Abdelrahman Mohamed

Guan-Ting Lin, Yung-Sung Chuang, Ho-Lam Chung et al. · meta-ai, mit

Spoken Question Answering (SQA) is to find the answer from a spoken document given a question, which is crucial for personal assistants when replying to the queries from the users. Existing SQA methods all rely on Automatic Speech Recognition (ASR) transcripts. Not only does ASR need to be trained with massive annotated data that are time and cost-prohibitive to collect for low-resourced languages, but more importantly, very often the answers to the questions include name entities or out-of-vocabulary words that cannot be recognized correctly. Also, ASR aims to minimize recognition errors equally over all words, including many function words irrelevant to the SQA task. Therefore, SQA without ASR transcripts (textless) is always highly desired, although known to be very difficult. This work proposes Discrete Spoken Unit Adaptive Learning (DUAL), leveraging unlabeled data for pre-training and fine-tuned by the SQA downstream task. The time intervals of spoken answers can be directly predicted from spoken documents. We also release a new SQA benchmark corpus, NMSQA, for data with more realistic scenarios. We empirically showed that DUAL yields results comparable to those obtained by cascading ASR and text QA model and robust to real-world data. Our code and model will be open-sourced.

Abdelrahman Mohamed, Hung-yi Lee, Lasse Borgholt et al. · meta-ai, mit

Although supervised deep learning has revolutionized speech and audio processing, it has necessitated the building of specialist models for individual tasks and application scenarios. It is likewise difficult to apply this to dialects and languages for which only limited labeled data is available. Self-supervised representation learning methods promise a single universal model that would benefit a wide variety of tasks and domains. Such methods have shown success in natural language processing and computer vision domains, achieving new levels of performance while reducing the number of labels required for many downstream scenarios. Speech representation learning is experiencing similar progress in three main categories: generative, contrastive, and predictive methods. Other approaches rely on multi-modal data for pre-training, mixing text or visual data streams with speech. Although self-supervised speech representation is still a nascent research area, it is closely related to acoustic word embedding and learning with zero lexical resources, both of which have seen active research for many years. This review presents approaches for self-supervised speech representation learning and their connection to other research areas. Since many current methods focus solely on automatic speech recognition as a downstream task, we review recent efforts on benchmarking learned representations to extend the application beyond speech recognition.

Hsiang-Sheng Tsai, Heng-Jui Chang, Wen-Chin Huang et al. · meta-ai, mit

Transfer learning has proven to be crucial in advancing the state of speech and natural language processing research in recent years. In speech, a model pre-trained by self-supervised learning transfers remarkably well on multiple tasks. However, the lack of a consistent evaluation methodology is limiting towards a holistic understanding of the efficacy of such models. SUPERB was a step towards introducing a common benchmark to evaluate pre-trained models across various speech tasks. In this paper, we introduce SUPERB-SG, a new benchmark focused on evaluating the semantic and generative capabilities of pre-trained models by increasing task diversity and difficulty over SUPERB. We use a lightweight methodology to test the robustness of representations learned by pre-trained models under shifts in data domain and quality across different types of tasks. It entails freezing pre-trained model parameters, only using simple task-specific trainable heads. The goal is to be inclusive of all researchers, and encourage efficient use of computational resources. We also show that the task diversity of SUPERB-SG coupled with limited task supervision is an effective recipe for evaluating the generalizability of model representation.

Paden Tomasello, Akshat Shrivastava, Daniel Lazar et al. · meta-ai, uw

End-to-end spoken language understanding (SLU) predicts intent directly from audio using a single model. It promises to improve the performance of assistant systems by leveraging acoustic information lost in the intermediate textual representation and preventing cascading errors from Automatic Speech Recognition (ASR). Further, having one unified model has efficiency advantages when deploying assistant systems on-device. However, the limited number of public audio datasets with semantic parse labels hinders the research progress in this area. In this paper, we release the Spoken Task-Oriented semantic Parsing (STOP) dataset, the largest and most complex SLU dataset to be publicly available. Additionally, we define low-resource splits to establish a benchmark for improving SLU when limited labeled data is available. Furthermore, in addition to the human-recorded audio, we are releasing a TTS-generated version to benchmark the performance for low-resource domain adaptation of end-to-end SLU systems. Initial experimentation show end-to-end SLU models performing slightly worse than their cascaded counterparts, which we hope encourages future work in this direction.

Tzu-hsun Feng, Annie Dong, Ching-Feng Yeh et al. · meta-ai, mit

We present the SUPERB challenge at SLT 2022, which aims at learning self-supervised speech representation for better performance, generalization, and efficiency. The challenge builds upon the SUPERB benchmark and implements metrics to measure the computation requirements of self-supervised learning (SSL) representation and to evaluate its generalizability and performance across the diverse SUPERB tasks. The SUPERB benchmark provides comprehensive coverage of popular speech processing tasks, from speech and speaker recognition to audio generation and semantic understanding. As SSL has gained interest in the speech community and showed promising outcomes, we envision the challenge to uplevel the impact of SSL techniques by motivating more practical designs of techniques beyond task performance. We summarize the results of 14 submitted models in this paper. We also discuss the main findings from those submissions and the future directions of SSL research.

Yun Tang, Hongyu Gong, Ning Dong et al. · meta-ai

We describe a method to jointly pre-train speech and text in an encoder-decoder modeling framework for speech translation and recognition. The proposed method incorporates four self-supervised and supervised subtasks for cross modality learning. A self-supervised speech subtask leverages unlabelled speech data, and a (self-)supervised text to text subtask makes use of abundant text training data. Two auxiliary supervised speech tasks are included to unify speech and text modeling space. Our contribution lies in integrating linguistic information from the text corpus into the speech pre-training. Detailed analysis reveals learning interference among subtasks. Two pre-training configurations for speech translation and recognition, respectively, are presented to alleviate subtask interference. Our experiments show the proposed method can effectively fuse speech and text information into one model. It achieves between 1.7 and 2.3 BLEU improvement above the state of the art on the MuST-C speech translation dataset and comparable WERs to wav2vec 2.0 on the Librispeech speech recognition task.

