. In this paper, we propose a method to detect the presence of adversarial examples, i.e., a binary classifier distinguishing between benign and adversarial examples. We build upon and extend previous work on attack type classification by exploring new architectures. Additionally, we introduce a method for identifying the victim model on which the adversarial attack is carried out. To achieve this, we generate a new dataset containing multiple attacks performed against various victim models. We achieve an AUC of 0.982 for attack detection, with no more than a 0.03 drop in performance for unknown attacks. Our attack classification accuracy (excluding benign) reaches 86.48% across eight attack types using our LightResNet34 architecture, while our victim model classification accuracy reaches 72.28% across four victim models.

Yen-Ju Lu, Kunxiao Gao, Mingrui Liang et al.

Recent audio language models can follow long conversations. However, research on emotion-aware or spoken dialogue summarization is constrained by the lack of data that links speech, summaries, and paralinguistic cues. We introduce Spoken DialogSum, the first corpus aligning raw conversational audio with factual summaries, emotion-rich summaries, and utterance-level labels for speaker age, gender, and emotion. The dataset is built in two stages: first, an LLM rewrites DialogSum scripts with Switchboard-style fillers and back-channels, then tags each utterance with emotion, pitch, and speaking rate. Second, an expressive TTS engine synthesizes speech from the tagged scripts, aligned with paralinguistic labels. Spoken DialogSum comprises 13,460 emotion-diverse dialogues, each paired with both a factual and an emotion-focused summary. We release an online demo at https://fatfat-emosum.github.io/EmoDialog-Sum-Audio-Samples/, with plans to release the full dataset in the near future. Baselines show that an Audio-LLM raises emotional-summary ROUGE-L by 28% relative to a cascaded ASR-LLM system, confirming the value of end-to-end speech modeling.

Yen-Ju Lu, Yashesh Gaur, Wei Zhou et al.

Auto-regressive speech-text models are typically pre-trained on a large number of interleaved sequences of text tokens and raw speech encoded as speech tokens using vector quantization. These models have demonstrated state-of-the-art performance in speech-to-speech understanding and generation benchmarks, together with promising scaling laws, primarily enabled by the representational alignment between text and speech. Nevertheless, they suffer from shortcomings, partly owing to the disproportionately longer sequences of speech tokens in contrast to textual tokens. This results in a large compute imbalance between modalities during pre-training as well as during inference, and a potential hindrance to effectively aligning speech and text, ultimately translating to several orders of magnitude slower scaling laws. We introduce the Latent Speech-Text Transformer (LST), which makes pre-training speech-text models more data-efficient by dynamically and inexpensively aggregating speech tokens into latent speech patches. These patches serve as higher-level units that can either align with corresponding textual units to aid capability transfer or even encapsulate common speech sequences like silences to be more compute-efficient. We show that LST outperforms vanilla approaches on speech-to-speech as well as text-to-text benchmarks in both data- and compute-controlled settings, the former indicating more effective representational alignment and the latter indicating steeper scaling laws for speech-text models. On HellaSwag story completion, LST achieves 6.5% absolute gain in speech accuracy under compute-controlled training and 5.3% under data-controlled training, while also improving text performance. We will release our models, code, and the evaluation data to facilitate further research.

Alexandrine Fortier, Thomas Thebaud, Jesús Villalba et al.

Large Language Models (LLMs) and their multimodal extensions are becoming increasingly popular. One common approach to enable multimodality is to cascade domain-specific encoders with an LLM, making the resulting model inherit vulnerabilities from all of its components. In this work, we present the first systematic study of audio backdoor attacks against speech language models. We demonstrate its effectiveness across four speech encoders and three datasets, covering four tasks: automatic speech recognition (ASR), speech emotion recognition, and gender and age prediction. The attack consistently achieves high success rates, ranging from 90.76% to 99.41%. To better understand how backdoors propagate, we conduct a component-wise analysis to identify the most vulnerable stages of the pipeline. Finally, we propose a fine-tuning-based defense that mitigates the threat of poisoned pretrained encoders.

Yen-Ju Lu, Thomas Thebaud, Laureano Moro-Velazquez et al.

