Jaň Černocký

Jiangyu Han, Federico Landini, Johan Rohdin et al.

In this work, we propose an error correction framework, named DiaCorrect, to refine the output of a diarization system in a simple yet effective way. This method is inspired by error correction techniques in automatic speech recognition. Our model consists of two parallel convolutional encoders and a transform-based decoder. By exploiting the interactions between the input recording and the initial system's outputs, DiaCorrect can automatically correct the initial speaker activities to minimize the diarization errors. Experiments on 2-speaker telephony data show that the proposed DiaCorrect can effectively improve the initial model's results. Our source code is publicly available at https://github.com/BUTSpeechFIT/diacorrect.

Juan Zuluaga-Gomez, Karel Veselý, Igor Szöke et al.

Personal assistants, automatic speech recognizers and dialogue understanding systems are becoming more critical in our interconnected digital world. A clear example is air traffic control (ATC) communications. ATC aims at guiding aircraft and controlling the airspace in a safe and optimal manner. These voice-based dialogues are carried between an air traffic controller (ATCO) and pilots via very-high frequency radio channels. In order to incorporate these novel technologies into ATC (low-resource domain), large-scale annotated datasets are required to develop the data-driven AI systems. Two examples are automatic speech recognition (ASR) and natural language understanding (NLU). In this paper, we introduce the ATCO2 corpus, a dataset that aims at fostering research on the challenging ATC field, which has lagged behind due to lack of annotated data. The ATCO2 corpus covers 1) data collection and pre-processing, 2) pseudo-annotations of speech data, and 3) extraction of ATC-related named entities. The ATCO2 corpus is split into three subsets. 1) ATCO2-test-set corpus contains 4 hours of ATC speech with manual transcripts and a subset with gold annotations for named-entity recognition (callsign, command, value). 2) The ATCO2-PL-set corpus consists of 5281 hours of unlabeled ATC data enriched with automatic transcripts from an in-domain speech recognizer, contextual information, speaker turn information, signal-to-noise ratio estimate and English language detection score per sample. Both available for purchase through ELDA at http://catalog.elra.info/en-us/repository/browse/ELRA-S0484. 3) The ATCO2-test-set-1h corpus is a one-hour subset from the original test set corpus, that we are offering for free at https://www.atco2.org/data. We expect the ATCO2 corpus will foster research on robust ASR and NLU not only in the field of ATC communications but also in the general research community.

Ján Švec, Kateřina Žmolíková, Martin Kocour et al.

Recently, the performance of blind speech separation (BSS) and target speech extraction (TSE) has greatly progressed. Most works, however, focus on relatively well-controlled conditions using, e.g., read speech. The performance may degrade in more realistic situations. One of the factors causing such degradation may be intrinsic speaker variability, such as emotions, occurring commonly in realistic speech. In this paper, we investigate the influence of emotions on TSE and BSS. We create a new test dataset of emotional mixtures for the evaluation of TSE and BSS. This dataset combines LibriSpeech and Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS). Through controlled experiments, we can analyze the impact of different emotions on the performance of BSS and TSE. We observe that BSS is relatively robust to emotions, while TSE, which requires identifying and extracting the speech of a target speaker, is much more sensitive to emotions. On comparative speaker verification experiments we show that identifying the target speaker may be particularly challenging when dealing with emotional speech. Using our findings, we outline potential future directions that could improve the robustness of BSS and TSE systems toward emotional speech.

Bolaji Yusuf, Jan "Honza" Černocký, Murat Saraçlar

End-to-end (E2E) keyword search (KWS) has emerged as an alternative and complimentary approach to conventional keyword search which depends on the output of automatic speech recognition (ASR) systems. While E2E methods greatly simplify the KWS pipeline, they generally have worse performance than their ASR-based counterparts, which can benefit from pretraining with untranscribed data. In this work, we propose a method for pretraining E2E KWS systems with untranscribed data, which involves using acoustic unit discovery (AUD) to obtain discrete units for untranscribed data and then learning to locate sequences of such units in the speech. We conduct experiments across languages and AUD systems: we show that finetuning such a model significantly outperforms a model trained from scratch, and the performance improvements are generally correlated with the quality of the AUD system used for pretraining.

Šimon Sedláček, Bolaji Yusuf, Ján Švec et al.

In this work, we approach spoken Dialogue State Tracking (DST) by bridging the representation spaces of speech encoders and LLMs via a small connector module, with a focus on fully open-sourced and open-data components (WavLM-large, OLMo). We focus on ablating different aspects of such systems including full/LoRA adapter fine-tuning, the effect of agent turns in the dialogue history, as well as fuzzy matching-based output post-processing, which greatly improves performance of our systems on named entities in the dialogue slot values. We conduct our experiments on the SpokenWOZ dataset, and additionally utilize the Speech-Aware MultiWOZ dataset to augment our training data. Ultimately, our best-performing WavLM + connector + OLMo-1B aligned models achieve state of the art on the SpokenWOZ test set (34.66% JGA), and our system with Gemma-2-9B-instruct further surpasses this result, reaching 42.17% JGA on SpokenWOZ test.