Siddharth Dalmia, Dmytro Okhonko, Mike Lewis et al. · cmu, meta-ai

State-of-the-art encoder-decoder models (e.g. for machine translation (MT) or automatic speech recognition (ASR)) are constructed and trained end-to-end as an atomic unit. No component of the model can be (re-)used without the others, making it impossible to share parts, e.g. a high resourced decoder, across tasks. We describe LegoNN, a procedure for building encoder-decoder architectures in a way so that its parts can be applied to other tasks without the need for any fine-tuning. To achieve this reusability, the interface between encoder and decoder modules is grounded to a sequence of marginal distributions over a pre-defined discrete vocabulary. We present two approaches for ingesting these marginals; one is differentiable, allowing the flow of gradients across the entire network, and the other is gradient-isolating. To enable the portability of decoder modules between MT tasks for different source languages and across other tasks like ASR, we introduce a modality agnostic encoder which consists of a length control mechanism to dynamically adapt encoders' output lengths in order to match the expected input length range of pre-trained decoders. We present several experiments to demonstrate the effectiveness of LegoNN models: a trained language generation LegoNN decoder module from German-English (De-En) MT task can be reused without any fine-tuning for the Europarl English ASR and the Romanian-English (Ro-En) MT tasks, matching or beating the performance of baseline. After fine-tuning, LegoNN models improve the Ro-En MT task by 1.5 BLEU points and achieve 12.5% relative WER reduction on the Europarl ASR task. To show how the approach generalizes, we compose a LegoNN ASR model from three modules -- each has been learned within different end-to-end trained models on three different datasets -- achieving an overall WER reduction of 19.5%.

Yuan Tseng, Layne Berry, Yi-Ting Chen et al. · meta-ai, mit

Audio-visual representation learning aims to develop systems with human-like perception by utilizing correlation between auditory and visual information. However, current models often focus on a limited set of tasks, and generalization abilities of learned representations are unclear. To this end, we propose the AV-SUPERB benchmark that enables general-purpose evaluation of unimodal audio/visual and bimodal fusion representations on 7 datasets covering 5 audio-visual tasks in speech and audio processing. We evaluate 5 recent self-supervised models and show that none of these models generalize to all tasks, emphasizing the need for future study on improving universal model performance. In addition, we show that representations may be improved with intermediate-task fine-tuning and audio event classification with AudioSet serves as a strong intermediate task. We release our benchmark with evaluation code and a model submission platform to encourage further research in audio-visual learning.

Abdelrahman Mohamed, Rushali Grandhe, K J Joseph et al.

In class incremental learning (CIL) setting, groups of classes are introduced to a model in each learning phase. The goal is to learn a unified model performant on all the classes observed so far. Given the recent popularity of Vision Transformers (ViTs) in conventional classification settings, an interesting question is to study their continual learning behaviour. In this work, we develop a Debiased Dual Distilled Transformer for CIL dubbed $\textrm{D}^3\textrm{Former}$. The proposed model leverages a hybrid nested ViT design to ensure data efficiency and scalability to small as well as large datasets. In contrast to a recent ViT based CIL approach, our $\textrm{D}^3\textrm{Former}$ does not dynamically expand its architecture when new tasks are learned and remains suitable for a large number of incremental tasks. The improved CIL behaviour of $\textrm{D}^3\textrm{Former}$ owes to two fundamental changes to the ViT design. First, we treat the incremental learning as a long-tail classification problem where the majority samples from new classes vastly outnumber the limited exemplars available for old classes. To avoid the bias against the minority old classes, we propose to dynamically adjust logits to emphasize on retaining the representations relevant to old tasks. Second, we propose to preserve the configuration of spatial attention maps as the learning progresses across tasks. This helps in reducing catastrophic forgetting by constraining the model to retain the attention on the most discriminative regions. $\textrm{D}^3\textrm{Former}$ obtains favorable results on incremental versions of CIFAR-100, MNIST, SVHN, and ImageNet datasets. Code is available at https://tinyurl.com/d3former

Krishna Pillutla, Kshitiz Malik, Abdelrahman Mohamed et al. · uw

We consider two federated learning algorithms for training partially personalized models, where the shared and personal parameters are updated either simultaneously or alternately on the devices. Both algorithms have been proposed in the literature, but their convergence properties are not fully understood, especially for the alternating variant. We provide convergence analyses of both algorithms in the general nonconvex setting with partial participation and delineate the regime where one dominates the other. Our experiments on real-world image, text, and speech datasets demonstrate that (a) partial personalization can obtain most of the benefits of full model personalization with a small fraction of personal parameters, and, (b) the alternating update algorithm often outperforms the simultaneous update algorithm by a small but consistent margin.

Jiatong Shi, William Chen, Dan Berrebbi et al. · meta-ai, mit

The 2023 Multilingual Speech Universal Performance Benchmark (ML-SUPERB) Challenge expands upon the acclaimed SUPERB framework, emphasizing self-supervised models in multilingual speech recognition and language identification. The challenge comprises a research track focused on applying ML-SUPERB to specific multilingual subjects, a Challenge Track for model submissions, and a New Language Track where language resource researchers can contribute and evaluate their low-resource language data in the context of the latest progress in multilingual speech recognition. The challenge garnered 12 model submissions and 54 language corpora, resulting in a comprehensive benchmark encompassing 154 languages. The findings indicate that merely scaling models is not the definitive solution for multilingual speech tasks, and a variety of speech/voice types present significant challenges in multilingual speech processing.

Cheol Jun Cho, Abdelrahman Mohamed, Shang-Wen Li et al. · meta-ai, mit

Data-driven unit discovery in self-supervised learning (SSL) of speech has embarked on a new era of spoken language processing. Yet, the discovered units often remain in phonetic space and the units beyond phonemes are largely underexplored. Here, we demonstrate that a syllabic organization emerges in learning sentence-level representation of speech. In particular, we adopt "self-distillation" objective to fine-tune the pretrained HuBERT with an aggregator token that summarizes the entire sentence. Without any supervision, the resulting model draws definite boundaries in speech, and the representations across frames exhibit salient syllabic structures. We demonstrate that this emergent structure largely corresponds to the ground truth syllables. Furthermore, we propose a new benchmark task, Spoken Speech ABX, for evaluating sentence-level representation of speech. When compared to previous models, our model outperforms in both unsupervised syllable discovery and learning sentence-level representation. Together, we demonstrate that the self-distillation of HuBERT gives rise to syllabic organization without relying on external labels or modalities, and potentially provides novel data-driven units for spoken language modeling.