We present Paired by the Teacher (PbT), a two-stage teacher-student pipeline that synthesizes accurate input-output pairs without human labels or parallel data. In many low-resource natural language generation (NLG) scenarios, practitioners may have only raw outputs, like highlights, recaps, or questions, or only raw inputs, such as articles, dialogues, or paragraphs, but seldom both. This mismatch forces small models to learn from very few examples or rely on costly, broad-scope synthetic examples produced by large LLMs. PbT addresses this by asking a teacher LLM to compress each unpaired example into a concise intermediate representation (IR), and training a student to reconstruct inputs from IRs. This enables outputs to be paired with student-generated inputs, yielding high-quality synthetic data. We evaluate PbT on five benchmarks-document summarization (XSum, CNNDM), dialogue summarization (SAMSum, DialogSum), and question generation (SQuAD)-as well as an unpaired setting on SwitchBoard (paired with DialogSum summaries). An 8B student trained only on PbT data outperforms models trained on 70 B teacher-generated corpora and other unsupervised baselines, coming within 1.2 ROUGE-L of human-annotated pairs and closing 82% of the oracle gap at one-third the annotation cost of direct synthesis. Human evaluation on SwitchBoard further confirms that only PbT produces concise, faithful summaries aligned with the target style, highlighting its advantage of generating in-domain sources that avoid the mismatch, limiting direct synthesis.

Junhyeok Lee, Helin Wang, Yaohan Guan et al.

We introduce MaskVCT, a zero-shot voice conversion (VC) model that offers multi-factor controllability through multiple classifier-free guidances (CFGs). While previous VC models rely on a fixed conditioning scheme, MaskVCT integrates diverse conditions in a single model. To further enhance robustness and control, the model can leverage continuous or quantized linguistic features to enhance intellgibility and speaker similarity, and can use or omit pitch contour to control prosody. These choices allow users to seamlessly balance speaker identity, linguistic content, and prosodic factors in a zero-shot VC setting. Extensive experiments demonstrate that MaskVCT achieves the best target speaker and accent similarities while obtaining competitive word and character error rates compared to existing baselines. Audio samples are available at https://maskvct.github.io/.

Gabrielle Chavez, Laureano Moro-Velazquez, Ankur Butala et al.

Handwriting is significantly affected by neurological disorders (ND) such as Parkinson's disease (PD) and Alzheimer's disease (AD). Prior works have analyzed handwriting tasks using feature-based approaches or computer-vision techniques, but these methods have struggled to generalize across multiple datasets, particularly between temporal features represented as time-series and images. We propose a framework that leverages both time-series and images of handwriting through a joint classifier, based on a ResNet50 pretrained on ImageNet-1k. Binary classification experiments demonstrate state-of-the-art performances on existing time-series and image datasets, with significant improvement on specific drawing and writing tasks from the NeuroLogical Signals (NLS) dataset. In particular, the proposed model demonstrates improved performance on Draw Clock and Spiral tasks. Additionally, cross-dataset and multi-dataset experiments were consistently able to achieve high F1 scores, up to 98 for PD detection, highlighting the potential of the proposed model to generalize over different forms of handwriting signals, and enhance the detection of motor deficits in ND.

Thomas Thebaud, Yen-Ju Lu, Matthew Wiesner et al.

In dialogue transcription pipelines, Large Language Models (LLMs) are frequently employed in post-processing to improve grammar, punctuation, and readability. We explore a complementary post-processing step: enriching transcribed dialogues by adding metadata tags for speaker characteristics such as age, gender, and emotion. Some of the tags are global to the entire dialogue, while some are time-variant. Our approach couples frozen audio foundation models, such as Whisper or WavLM, with a frozen LLAMA language model to infer these speaker attributes, without requiring task-specific fine-tuning of either model. Using lightweight, efficient connectors to bridge audio and language representations, we achieve competitive performance on speaker profiling tasks while preserving modularity and speed. Additionally, we demonstrate that a frozen LLAMA model can compare x-vectors directly, achieving an Equal Error Rate of 8.8% in some scenarios.

Piotr Żelasko, Siyuan Feng, Laureano Moro Velazquez et al.