Šimon Sedláček, Santosh Kesiraju, Alexander Polok et al.

This paper investigates a novel approach to end-to-end speech translation (ST) based on aligning frozen pre-trained automatic speech recognition (ASR) and machine translation (MT) models via a small connector module (Q-Former, our Subsampler-Transformer Encoder). This connector bridges the gap between the speech and text modalities, transforming ASR encoder embeddings into the latent representation space of the MT encoder while being the only part of the system optimized during training. Experiments are conducted on the How2 English-Portuguese dataset as we investigate the alignment approach in a small-scale scenario focusing on ST. While keeping the size of the connector module constant and small in comparison ( < 5% of the size of the larger aligned models), increasing the size and capability of the foundation ASR and MT models universally improves translation results. We also find that the connectors can serve as domain adapters for the foundation MT models, significantly improving translation performance in the aligned ST setting. We conclude that this approach represents a viable and scalable approach to training end-to-end ST systems.

Šimon Sedláček, Sara Barahona, Bolaji Yusuf et al.

Evaluating open-ended responses from large audio language models (LALMs) is challenging because human annotators often genuinely disagree on answer correctness due to multiple valid interpretations, partial correctness, and subjective judgment. Traditional metrics reporting only mean scores fail to capture this uncertainty. We present ORCA (Open-ended Response Correctness Assessment), a framework that models the variability in human judgments using Beta distributions to predict both expected correctness and uncertainty. Our three-stage annotation framework combines human judgment with structured feedback and iterative refinement to simultaneously curate training data and improve benchmark quality. We collected 11,721 annotations across 3,580 question-answer pairs from 15 LALMs on two audio QA benchmarks, achieving inter-annotator agreement of 0.82 (Krippendorff's alpha). ORCA achieves 0.91 Spearman correlation with mean human judgments, matching or outperforming LLM-judge baselines while providing uncertainty estimates and requiring significantly less compute. We release our models, code, and curated dataset.

Katia Vendrame, Bolaji Yusuf, Santosh Kesiraju et al.

End-to-end spoken dialogue state tracking (DST) is made difficult by the tandem of having to handle speech input and data scarcity. Combining speech foundation encoders and large language models has been proposed in recent work as to alleviate some of this difficulty. Although this approach has been shown to result in strong spoken DST models, achieving state-of-the-art performance in realistic multi-turn DST, it struggles to generalize across domains and requires annotated spoken DST training data for each domain of interest. However, collecting such data for every target domain is both costly and difficult. Noting that textual DST data is more easily obtained for various domains, in this work, we propose jointly training on available spoken DST data and written textual data from other domains as a way to achieve cross-domain generalization. We conduct experiments which show the efficacy of our proposed method for getting good cross-domain DST performance without relying on spoken training data from the target domains.

Martin Kocour, Martin Karafiat, Alexander Polok et al.

We propose a speaker-attributed (SA) Whisper-based model for multi-talker speech recognition that combines target-speaker modeling with serialized output training (SOT). Our approach leverages a Diarization-Conditioned Whisper (DiCoW) encoder to extract target-speaker embeddings, which are concatenated into a single representation and passed to a shared decoder. This enables the model to transcribe overlapping speech as a serialized output stream with speaker tags and timestamps. In contrast to target-speaker ASR systems such as DiCoW, which decode each speaker separately, our approach performs joint decoding, allowing the decoder to condition on the context of all speakers simultaneously. Experiments show that the model outperforms existing SOT-based approaches and surpasses DiCoW on multi-talker mixtures (e.g., LibriMix).

Dominik Klement, Matthew Maciejewski, Sanjeev Khudanpur et al.

The majority of deep learning-based speech enhancement methods require paired clean-noisy speech data. Collecting such data at scale in real-world conditions is infeasible, which has led the community to rely on synthetically generated noisy speech. However, this introduces a gap between the training and testing phases. In this work, we propose a novel dual-branch encoder-decoder architecture for unsupervised speech enhancement that separates the input into clean speech and residual noise. Adversarial training is employed to impose priors on each branch, defined by unpaired datasets of clean speech and, optionally, noise. Experimental results show that our method achieves performance comparable to leading unsupervised speech enhancement approaches. Furthermore, we demonstrate the critical impact of clean speech data selection on enhancement performance. In particular, our findings reveal that performance may appear overly optimistic when in-domain clean speech data are used for prior definition -- a practice adopted in previous unsupervised speech enhancement studies.