Bowen Shi, Abdelrahman Mohamed, Wei-Ning Hsu

This paper investigates self-supervised pre-training for audio-visual speaker representation learning where a visual stream showing the speaker's mouth area is used alongside speech as inputs. Our study focuses on the Audio-Visual Hidden Unit BERT (AV-HuBERT) approach, a recently developed general-purpose audio-visual speech pre-training framework. We conducted extensive experiments probing the effectiveness of pre-training and visual modality. Experimental results suggest that AV-HuBERT generalizes decently to speaker related downstream tasks, improving label efficiency by roughly ten fold for both audio-only and audio-visual speaker verification. We also show that incorporating visual information, even just the lip area, greatly improves the performance and noise robustness, reducing EER by 38% in the clean condition and 75% in noisy conditions.

Robin Algayres, Tristan Ricoul, Julien Karadayi et al.

Finding word boundaries in continuous speech is challenging as there is little or no equivalent of a 'space' delimiter between words. Popular Bayesian non-parametric models for text segmentation use a Dirichlet process to jointly segment sentences and build a lexicon of word types. We introduce DP-Parse, which uses similar principles but only relies on an instance lexicon of word tokens, avoiding the clustering errors that arise with a lexicon of word types. On the Zero Resource Speech Benchmark 2017, our model sets a new speech segmentation state-of-the-art in 5 languages. The algorithm monotonically improves with better input representations, achieving yet higher scores when fed with weakly supervised inputs. Despite lacking a type lexicon, DP-Parse can be pipelined to a language model and learn semantic and syntactic representations as assessed by a new spoken word embedding benchmark.

Andros Tjandra, Nayan Singhal, David Zhang et al.

End-to-end multilingual ASR has become more appealing because of several reasons such as simplifying the training and deployment process and positive performance transfer from high-resource to low-resource languages. However, scaling up the number of languages, total hours, and number of unique tokens is not a trivial task. This paper explores large-scale multilingual ASR models on 70 languages. We inspect two architectures: (1) Shared embedding and output and (2) Multiple embedding and output model. In the shared model experiments, we show the importance of tokenization strategy across different languages. Later, we use our optimal tokenization strategy to train multiple embedding and output model to further improve our result. Our multilingual ASR achieves 13.9%-15.6% average WER relative improvement compared to monolingual models. We show that our multilingual ASR generalizes well on an unseen dataset and domain, achieving 9.5% and 7.5% WER on Multilingual Librispeech (MLS) with zero-shot and finetuning, respectively.

Florian L. Kreyssig, Yangyang Shi, Jinxi Guo et al.

Self-supervised learning via masked prediction pre-training (MPPT) has shown impressive performance on a range of speech-processing tasks. This paper proposes a method to bias self-supervised learning towards a specific task. The core idea is to slightly finetune the model that is used to obtain the target sequence. This leads to better performance and a substantial increase in training speed. Furthermore, this paper proposes a variant of MPPT that allows low-footprint streaming models to be trained effectively by computing the MPPT loss on masked and unmasked frames. These approaches are evaluated for automatic speech recognition on the Librispeech corpus, where 100 hours of data served as the labelled data and 860 hours as the unlabelled data. The biased training outperforms the unbiased training by 15.5% after 250k updates and 23.8% after 100k updates on test-other. For the streaming models, the pre-training approach yields a reduction in word error rate of 44.1%.

Cheol Jun Cho, Peter Wu, Abdelrahman Mohamed et al.

Recent self-supervised learning (SSL) models have proven to learn rich representations of speech, which can readily be utilized by diverse downstream tasks. To understand such utilities, various analyses have been done for speech SSL models to reveal which and how information is encoded in the learned representations. Although the scope of previous analyses is extensive in acoustic, phonetic, and semantic perspectives, the physical grounding by speech production has not yet received full attention. To bridge this gap, we conduct a comprehensive analysis to link speech representations to articulatory trajectories measured by electromagnetic articulography (EMA). Our analysis is based on a linear probing approach where we measure articulatory score as an average correlation of linear mapping to EMA. We analyze a set of SSL models selected from the leaderboard of the SUPERB benchmark and perform further layer-wise analyses on two most successful models, Wav2Vec 2.0 and HuBERT. Surprisingly, representations from the recent speech SSL models are highly correlated with EMA traces (best: r = 0.81), and only 5 minutes are sufficient to train a linear model with high performance (r = 0.77). Our findings suggest that SSL models learn to align closely with continuous articulations, and provide a novel insight into speech SSL.

Anuj Diwan, Ching-Feng Yeh, Wei-Ning Hsu et al.

Automatic speech recognition research focuses on training and evaluating on static datasets. Yet, as speech models are increasingly deployed on personal devices, such models encounter user-specific distributional shifts. To simulate this real-world scenario, we introduce LibriContinual, a continual learning benchmark for speaker-specific domain adaptation derived from LibriVox audiobooks, with data corresponding to 118 individual speakers and 6 train splits per speaker of different sizes. Additionally, current speech recognition models and continual learning algorithms are not optimized to be compute-efficient. We adapt a general-purpose training algorithm NetAug for ASR and create a novel Conformer variant called the DisConformer (Disentangled Conformer). This algorithm produces ASR models consisting of a frozen 'core' network for general-purpose use and several tunable 'augment' networks for speaker-specific tuning. Using such models, we propose a novel compute-efficient continual learning algorithm called DisentangledCL. Our experiments show that the DisConformer models significantly outperform baselines on general ASR i.e. LibriSpeech (15.58% rel. WER on test-other). On speaker-specific LibriContinual they significantly outperform trainable-parameter-matched baselines (by 20.65% rel. WER on test) and even match fully finetuned baselines in some settings.