The high cost of data acquisition makes Automatic Speech Recognition (ASR) model training problematic for most existing languages, including languages that do not even have a written script, or for which the phone inventories remain unknown. Past works explored multilingual training, transfer learning, as well as zero-shot learning in order to build ASR systems for these low-resource languages. While it has been shown that the pooling of resources from multiple languages is helpful, we have not yet seen a successful application of an ASR model to a language unseen during training. A crucial step in the adaptation of ASR from seen to unseen languages is the creation of the phone inventory of the unseen language. The ultimate goal of our work is to build the phone inventory of a language unseen during training in an unsupervised way without any knowledge about the language. In this paper, we 1) investigate the influence of different factors (i.e., model architecture, phonotactic model, type of speech representation) on phone recognition in an unknown language; 2) provide an analysis of which phones transfer well across languages and which do not in order to understand the limitations of and areas for further improvement for automatic phone inventory creation; and 3) present different methods to build a phone inventory of an unseen language in an unsupervised way. To that end, we conducted mono-, multi-, and crosslingual experiments on a set of 13 phonetically diverse languages and several in-depth analyses. We found a number of universal phone tokens (IPA symbols) that are well-recognized cross-linguistically. Through a detailed analysis of results, we conclude that unique sounds, similar sounds, and tone languages remain a major challenge for phonetic inventory discovery.

Amir Hussein, Shammur Absar Chowdhury, Ahmed Abdelali et al.

The pervasiveness of intra-utterance code-switching (CS) in spoken content requires that speech recognition (ASR) systems handle mixed language. Designing a CS-ASR system has many challenges, mainly due to data scarcity, grammatical structure complexity, and domain mismatch. The most common method for addressing CS is to train an ASR system with the available transcribed CS speech, along with monolingual data. In this work, we propose a zero-shot learning methodology for CS-ASR by augmenting the monolingual data with artificially generating CS text. We based our approach on random lexical replacements and Equivalence Constraint (EC) while exploiting aligned translation pairs to generate random and grammatically valid CS content. Our empirical results show a 65.5% relative reduction in language model perplexity, and 7.7% in ASR WER on two ecologically valid CS test sets. The human evaluation of the generated text using EC suggests that more than 80% is of adequate quality.

Saurabhchand Bhati, Jesús Villalba, Piotr Żelasko et al.

Typically, unsupervised segmentation of speech into the phone and word-like units are treated as separate tasks and are often done via different methods which do not fully leverage the inter-dependence of the two tasks. Here, we unify them and propose a technique that can jointly perform both, showing that these two tasks indeed benefit from each other. Recent attempts employ self-supervised learning, such as contrastive predictive coding (CPC), where the next frame is predicted given past context. However, CPC only looks at the audio signal's frame-level structure. We overcome this limitation with a segmental contrastive predictive coding (SCPC) framework to model the signal structure at a higher level, e.g., phone level. A convolutional neural network learns frame-level representation from the raw waveform via noise-contrastive estimation (NCE). A differentiable boundary detector finds variable-length segments, which are then used to optimize a segment encoder via NCE to learn segment representations. The differentiable boundary detector allows us to train frame-level and segment-level encoders jointly. Experiments show that our single model outperforms existing phone and word segmentation methods on TIMIT and Buckeye datasets. We discover that phone class impacts the boundary detection performance, and the boundaries between successive vowels or semivowels are the most difficult to identify. Finally, we use SCPC to extract speech features at the segment level rather than at uniformly spaced frame level (e.g., 10 ms) and produce variable rate representations that change according to the contents of the utterance. We can lower the feature extraction rate from the typical 100 Hz to as low as 14.5 Hz on average while still outperforming the MFCC features on the linear phone classification task.

Jejin Cho, Jesus Villalba, Najim Dehak

This technical report describes Johns Hopkins University speaker recognition system submitted to Voxceleb Speaker Recognition Challenge 2021 Track 3: Self-supervised speaker verification (closed). Our overall training process is similar to the proposed one from the first place team in the last year's VoxSRC2020 challenge. The main difference is a recently proposed non-contrastive self-supervised method in computer vision (CV), distillation with no labels (DINO), is used to train our initial model, which outperformed the last year's contrastive learning based on momentum contrast (MoCo). Also, this requires only a few iterations in the iterative clustering stage, where pseudo labels for supervised embedding learning are updated based on the clusters of the embeddings generated from a model that is continually fine-tuned over iterations. In the final stage, Res2Net50 is trained on the final pseudo labels from the iterative clustering stage. This is our best submitted model to the challenge, showing 1.89, 6.50, and 6.89 in EER(%) in voxceleb1 test o, VoxSRC-21 validation, and test trials, respectively.