Pradyoth Hegde, Santosh Kesiraju, Jan Švec et al.

This study explores the application of in-context learning (ICL) to the dialogue state tracking (DST) problem and investigates the factors that influence its effectiveness. We use a sentence embedding based k-nearest neighbour method to retrieve the suitable demonstrations for ICL. The selected demonstrations, along with the test samples, are structured within a template as input to the LLM. We then conduct a systematic study to analyse the impact of factors related to demonstration selection and prompt context on DST performance. This work is conducted using the MultiWoZ2.4 dataset and focuses primarily on the OLMo-7B-instruct, Mistral-7B-Instruct-v0.3, and Llama3.2-3B-Instruct models. Our findings provide several useful insights on in-context learning abilities of LLMs for dialogue state tracking.

Junyi Peng, Takanori Ashihara, Marc Delcroix et al.

Self-supervised learning (SSL) models have significantly advanced speech processing tasks, and several benchmarks have been proposed to validate their effectiveness. However, previous benchmarks have primarily focused on single-speaker scenarios, with less exploration of target-speaker tasks in noisy, multi-talker conditions -- a more challenging yet practical case. In this paper, we introduce the Target-Speaker Speech Processing Universal Performance Benchmark (TS-SUPERB), which includes four widely recognized target-speaker processing tasks that require identifying the target speaker and extracting information from the speech mixture. In our benchmark, the speaker embedding extracted from enrollment speech is used as a clue to condition downstream models. The benchmark result reveals the importance of evaluating SSL models in target speaker scenarios, demonstrating that performance cannot be easily inferred from related single-speaker tasks. Moreover, by using a unified SSL-based target speech encoder, consisting of a speaker encoder and an extractor module, we also investigate joint optimization across TS tasks to leverage mutual information and demonstrate its effectiveness.

Jan Pešán, Santosh Kesiraju, Lukáš Burget et al.

Paralinguistic traits like cognitive load and emotion are increasingly recognized as pivotal areas in speech recognition research, often examined through specialized datasets like CLSE and IEMOCAP. However, the integrity of these datasets is seldom scrutinized for text-dependency. This paper critically evaluates the prevalent assumption that machine learning models trained on such datasets genuinely learn to identify paralinguistic traits, rather than merely capturing lexical features. By examining the lexical overlap in these datasets and testing the performance of machine learning models, we expose significant text-dependency in trait-labeling. Our results suggest that some machine learning models, especially large pre-trained models like HuBERT, might inadvertently focus on lexical characteristics rather than the intended paralinguistic features. The study serves as a call to action for the research community to reevaluate the reliability of existing datasets and methodologies, ensuring that machine learning models genuinely learn what they are designed to recognize.

Ladislav Mošner, Oldřich Plchot, Lukáš Burget et al.

Motivated by unconsolidated data situation and the lack of a standard benchmark in the field, we complement our previous efforts and present a comprehensive corpus designed for training and evaluating text-independent multi-channel speaker verification systems. It can be readily used also for experiments with dereverberation, denoising, and speech enhancement. We tackled the ever-present problem of the lack of multi-channel training data by utilizing data simulation on top of clean parts of the Voxceleb dataset. The development and evaluation trials are based on a retransmitted Voices Obscured in Complex Environmental Settings (VOiCES) corpus, which we modified to provide multi-channel trials. We publish full recipes that create the dataset from public sources as the MultiSV corpus, and we provide results with two of our multi-channel speaker verification systems with neural network-based beamforming based either on predicting ideal binary masks or the more recent Conv-TasNet.

Martin Kocour, Kateřina Žmolíková, Lucas Ondel et al.

In typical multi-talker speech recognition systems, a neural network-based acoustic model predicts senone state posteriors for each speaker. These are later used by a single-talker decoder which is applied on each speaker-specific output stream separately. In this work, we argue that such a scheme is sub-optimal and propose a principled solution that decodes all speakers jointly. We modify the acoustic model to predict joint state posteriors for all speakers, enabling the network to express uncertainty about the attribution of parts of the speech signal to the speakers. We employ a joint decoder that can make use of this uncertainty together with higher-level language information. For this, we revisit decoding algorithms used in factorial generative models in early multi-talker speech recognition systems. In contrast with these early works, we replace the GMM acoustic model with DNN, which provides greater modeling power and simplifies part of the inference. We demonstrate the advantage of joint decoding in proof of concept experiments on a mixed-TIDIGITS dataset.

Murali Karthick Baskar, Lukáš Burget, Shinji Watanabe et al.