Ching-Feng Yeh, Wei-Ning Hsu, Paden Tomasello et al.

With the development of hardware for machine learning, newer models often come at the cost of both increased sizes and computational complexity. In effort to improve the efficiency for these models, we apply and investigate recent quantization techniques on speech representation learning models. The quantization techniques were evaluated on the SUPERB benchmark. On the ASR task, with aggressive quantization to 1 bit, we achieved 86.32% storage reduction (184.42 -> 25.23), 88% estimated runtime reduction (1.00 -> 0.12) with increased word error rate (7.06 -> 15.96). In comparison with DistillHuBERT which also aims for model compression, the 2-bit configuration yielded slightly smaller storage (35.84 vs. 46.98), better word error rate (12.68 vs. 13.37) and more efficient estimated runtime (0.15 vs. 0.73).

Cheol Jun Cho, Abdelrahman Mohamed, Alan W Black et al.

Self-Supervised Learning (SSL) based models of speech have shown remarkable performance on a range of downstream tasks. These state-of-the-art models have remained blackboxes, but many recent studies have begun "probing" models like HuBERT, to correlate their internal representations to different aspects of speech. In this paper, we show "inference of articulatory kinematics" as fundamental property of SSL models, i.e., the ability of these models to transform acoustics into the causal articulatory dynamics underlying the speech signal. We also show that this abstraction is largely overlapping across the language of the data used to train the model, with preference to the language with similar phonological system. Furthermore, we show that with simple affine transformations, Acoustic-to-Articulatory inversion (AAI) is transferrable across speakers, even across genders, languages, and dialects, showing the generalizability of this property. Together, these results shed new light on the internals of SSL models that are critical to their superior performance, and open up new avenues into language-agnostic universal models for speech engineering, that are interpretable and grounded in speech science.

Abdelrahman Mohamed, Fakhraddin Alwajih, El Moatez Billah Nagoudi et al.

Although image captioning has a vast array of applications, it has not reached its full potential in languages other than English. Arabic, for instance, although the native language of more than 400 million people, remains largely underrepresented in this area. This is due to the lack of labeled data and powerful Arabic generative models. We alleviate this issue by presenting a novel vision-language model dedicated to Arabic, dubbed \textit{Violet}. Our model is based on a vision encoder and a Gemini text decoder that maintains generation fluency while allowing fusion between the vision and language components. To train our model, we introduce a new method for automatically acquiring data from available English datasets. We also manually prepare a new dataset for evaluation. \textit{Violet} performs sizeably better than our baselines on all of our evaluation datasets. For example, it reaches a CIDEr score of $61.2$ on our manually annotated dataset and achieves an improvement of $13$ points on Flickr8k.

Xinyue Zhang, Jiaqi Yang, Xiangting Meng et al.

In the realm of computer vision, the perception and reconstruction of the 3D world through vision signals heavily rely on camera intrinsic parameters, which have long been a subject of intense research within the community. In practical applications, without a strong scene geometry prior like the Manhattan World assumption or special artificial calibration patterns, monocular focal length estimation becomes a challenging task. In this paper, we propose a method for monocular focal length estimation using category-level object priors. Based on two well-studied existing tasks: monocular depth estimation and category-level object canonical representation learning, our focal solver takes depth priors and object shape priors from images containing objects and estimates the focal length from triplets of correspondences in closed form. Our experiments on simulated and real world data demonstrate that the proposed method outperforms the current state-of-the-art, offering a promising solution to the long-standing monocular focal length estimation problem.

Lihe Yang, Shang-Wen Li, Yang Li et al.

At the most basic level, pixels are the source of the visual information through which we perceive the world. Pixels contain information at all levels, ranging from low-level attributes to high-level concepts. Autoencoders represent a classical and long-standing paradigm for learning representations from pixels or other raw inputs. In this work, we demonstrate that autoencoder-based self-supervised learning remains competitive today and can produce strong representations for downstream tasks, while remaining simple, stable, and efficient. Our model, codenamed "Pixio", is an enhanced masked autoencoder (MAE) with more challenging pre-training tasks and more capable architectures. The model is trained on 2B web-crawled images with a self-curation strategy with minimal human curation. Pixio performs competitively across a wide range of downstream tasks in the wild, including monocular depth estimation (e.g., Depth Anything), feed-forward 3D reconstruction (i.e., MapAnything), semantic segmentation, and robot learning, outperforming or matching DINOv3 trained at similar scales. Our results suggest that pixel-space self-supervised learning can serve as a promising alternative and a complement to latent-space approaches.

Fakhraddin Alwajih, El Moatez Billah Nagoudi, Gagan Bhatia et al.

Multimodal large language models (MLLMs) have proven effective in a wide range of tasks requiring complex reasoning and linguistic comprehension. However, due to a lack of high-quality multimodal resources in languages other than English, success of MLLMs remains relatively limited to English-based settings. This poses significant challenges in developing comparable models for other languages, including even those with large speaker populations such as Arabic. To alleviate this challenge, we introduce a comprehensive family of Arabic MLLMs, dubbed \textit{Peacock}, with strong vision and language capabilities. Through comprehensive qualitative and quantitative analysis, we demonstrate the solid performance of our models on various visual reasoning tasks and further show their emerging dialectal potential. Additionally, we introduce ~\textit{Henna}, a new benchmark specifically designed for assessing MLLMs on aspects related to Arabic culture, setting the first stone for culturally-aware Arabic MLLMs.The GitHub repository for the \textit{Peacock} project is available at \url{https://github.com/UBC-NLP/peacock}.

Karima Kadaoui, Hanin Atwany, Hamdan Al-Ali et al.