Raghavendra Pappagari, Piotr Żelasko, Jesús Villalba et al.

Speech emotion recognition is the task of recognizing the speaker's emotional state given a recording of their utterance. While most of the current approaches focus on inferring emotion from isolated utterances, we argue that this is not sufficient to achieve conversational emotion recognition (CER) which deals with recognizing emotions in conversations. In this work, we propose several approaches for CER by treating it as a sequence labeling task. We investigated transformer architecture for CER and, compared it with ResNet-34 and BiLSTM architectures in both contextual and context-less scenarios using IEMOCAP corpus. Based on the inner workings of the self-attention mechanism, we proposed DiverseCatAugment (DCA), an augmentation scheme, which improved the transformer model performance by an absolute 3.3% micro-f1 on conversations and 3.6% on isolated utterances. We further enhanced the performance by introducing an interlocutor-aware transformer model where we learn a dictionary of interlocutor index embeddings to exploit diarized conversations.

Raghavendra Pappagari, Piotr Żelasko, Agnieszka Mikołajczyk et al.

Capitalization and punctuation are important cues for comprehending written texts and conversational transcripts. Yet, many ASR systems do not produce punctuated and case-formatted speech transcripts. We propose to use a multi-task system that can exploit the relations between casing and punctuation to improve their prediction performance. Whereas text data for predicting punctuation and truecasing is seemingly abundant, we argue that written text resources are inadequate as training data for conversational models. We quantify the mismatch between written and conversational text domains by comparing the joint distributions of punctuation and word cases, and by testing our model cross-domain. Further, we show that by training the model in the written text domain and then transfer learning to conversations, we can achieve reasonable performance with less data.

Piotr Żelasko, Raghavendra Pappagari, Najim Dehak

Dialog acts can be interpreted as the atomic units of a conversation, more fine-grained than utterances, characterized by a specific communicative function. The ability to structure a conversational transcript as a sequence of dialog acts -- dialog act recognition, including the segmentation -- is critical for understanding dialog. We apply two pre-trained transformer models, XLNet and Longformer, to this task in English and achieve strong results on Switchboard Dialog Act and Meeting Recorder Dialog Act corpora with dialog act segmentation error rates (DSER) of 8.4% and 14.2%. To understand the key factors affecting dialog act recognition, we perform a comparative analysis of models trained under different conditions. We find that the inclusion of a broader conversational context helps disambiguate many dialog act classes, especially those infrequent in the training data. The presence of punctuation in the transcripts has a massive effect on the models' performance, and a detailed analysis reveals specific segmentation patterns observed in its absence. Finally, we find that the label set specificity does not affect dialog act segmentation performance. These findings have significant practical implications for spoken language understanding applications that depend heavily on a good-quality segmentation being available.

Nanxin Chen, Yu Zhang, Heiga Zen et al.

This paper introduces WaveGrad 2, a non-autoregressive generative model for text-to-speech synthesis. WaveGrad 2 is trained to estimate the gradient of the log conditional density of the waveform given a phoneme sequence. The model takes an input phoneme sequence, and through an iterative refinement process, generates an audio waveform. This contrasts to the original WaveGrad vocoder which conditions on mel-spectrogram features, generated by a separate model. The iterative refinement process starts from Gaussian noise, and through a series of refinement steps (e.g., 50 steps), progressively recovers the audio sequence. WaveGrad 2 offers a natural way to trade-off between inference speed and sample quality, through adjusting the number of refinement steps. Experiments show that the model can generate high fidelity audio, approaching the performance of a state-of-the-art neural TTS system. We also report various ablation studies over different model configurations. Audio samples are available at https://wavegrad.github.io/v2.

Amir Hussein, Shammur Chowdhury, Najim Dehak et al.