We introduce JEEM, a benchmark designed to evaluate Vision-Language Models (VLMs) on visual understanding across four Arabic-speaking countries: Jordan, The Emirates, Egypt, and Morocco. JEEM includes the tasks of image captioning and visual question answering, and features culturally rich and regionally diverse content. This dataset aims to assess the ability of VLMs to generalize across dialects and accurately interpret cultural elements in visual contexts. In an evaluation of five prominent open-source Arabic VLMs and GPT-4V, we find that the Arabic VLMs consistently underperform, struggling with both visual understanding and dialect-specific generation. While GPT-4V ranks best in this comparison, the model's linguistic competence varies across dialects, and its visual understanding capabilities lag behind. This underscores the need for more inclusive models and the value of culturally-diverse evaluation paradigms.

Puyuan Peng, Po-Yao Huang, Shang-Wen Li et al. · meta-ai, mit

We introduce VoiceCraft, a token infilling neural codec language model, that achieves state-of-the-art performance on both speech editing and zero-shot text-to-speech (TTS) on audiobooks, internet videos, and podcasts. VoiceCraft employs a Transformer decoder architecture and introduces a token rearrangement procedure that combines causal masking and delayed stacking to enable generation within an existing sequence. On speech editing tasks, VoiceCraft produces edited speech that is nearly indistinguishable from unedited recordings in terms of naturalness, as evaluated by humans; for zero-shot TTS, our model outperforms prior SotA models including VALLE and the popular commercial model XTTS-v2. Crucially, the models are evaluated on challenging and realistic datasets, that consist of diverse accents, speaking styles, recording conditions, and background noise and music, and our model performs consistently well compared to other models and real recordings. In particular, for speech editing evaluation, we introduce a high quality, challenging, and realistic dataset named RealEdit. We encourage readers to listen to the demos at https://jasonppy.github.io/VoiceCraft_web.

Eugene Kharitonov, Jade Copet, Kushal Lakhotia et al.

Textless spoken language processing research aims to extend the applicability of standard NLP toolset onto spoken language and languages with few or no textual resources. In this paper, we introduce textless-lib, a PyTorch-based library aimed to facilitate research in this research area. We describe the building blocks that the library provides and demonstrate its usability by discuss three different use-case examples: (i) speaker probing, (ii) speech resynthesis and compression, and (iii) speech continuation. We believe that textless-lib substantially simplifies research the textless setting and will be handful not only for speech researchers but also for the NLP community at large. The code, documentation, and pre-trained models are available at https://github.com/facebookresearch/textlesslib/ .

Bowen Shi, Wei-Ning Hsu, Kushal Lakhotia et al.

Video recordings of speech contain correlated audio and visual information, providing a strong signal for speech representation learning from the speaker's lip movements and the produced sound. We introduce Audio-Visual Hidden Unit BERT (AV-HuBERT), a self-supervised representation learning framework for audio-visual speech, which masks multi-stream video input and predicts automatically discovered and iteratively refined multimodal hidden units. AV-HuBERT learns powerful audio-visual speech representation benefiting both lip-reading and automatic speech recognition. On the largest public lip-reading benchmark LRS3 (433 hours), AV-HuBERT achieves 32.5% WER with only 30 hours of labeled data, outperforming the former state-of-the-art approach (33.6%) trained with a thousand times more transcribed video data (31K hours). The lip-reading WER is further reduced to 26.9% when using all 433 hours of labeled data from LRS3 and combined with self-training. Using our audio-visual representation on the same benchmark for audio-only speech recognition leads to a 40% relative WER reduction over the state-of-the-art performance (1.3% vs 2.3%). Our code and models are available at https://github.com/facebookresearch/av_hubert

Eugene Kharitonov, Ann Lee, Adam Polyak et al.

Speech pre-training has primarily demonstrated efficacy on classification tasks, while its capability of generating novel speech, similar to how GPT-2 can generate coherent paragraphs, has barely been explored. Generative Spoken Language Modeling (GSLM) \cite{Lakhotia2021} is the only prior work addressing the generative aspects of speech pre-training, which replaces text with discovered phone-like units for language modeling and shows the ability to generate meaningful novel sentences. Unfortunately, despite eliminating the need of text, the units used in GSLM discard most of the prosodic information. Hence, GSLM fails to leverage prosody for better comprehension, and does not generate expressive speech. In this work, we present a prosody-aware generative spoken language model (pGSLM). It is composed of a multi-stream transformer language model (MS-TLM) of speech, represented as discovered unit and prosodic feature streams, and an adapted HiFi-GAN model converting MS-TLM outputs to waveforms. We devise a series of metrics for prosody modeling and generation, and re-use metrics from GSLM for content modeling. Experimental results show that the pGSLM can utilize prosody to improve both prosody and content modeling, and also generate natural, meaningful, and coherent speech given a spoken prompt. Audio samples can be found at https://speechbot.github.io/pgslm. Codes and models are available at https://github.com/pytorch/fairseq/tree/main/examples/textless_nlp/pgslm.

Jacob Kahn, Morgane Rivière, Weiyi Zheng et al.

We introduce a new collection of spoken English audio suitable for training speech recognition systems under limited or no supervision. It is derived from open-source audio books from the LibriVox project. It contains over 60K hours of audio, which is, to our knowledge, the largest freely-available corpus of speech. The audio has been segmented using voice activity detection and is tagged with SNR, speaker ID and genre descriptions. Additionally, we provide baseline systems and evaluation metrics working under three settings: (1) the zero resource/unsupervised setting (ABX), (2) the semi-supervised setting (PER, CER) and (3) the distant supervision setting (WER). Settings (2) and (3) use limited textual resources (10 minutes to 10 hours) aligned with the speech. Setting (3) uses large amounts of unaligned text. They are evaluated on the standard LibriSpeech dev and test sets for comparison with the supervised state-of-the-art.

Shu-wen Yang, Heng-Jui Chang, Zili Huang et al. · meta-ai, mit

The foundation model paradigm leverages a shared foundation model to achieve state-of-the-art (SOTA) performance for various tasks, requiring minimal downstream-specific modeling and data annotation. This approach has proven crucial in the field of Natural Language Processing (NLP). However, the speech processing community lacks a similar setup to explore the paradigm systematically. In this work, we establish the Speech processing Universal PERformance Benchmark (SUPERB) to study the effectiveness of the paradigm for speech. We propose a unified multi-tasking framework to address speech processing tasks in SUPERB using a frozen foundation model followed by task-specialized, lightweight prediction heads. Combining our results with community submissions, we verify that the foundation model paradigm is promising for speech, and our multi-tasking framework is simple yet effective, as the best-performing foundation model shows competitive generalizability across most SUPERB tasks. For reproducibility and extensibility, we have developed a long-term maintained platform that enables deterministic benchmarking, allows for result sharing via an online leaderboard, and promotes collaboration through a community-driven benchmark database to support new development cycles. Finally, we conduct a series of analyses to offer an in-depth understanding of SUPERB and speech foundation models, including information flows across tasks inside the models, the correctness of the weighted-sum benchmarking protocol and the statistical significance and robustness of the benchmark.

Gyeongjin Kang, Seungtae Nam, Seungkwon Yang et al.

Feed-forward 3D modeling has emerged as a promising approach for rapid and high-quality 3D reconstruction. In particular, directly generating explicit 3D representations, such as 3D Gaussian splatting, has attracted significant attention due to its fast and high-quality rendering, as well as numerous applications. However, many state-of-the-art methods, primarily based on transformer architectures, suffer from severe scalability issues because they rely on full attention across image tokens from multiple input views, resulting in prohibitive computational costs as the number of views or image resolution increases. Toward a scalable and efficient feed-forward 3D reconstruction, we introduce an iterative Large 3D Reconstruction Model (iLRM) that generates 3D Gaussian representations through an iterative refinement mechanism, guided by three core principles: (1) decoupling the scene representation from input-view images to enable compact 3D representations; (2) decomposing fully-attentional multi-view interactions into a two-stage attention scheme to reduce computational costs; and (3) injecting high-resolution information at every layer to achieve high-fidelity reconstruction. Experimental results on widely used datasets, such as RE10K and DL3DV, demonstrate that iLRM outperforms existing methods in both reconstruction quality and speed.

Abdelrahman Mohamed, Yova Kementchedjhieva

Despite significant advances in vision-language models (VLMs), image captioning often suffers from a lack of detail, with base models producing short, generic captions. This limitation persists even though VLMs are equipped with strong vision and language backbones. While supervised data and complex reward functions have been proposed to improve detailed image captioning, we identify a simpler underlying issue: a bias towards the end-of-sequence (EOS) token, which is introduced during cross-entropy training. We propose an unsupervised method to debias the model's tendency to predict the EOS token prematurely. By reducing this bias, we encourage the generation of longer, more detailed captions without the need for intricate reward functions or supervision. Our approach is straightforward, effective, and easily applicable to any pretrained model. We demonstrate its effectiveness through experiments with three VLMs and on three detailed captioning benchmarks. Our results show a substantial increase in caption length and relevant details, albeit with an expected increase in the rate of hallucinations.

Sho Takishita, Jay Gala, Abdelrahman Mohamed et al.

Many vision-language models (VLMs) that prove very effective at a range of multimodal task, build on CLIP-based vision encoders, which are known to have various limitations. We investigate the hypothesis that the strong language backbone in VLMs compensates for possibly weak visual features by contextualizing or enriching them. Using three CLIP-based VLMs, we perform controlled self-attention ablations on a carefully designed probing task. Our findings show that despite known limitations, CLIP visual representations offer ready-to-read semantic information to the language decoder. However, in scenarios of reduced contextualization in the visual representations, the language decoder can largely compensate for the deficiency and recover performance. This suggests a dynamic division of labor in VLMs and motivates future architectures that offload more visual processing to the language decoder.

Chyi-Jiunn Lin, Guan-Ting Lin, Yung-Sung Chuang et al.

Spoken Question Answering (SQA) is essential for machines to reply to user's question by finding the answer span within a given spoken passage. SQA has been previously achieved without ASR to avoid recognition errors and Out-of-Vocabulary (OOV) problems. However, the real-world problem of Open-domain SQA (openSQA), in which the machine needs to first retrieve passages that possibly contain the answer from a spoken archive in addition, was never considered. This paper proposes the first known end-to-end framework, Speech Dense Passage Retriever (SpeechDPR), for the retrieval component of the openSQA problem. SpeechDPR learns a sentence-level semantic representation by distilling knowledge from the cascading model of unsupervised ASR (UASR) and text dense retriever (TDR). No manually transcribed speech data is needed. Initial experiments showed performance comparable to the cascading model of UASR and TDR, and significantly better when UASR was poor, verifying this approach is more robust to speech recognition errors.

Puyuan Peng, Shang-Wen Li, Okko Räsänen et al.

In this paper, we show that representations capturing syllabic units emerge when training a self-supervised speech model with a visually-grounded training objective. We demonstrate that a nearly identical model architecture (HuBERT) trained with a masked language modeling loss does not exhibit this same ability, suggesting that the visual grounding objective is responsible for the emergence of this phenomenon. We propose the use of a minimum cut algorithm to automatically predict syllable boundaries in speech, followed by a 2-stage clustering method to group identical syllables together. We show that our model not only outperforms a state-of-the-art syllabic segmentation method on the language it was trained on (English), but also generalizes in a zero-shot fashion to Estonian. Finally, we show that the same model is capable of zero-shot generalization for a word segmentation task on 4 other languages from the Zerospeech Challenge, in some cases beating the previous state-of-the-art.

Jiatong Shi, Dan Berrebbi, William Chen et al.

Speech processing Universal PERformance Benchmark (SUPERB) is a leaderboard to benchmark the performance of Self-Supervised Learning (SSL) models on various speech processing tasks. However, SUPERB largely considers English speech in its evaluation. This paper presents multilingual SUPERB (ML-SUPERB), covering 143 languages (ranging from high-resource to endangered), and considering both automatic speech recognition and language identification. Following the concept of SUPERB, ML-SUPERB utilizes frozen SSL features and employs a simple framework for multilingual tasks by learning a shallow downstream model. Similar to the SUPERB benchmark, we find speech SSL models can significantly improve performance compared to FBANK features. Furthermore, we find that multilingual models do not always perform better than their monolingual counterparts. We will release ML-SUPERB as a challenge with organized datasets and reproducible training scripts for future multilingual representation research.