The success in designing Code-Switching (CS) ASR often depends on the availability of the transcribed CS resources. Such dependency harms the development of ASR in low-resourced languages such as Bengali and Hindi. In this paper, we exploit the transfer learning approach to design End-to-End (E2E) CS ASR systems for the two low-resourced language pairs using different monolingual speech data and a small set of noisy CS data. We trained the CS-ASR, following two steps: (i) building a robust bilingual ASR system using a convolution-augmented transformer (Conformer) based acoustic model and n-gram language model, and (ii) fine-tuned the entire E2E ASR with limited noisy CS data. We tested our method on MUCS 2021 challenge and achieved 3rd place in the CS track. We then tested the proposed method using noisy CS data released for Hindi-English and Bengali-English pairs in Multilingual and Code-Switching ASR Challenges for Low Resource Indian Languages (MUCS 2021) and achieved 3rd place in the CS track. Unlike, the leading two systems that benefited from crawling YouTube and learning transliteration pairs, our proposed transfer learning approach focused on using only the limited CS data with no data-cleaning or data re-segmentation. Our approach achieved 14.1% relative gain in word error rate (WER) in Hindi-English and 27.1% in Bengali-English. We provide detailed guidelines on the steps to finetune the self-attention based model for limited data for ASR. Moreover, we release the code and recipe used in this paper.

Saurabhchand Bhati, Jesús Villalba, Piotr Żelasko et al.

Automatic detection of phoneme or word-like units is one of the core objectives in zero-resource speech processing. Recent attempts employ self-supervised training methods, such as contrastive predictive coding (CPC), where the next frame is predicted given past context. However, CPC only looks at the audio signal's frame-level structure. We overcome this limitation with a segmental contrastive predictive coding (SCPC) framework that can model the signal structure at a higher level e.g. at the phoneme level. In this framework, a convolutional neural network learns frame-level representation from the raw waveform via noise-contrastive estimation (NCE). A differentiable boundary detector finds variable-length segments, which are then used to optimize a segment encoder via NCE to learn segment representations. The differentiable boundary detector allows us to train frame-level and segment-level encoders jointly. Typically, phoneme and word segmentation are treated as separate tasks. We unify them and experimentally show that our single model outperforms existing phoneme and word segmentation methods on TIMIT and Buckeye datasets. We analyze the impact of boundary threshold and when is the right time to include the segmental loss in the learning process.

Piotr Żelasko, Sonal Joshi, Yiwen Shao et al.

The ubiquitous presence of machine learning systems in our lives necessitates research into their vulnerabilities and appropriate countermeasures. In particular, we investigate the effectiveness of adversarial attacks and defenses against automatic speech recognition (ASR) systems. We select two ASR models - a thoroughly studied DeepSpeech model and a more recent Espresso framework Transformer encoder-decoder model. We investigate two threat models: a denial-of-service scenario where fast gradient-sign method (FGSM) or weak projected gradient descent (PGD) attacks are used to degrade the model's word error rate (WER); and a targeted scenario where a more potent imperceptible attack forces the system to recognize a specific phrase. We find that the attack transferability across the investigated ASR systems is limited. To defend the model, we use two preprocessing defenses: randomized smoothing and WaveGAN-based vocoder, and find that they significantly improve the model's adversarial robustness. We show that a WaveGAN vocoder can be a useful countermeasure to adversarial attacks on ASR systems - even when it is jointly attacked with the ASR, the target phrases' word error rate is high.

Sonal Joshi, Jesús Villalba, Piotr Żelasko et al.

Adversarial examples to speaker recognition (SR) systems are generated by adding a carefully crafted noise to the speech signal to make the system fail while being imperceptible to humans. Such attacks pose severe security risks, making it vital to deep-dive and understand how much the state-of-the-art SR systems are vulnerable to these attacks. Moreover, it is of greater importance to propose defenses that can protect the systems against these attacks. Addressing these concerns, this paper at first investigates how state-of-the-art x-vector based SR systems are affected by white-box adversarial attacks, i.e., when the adversary has full knowledge of the system. x-Vector based SR systems are evaluated against white-box adversarial attacks common in the literature like fast gradient sign method (FGSM), basic iterative method (BIM)--a.k.a. iterative-FGSM--, projected gradient descent (PGD), and Carlini-Wagner (CW) attack. To mitigate against these attacks, the paper proposes four pre-processing defenses. It evaluates them against powerful adaptive white-box adversarial attacks, i.e., when the adversary has full knowledge of the system, including the defense. The four pre-processing defenses--viz. randomized smoothing, DefenseGAN, variational autoencoder (VAE), and Parallel WaveGAN vocoder (PWG) are compared against the baseline defense of adversarial training. Conclusions indicate that SR systems were extremely vulnerable under BIM, PGD, and CW attacks. Among the proposed pre-processing defenses, PWG combined with randomized smoothing offers the most protection against the attacks, with accuracy averaging 93% compared to 52% in the undefended system and an absolute improvement >90% for BIM attacks with $L_\infty>0.001$ and CW attack.