Tu Anh Nguyen, Eugene Kharitonov, Jade Copet et al.

We introduce dGSLM, the first "textless" model able to generate audio samples of naturalistic spoken dialogues. It uses recent work on unsupervised spoken unit discovery coupled with a dual-tower transformer architecture with cross-attention trained on 2000 hours of two-channel raw conversational audio (Fisher dataset) without any text or labels. We show that our model is able to generate speech, laughter and other paralinguistic signals in the two channels simultaneously and reproduces more naturalistic and fluid turn-taking compared to a text-based cascaded model.

Hashmat Shadab Malik, Ikboljon Sobirov, Abdelrahman Mohamed

Object detection is a challenging and popular computer vision problem. The problem is even more challenging in aerial images due to significant variation in scale and viewpoint in a diverse set of object categories. Recently, deep learning-based object detection approaches have been actively explored for the problem of object detection in aerial images. In this work, we investigate the impact of Faster R-CNN for aerial object detection and explore numerous strategies to improve its performance for aerial images. We conduct extensive experiments on the challenging iSAID dataset. The resulting adapted Faster R-CNN obtains a significant mAP gain of 4.96% over its vanilla baseline counterpart on the iSAID validation set, demonstrating the impact of different strategies investigated in this work.

Bowen Shi, Wei-Ning Hsu, Abdelrahman Mohamed

Audio-based automatic speech recognition (ASR) degrades significantly in noisy environments and is particularly vulnerable to interfering speech, as the model cannot determine which speaker to transcribe. Audio-visual speech recognition (AVSR) systems improve robustness by complementing the audio stream with the visual information that is invariant to noise and helps the model focus on the desired speaker. However, previous AVSR work focused solely on the supervised learning setup; hence the progress was hindered by the amount of labeled data available. In this work, we present a self-supervised AVSR framework built upon Audio-Visual HuBERT (AV-HuBERT), a state-of-the-art audio-visual speech representation learning model. On the largest available AVSR benchmark dataset LRS3, our approach outperforms prior state-of-the-art by ~50% (28.0% vs. 14.1%) using less than 10% of labeled data (433hr vs. 30hr) in the presence of babble noise, while reducing the WER of an audio-based model by over 75% (25.8% vs. 5.8%) on average.

Felix Kreuk, Adam Polyak, Jade Copet et al.

Speech emotion conversion is the task of modifying the perceived emotion of a speech utterance while preserving the lexical content and speaker identity. In this study, we cast the problem of emotion conversion as a spoken language translation task. We use a decomposition of the speech signal into discrete learned representations, consisting of phonetic-content units, prosodic features, speaker, and emotion. First, we modify the speech content by translating the phonetic-content units to a target emotion, and then predict the prosodic features based on these units. Finally, the speech waveform is generated by feeding the predicted representations into a neural vocoder. Such a paradigm allows us to go beyond spectral and parametric changes of the signal, and model non-verbal vocalizations, such as laughter insertion, yawning removal, etc. We demonstrate objectively and subjectively that the proposed method is vastly superior to current approaches and even beats text-based systems in terms of perceived emotion and audio quality. We rigorously evaluate all components of such a complex system and conclude with an extensive model analysis and ablation study to better emphasize the architectural choices, strengths and weaknesses of the proposed method. Samples are available under the following link: https://speechbot.github.io/emotion.

Alex Xiao, Weiyi Zheng, Gil Keren et al.

With 4.5 million hours of English speech from 10 different sources across 120 countries and models of up to 10 billion parameters, we explore the frontiers of scale for automatic speech recognition. We propose data selection techniques to efficiently scale training data to find the most valuable samples in massive datasets. To efficiently scale model sizes, we leverage various optimizations such as sparse transducer loss and model sharding. By training 1-10B parameter universal English ASR models, we push the limits of speech recognition performance across many domains. Furthermore, our models learn powerful speech representations with zero and few-shot capabilities on novel domains and styles of speech, exceeding previous results across multiple in-house and public benchmarks. For speakers with disorders due to brain damage, our best zero-shot and few-shot models achieve 22% and 60% relative improvement on the AphasiaBank test set, respectively, while realizing the best performance on public social media videos. Furthermore, the same universal model reaches equivalent performance with 500x less in-domain data on the SPGISpeech financial-domain dataset.

Vimal Manohar, Tatiana Likhomanenko, Qiantong Xu et al.

In this paper, we introduce the Kaizen framework that uses a continuously improving teacher to generate pseudo-labels for semi-supervised speech recognition (ASR). The proposed approach uses a teacher model which is updated as the exponential moving average (EMA) of the student model parameters. We demonstrate that it is critical for EMA to be accumulated with full-precision floating point. The Kaizen framework can be seen as a continuous version of the iterative pseudo-labeling approach for semi-supervised training. It is applicable for different training criteria, and in this paper we demonstrate its effectiveness for frame-level hybrid hidden Markov model-deep neural network (HMM-DNN) systems as well as sequence-level Connectionist Temporal Classification (CTC) based models. For large scale real-world unsupervised public videos in UK English and Italian languages the proposed approach i) shows more than 10% relative word error rate (WER) reduction over standard teacher-student training; ii) using just 10 hours of supervised data and a large amount of unsupervised data closes the gap to the upper-bound supervised ASR system that uses 650h or 2700h respectively.

Wei-Ning Hsu, Benjamin Bolte, Yao-Hung Hubert Tsai et al.