Nanxin Chen, Piotr Żelasko, Jesús Villalba et al.

This paper introduces a novel method to diagnose the source-target attention in state-of-the-art end-to-end speech recognition models with joint connectionist temporal classification (CTC) and attention training. Our method is based on the fact that both, CTC and source-target attention, are acting on the same encoder representations. To understand the functionality of the attention, CTC is applied to compute the token posteriors given the attention outputs. We found that the source-target attention heads are able to predict several tokens ahead of the current one. Inspired by the observation, a new regularization method is proposed which leverages CTC to make source-target attention more focused on the frames corresponding to the output token being predicted by the decoder. Experiments reveal stable improvements up to 7\% and 13\% relatively with the proposed regularization on TED-LIUM 2 and LibriSpeech.

Raghavendra Pappagari, Jesús Villalba, Piotr Żelasko et al.

Data augmentation is a widely used strategy for training robust machine learning models. It partially alleviates the problem of limited data for tasks like speech emotion recognition (SER), where collecting data is expensive and challenging. This study proposes CopyPaste, a perceptually motivated novel augmentation procedure for SER. Assuming that the presence of emotions other than neutral dictates a speaker's overall perceived emotion in a recording, concatenation of an emotional (emotion E) and a neutral utterance can still be labeled with emotion E. We hypothesize that SER performance can be improved using these concatenated utterances in model training. To verify this, three CopyPaste schemes are tested on two deep learning models: one trained independently and another using transfer learning from an x-vector model, a speaker recognition model. We observed that all three CopyPaste schemes improve SER performance on all the three datasets considered: MSP-Podcast, Crema-D, and IEMOCAP. Additionally, CopyPaste performs better than noise augmentation and, using them together improves the SER performance further. Our experiments on noisy test sets suggested that CopyPaste is effective even in noisy test conditions.

Siyuan Feng, Piotr Żelasko, Laureano Moro-Velázquez et al.

The idea of combining multiple languages' recordings to train a single automatic speech recognition (ASR) model brings the promise of the emergence of universal speech representation. Recently, a Transformer encoder-decoder model has been shown to leverage multilingual data well in IPA transcriptions of languages presented during training. However, the representations it learned were not successful in zero-shot transfer to unseen languages. Because that model lacks an explicit factorization of the acoustic model (AM) and language model (LM), it is unclear to what degree the performance suffered from differences in pronunciation or the mismatch in phonotactics. To gain more insight into the factors limiting zero-shot ASR transfer, we replace the encoder-decoder with a hybrid ASR system consisting of a separate AM and LM. Then, we perform an extensive evaluation of monolingual, multilingual, and crosslingual (zero-shot) acoustic and language models on a set of 13 phonetically diverse languages. We show that the gain from modeling crosslingual phonotactics is limited, and imposing a too strong model can hurt the zero-shot transfer. Furthermore, we find that a multilingual LM hurts a multilingual ASR system's performance, and retaining only the target language's phonotactic data in LM training is preferable.

Saurabh Kataria, Jesús Villalba, Najim Dehak

Deep learning based speech denoising still suffers from the challenge of improving perceptual quality of enhanced signals. We introduce a generalized framework called Perceptual Ensemble Regularization Loss (PERL) built on the idea of perceptual losses. Perceptual loss discourages distortion to certain speech properties and we analyze it using six large-scale pre-trained models: speaker classification, acoustic model, speaker embedding, emotion classification, and two self-supervised speech encoders (PASE+, wav2vec 2.0). We first build a strong baseline (w/o PERL) using Conformer Transformer Networks on the popular enhancement benchmark called VCTK-DEMAND. Using auxiliary models one at a time, we find acoustic event and self-supervised model PASE+ to be most effective. Our best model (PERL-AE) only uses acoustic event model (utilizing AudioSet) to outperform state-of-the-art methods on major perceptual metrics. To explore if denoising can leverage full framework, we use all networks but find that our seven-loss formulation suffers from the challenges of Multi-Task Learning. Finally, we report a critical observation that state-of-the-art Multi-Task weight learning methods cannot outperform hand tuning, perhaps due to challenges of domain mismatch and weak complementarity of losses.

Jaejin Cho, Piotr Zelasko, Jesus Villalba et al.

Zero-shot multi-speaker Text-to-Speech (TTS) generates target speaker voices given an input text and the corresponding speaker embedding. In this work, we investigate the effectiveness of the TTS reconstruction objective to improve representation learning for speaker verification. We jointly trained end-to-end Tacotron 2 TTS and speaker embedding networks in a self-supervised fashion. We hypothesize that the embeddings will contain minimal phonetic information since the TTS decoder will obtain that information from the textual input. TTS reconstruction can also be combined with speaker classification to enhance these embeddings further. Once trained, the speaker encoder computes representations for the speaker verification task, while the rest of the TTS blocks are discarded. We investigated training TTS from either manual or ASR-generated transcripts. The latter allows us to train embeddings on datasets without manual transcripts. We compared ASR transcripts and Kaldi phone alignments as TTS inputs, showing that the latter performed better due to their finer resolution. Unsupervised TTS embeddings improved EER by 2.06\% absolute with regard to i-vectors for the LibriTTS dataset. TTS with speaker classification loss improved EER by 0.28\% and 0.73\% absolutely from a model using only speaker classification loss in LibriTTS and Voxceleb1 respectively.

Saurabhchand Bhati, Jesús Villalba, Piotr Żelasko et al.

Unsupervised spoken term discovery consists of two tasks: finding the acoustic segment boundaries and labeling acoustically similar segments with the same labels. We perform segmentation based on the assumption that the frame feature vectors are more similar within a segment than across the segments. Therefore, for strong segmentation performance, it is crucial that the features represent the phonetic properties of a frame more than other factors of variability. We achieve this via a self-expressing autoencoder framework. It consists of a single encoder and two decoders with shared weights. The encoder projects the input features into a latent representation. One of the decoders tries to reconstruct the input from these latent representations and the other from the self-expressed version of them. We use the obtained features to segment and cluster the speech data. We evaluate the performance of the proposed method in the Zero Resource 2020 challenge unit discovery task. The proposed system consistently outperforms the baseline, demonstrating the usefulness of the method in learning representations.

Phani Sankar Nidadavolu, Saurabh Kataria, Paola García-Perera et al.

We investigated an enhancement and a domain adaptation approach to make speaker verification systems robust to perturbations of far-field speech. In the enhancement approach, using paired (parallel) reverberant-clean speech, we trained a supervised Generative Adversarial Network (GAN) along with a feature mapping loss. For the domain adaptation approach, we trained a Cycle Consistent Generative Adversarial Network (CycleGAN), which maps features from far-field domain to the speaker embedding training domain. This was trained on unpaired data in an unsupervised manner. Both networks, termed Supervised Enhancement Network (SEN) and Domain Adaptation Network (DAN) respectively, were trained with multi-task objectives in (filter-bank) feature domain. On a simulated test setup, we first note the benefit of using feature mapping (FM) loss along with adversarial loss in SEN. Then, we tested both supervised and unsupervised approaches on several real noisy datasets. We observed relative improvements ranging from 2% to 31% in terms of DCF. Using three training schemes, we also establish the effectiveness of the novel DAN approach.

Piotr Żelasko, Laureano Moro-Velázquez, Mark Hasegawa-Johnson et al.

Only a handful of the world's languages are abundant with the resources that enable practical applications of speech processing technologies. One of the methods to overcome this problem is to use the resources existing in other languages to train a multilingual automatic speech recognition (ASR) model, which, intuitively, should learn some universal phonetic representations. In this work, we focus on gaining a deeper understanding of how general these representations might be, and how individual phones are getting improved in a multilingual setting. To that end, we select a phonetically diverse set of languages, and perform a series of monolingual, multilingual and crosslingual (zero-shot) experiments. The ASR is trained to recognize the International Phonetic Alphabet (IPA) token sequences. We observe significant improvements across all languages in the multilingual setting, and stark degradation in the crosslingual setting, where the model, among other errors, considers Javanese as a tone language. Notably, as little as 10 hours of the target language training data tremendously reduces ASR error rates. Our analysis uncovered that even the phones that are unique to a single language can benefit greatly from adding training data from other languages - an encouraging result for the low-resource speech community.