Self-supervised approaches for speech representation learning are challenged by three unique problems: (1) there are multiple sound units in each input utterance, (2) there is no lexicon of input sound units during the pre-training phase, and (3) sound units have variable lengths with no explicit segmentation. To deal with these three problems, we propose the Hidden-Unit BERT (HuBERT) approach for self-supervised speech representation learning, which utilizes an offline clustering step to provide aligned target labels for a BERT-like prediction loss. A key ingredient of our approach is applying the prediction loss over the masked regions only, which forces the model to learn a combined acoustic and language model over the continuous inputs. HuBERT relies primarily on the consistency of the unsupervised clustering step rather than the intrinsic quality of the assigned cluster labels. Starting with a simple k-means teacher of 100 clusters, and using two iterations of clustering, the HuBERT model either matches or improves upon the state-of-the-art wav2vec 2.0 performance on the Librispeech (960h) and Libri-light (60,000h) benchmarks with 10min, 1h, 10h, 100h, and 960h fine-tuning subsets. Using a 1B parameter model, HuBERT shows up to 19% and 13% relative WER reduction on the more challenging dev-other and test-other evaluation subsets.

Shu-wen Yang, Po-Han Chi, Yung-Sung Chuang et al.

Self-supervised learning (SSL) has proven vital for advancing research in natural language processing (NLP) and computer vision (CV). The paradigm pretrains a shared model on large volumes of unlabeled data and achieves state-of-the-art (SOTA) for various tasks with minimal adaptation. However, the speech processing community lacks a similar setup to systematically explore the paradigm. To bridge this gap, we introduce Speech processing Universal PERformance Benchmark (SUPERB). SUPERB is a leaderboard to benchmark the performance of a shared model across a wide range of speech processing tasks with minimal architecture changes and labeled data. Among multiple usages of the shared model, we especially focus on extracting the representation learned from SSL due to its preferable re-usability. We present a simple framework to solve SUPERB tasks by learning task-specialized lightweight prediction heads on top of the frozen shared model. Our results demonstrate that the framework is promising as SSL representations show competitive generalizability and accessibility across SUPERB tasks. We release SUPERB as a challenge with a leaderboard and a benchmark toolkit to fuel the research in representation learning and general speech processing.

Adam Polyak, Yossi Adi, Jade Copet et al.

We propose using self-supervised discrete representations for the task of speech resynthesis. To generate disentangled representation, we separately extract low-bitrate representations for speech content, prosodic information, and speaker identity. This allows to synthesize speech in a controllable manner. We analyze various state-of-the-art, self-supervised representation learning methods and shed light on the advantages of each method while considering reconstruction quality and disentanglement properties. Specifically, we evaluate the F0 reconstruction, speaker identification performance (for both resynthesis and voice conversion), recordings' intelligibility, and overall quality using subjective human evaluation. Lastly, we demonstrate how these representations can be used for an ultra-lightweight speech codec. Using the obtained representations, we can get to a rate of 365 bits per second while providing better speech quality than the baseline methods. Audio samples can be found under the following link: speechbot.github.io/resynthesis.

Alex Xiao, Christian Fuegen, Abdelrahman Mohamed

Pseudo-labeling is the most adopted method for pre-training automatic speech recognition (ASR) models. However, its performance suffers from the supervised teacher model's degrading quality in low-resource setups and under domain transfer. Inspired by the successes of contrastive representation learning for computer vision and speech applications, and more recently for supervised learning of visual objects, we propose Contrastive Semi-supervised Learning (CSL). CSL eschews directly predicting teacher-generated pseudo-labels in favor of utilizing them to select positive and negative examples. In the challenging task of transcribing public social media videos, using CSL reduces the WER by 8% compared to the standard Cross-Entropy pseudo-labeling (CE-PL) when 10hr of supervised data is used to annotate 75,000hr of videos. The WER reduction jumps to 19% under the ultra low-resource condition of using 1hr labels for teacher supervision. CSL generalizes much better in out-of-domain conditions, showing up to 17% WER reduction compared to the best CE-PL pre-trained model.

Alexis Conneau, Alexei Baevski, Ronan Collobert et al.

This paper presents XLSR which learns cross-lingual speech representations by pretraining a single model from the raw waveform of speech in multiple languages. We build on wav2vec 2.0 which is trained by solving a contrastive task over masked latent speech representations and jointly learns a quantization of the latents shared across languages. The resulting model is fine-tuned on labeled data and experiments show that cross-lingual pretraining significantly outperforms monolingual pretraining. On the CommonVoice benchmark, XLSR shows a relative phoneme error rate reduction of 72% compared to the best known results. On BABEL, our approach improves word error rate by 16% relative compared to a comparable system. Our approach enables a single multilingual speech recognition model which is competitive to strong individual models. Analysis shows that the latent discrete speech representations are shared across languages with increased sharing for related languages. We hope to catalyze research in low-resource speech understanding by releasing XLSR-53, a large model pretrained in 53 languages.

Alexei Baevski, Henry Zhou, Abdelrahman Mohamed et al.

We show for the first time that learning powerful representations from speech audio alone followed by fine-tuning on transcribed speech can outperform the best semi-supervised methods while being conceptually simpler. wav2vec 2.0 masks the speech input in the latent space and solves a contrastive task defined over a quantization of the latent representations which are jointly learned. Experiments using all labeled data of Librispeech achieve 1.8/3.3 WER on the clean/other test sets. When lowering the amount of labeled data to one hour, wav2vec 2.0 outperforms the previous state of the art on the 100 hour subset while using 100 times less labeled data. Using just ten minutes of labeled data and pre-training on 53k hours of unlabeled data still achieves 4.8/8.2 WER. This demonstrates the feasibility of speech recognition with limited amounts of labeled data.

Kritika Singh, Vimal Manohar, Alex Xiao et al.

Many semi- and weakly-supervised approaches have been investigated for overcoming the labeling cost of building high quality speech recognition systems. On the challenging task of transcribing social media videos in low-resource conditions, we conduct a large scale systematic comparison between two self-labeling methods on one hand, and weakly-supervised pretraining using contextual metadata on the other. We investigate distillation methods at the frame level and the sequence level for hybrid, encoder-only CTC-based, and encoder-decoder speech recognition systems on Dutch and Romanian languages using 27,000 and 58,000 hours of unlabeled audio respectively. Although all approaches improved upon their respective baseline WERs by more than 8%, sequence-level distillation for encoder-decoder models provided the largest relative WER reduction of 20% compared to the strongest data-augmented supervised baseline.