Łukasz Augustyniak, Piotr Szymanski, Mikołaj Morzy et al.

Automatic Speech Recognition (ASR) systems introduce word errors, which often confuse punctuation prediction models, turning punctuation restoration into a challenging task. These errors usually take the form of homonyms. We show how retrofitting of the word embeddings on the domain-specific data can mitigate ASR errors. Our main contribution is a method for better alignment of homonym embeddings and the validation of the presented method on the punctuation prediction task. We record the absolute improvement in punctuation prediction accuracy between 6.2% (for question marks) to 9% (for periods) when compared with the state-of-the-art model.

Raghavendra Pappagari, Tianzi Wang, Jesus Villalba et al.

In this work, we explore the dependencies between speaker recognition and emotion recognition. We first show that knowledge learned for speaker recognition can be reused for emotion recognition through transfer learning. Then, we show the effect of emotion on speaker recognition. For emotion recognition, we show that using a simple linear model is enough to obtain good performance on the features extracted from pre-trained models such as the x-vector model. Then, we improve emotion recognition performance by fine-tuning for emotion classification. We evaluated our experiments on three different types of datasets: IEMOCAP, MSP-Podcast, and Crema-D. By fine-tuning, we obtained 30.40%, 7.99%, and 8.61% absolute improvement on IEMOCAP, MSP-Podcast, and Crema-D respectively over baseline model with no pre-training. Finally, we present results on the effect of emotion on speaker verification. We observed that speaker verification performance is prone to changes in test speaker emotions. We found that trials with angry utterances performed worst in all three datasets. We hope our analysis will initiate a new line of research in the speaker recognition community.

Saurabh Kataria, Phani Sankar Nidadavolu, Jesús Villalba et al.

Data augmentation is conventionally used to inject robustness in Speaker Verification systems. Several recently organized challenges focus on handling novel acoustic environments. Deep learning based speech enhancement is a modern solution for this. Recently, a study proposed to optimize the enhancement network in the activation space of a pre-trained auxiliary network. This methodology, called deep feature loss, greatly improved over the state-of-the-art conventional x-vector based system on a children speech dataset called BabyTrain. This work analyzes various facets of that approach and asks few novel questions in that context. We first search for optimal number of auxiliary network activations, training data, and enhancement feature dimension. Experiments reveal the importance of Signal-to-Noise Ratio filtering that we employ to create a large, clean, and naturalistic corpus for enhancement network training. To counter the "mismatch" problem in enhancement, we find enhancing front-end (x-vector network) data helpful while harmful for the back-end (Probabilistic Linear Discriminant Analysis (PLDA)). Importantly, we find enhanced signals contain complementary information to original. Established by combining them in front-end, this gives ~40% relative improvement over the baseline. We also do an ablation study to remove a noise class from x-vector data augmentation and, for such systems, we establish the utility of enhancement regardless of whether it has seen that noise class itself during training. Finally, we design several dereverberation schemes to conclude ineffectiveness of deep feature loss enhancement scheme for this task.

Paola Garcia, Jesus Villalba, Herve Bredin et al.

This paper presents the problems and solutions addressed at the JSALT workshop when using a single microphone for speaker detection in adverse scenarios. The main focus was to tackle a wide range of conditions that go from meetings to wild speech. We describe the research threads we explored and a set of modules that was successful for these scenarios. The ultimate goal was to explore speaker detection; but our first finding was that an effective diarization improves detection, and not having a diarization stage impoverishes the performance. All the different configurations of our research agree on this fact and follow a main backbone that includes diarization as a previous stage. With this backbone, we analyzed the following problems: voice activity detection, how to deal with noisy signals, domain mismatch, how to improve the clustering; and the overall impact of previous stages in the final speaker detection. In this paper, we show partial results for speaker diarizarion to have a better understanding of the problem and we present the final results for speaker detection.