Self-supervised ASR-TTS models suffer in out-of-domain data conditions. Here we propose an enhanced ASR-TTS (EAT) model that incorporates two main features: 1) The ASR$\rightarrow$TTS direction is equipped with a language model reward to penalize the ASR hypotheses before forwarding it to TTS. 2) In the TTS$\rightarrow$ASR direction, a hyper-parameter is introduced to scale the attention context from synthesized speech before sending it to ASR to handle out-of-domain data. Training strategies and the effectiveness of the EAT model are explored under out-of-domain data conditions. The results show that EAT reduces the performance gap between supervised and self-supervised training significantly by absolute 2.6\% and 2.7\% on Librispeech and BABEL respectively.

Martin Kocour, Guillermo Cámbara, Jordi Luque et al.

This paper describes joint effort of BUT and Telefónica Research on development of Automatic Speech Recognition systems for Albayzin 2020 Challenge. We compare approaches based on either hybrid or end-to-end models. In hybrid modelling, we explore the impact of SpecAugment layer on performance. For end-to-end modelling, we used a convolutional neural network with gated linear units (GLUs). The performance of such model is also evaluated with an additional n-gram language model to improve word error rates. We further inspect source separation methods to extract speech from noisy environment (i.e. TV shows). More precisely, we assess the effect of using a neural-based music separator named Demucs. A fusion of our best systems achieved 23.33% WER in official Albayzin 2020 evaluations. Aside from techniques used in our final submitted systems, we also describe our efforts in retrieving high quality transcripts for training.

Bolaji Yusuf, Lucas Ondel, Lukas Burget et al.

In this work, we propose a hierarchical subspace model for acoustic unit discovery. In this approach, we frame the task as one of learning embeddings on a low-dimensional phonetic subspace, and simultaneously specify the subspace itself as an embedding on a hyper-subspace. We train the hyper-subspace on a set of transcribed languages and transfer it to the target language. In the target language, we infer both the language and unit embeddings in an unsupervised manner, and in so doing, we simultaneously learn a subspace of units specific to that language and the units that dwell on it. We conduct our experiments on TIMIT and two low-resource languages: Mboshi and Yoruba. Results show that our model outperforms major acoustic unit discovery techniques, both in terms of clustering quality and segmentation accuracy.

Hari Krishna Vydana, Lukas Burget, Jan Cernocky

The paper describes the BUT's speech translation systems. The systems are English$\longrightarrow$German offline speech translation systems. The systems are based on our previous works \cite{Jointly_trained_transformers}. Though End-to-End and cascade~(ASR-MT) spoken language translation~(SLT) systems are reaching comparable performances, a large degradation is observed when translating ASR hypothesis compared to the oracle input text. To reduce this performance degradation, we have jointly-trained ASR and MT modules with ASR objective as an auxiliary loss. Both the networks are connected through the neural hidden representations. This model has an End-to-End differentiable path with respect to the final objective function and also utilizes the ASR objective for better optimization. During the inference both the modules(i.e., ASR and MT) are connected through the hidden representations corresponding to the n-best hypotheses. Ensembling with independently trained ASR and MT models have further improved the performance of the system.

Martin Karafiát, Murali Karthick Baskar, Igor Szöke et al.

The paper describes the BUT Automatic Speech Recognition (ASR) systems submitted for OpenSAT evaluations under two domain categories such as low resourced languages and public safety communications. The first was challenging due to lack of training data, therefore various architectures and multilingual approaches were employed. The combination led to superior performance. The second domain was challenging due to recording in extreme conditions such as specific channel, speaker under stress and high levels of noise. Data augmentation process was inevitable to get reasonably good performance.

Hossein Zeinali, Lukáš Burget, Jan "Honza'' Černocký

In this report, the Brno University of Technology (BUT) team submissions for Task 1 (Acoustic Scene Classification, ASC) of the DCASE-2019 challenge are described. Also, the analysis of different methods is provided. The proposed approach is a fusion of three different Convolutional Neural Network (CNN) topologies. The first one is a VGG like two-dimensional CNNs. The second one is again a two-dimensional CNN network which uses Max-Feature-Map activation and called Light-CNN (LCNN). The third network is a one-dimensional CNN which mainly used for speaker verification and called x-vector topology. All proposed networks use self-attention mechanism for statistic pooling. As a feature, we use a 256-dimensional log Mel-spectrogram. Our submissions are a fusion of several networks trained on 4-folds generated evaluation setup using different fusion strategies.

Murali Karthick Baskar, Shinji Watanabe, Ramon Astudillo et al.

Sequence-to-sequence automatic speech recognition (ASR) models require large quantities of data to attain high performance. For this reason, there has been a recent surge in interest for unsupervised and semi-supervised training in such models. This work builds upon recent results showing notable improvements in semi-supervised training using cycle-consistency and related techniques. Such techniques derive training procedures and losses able to leverage unpaired speech and/or text data by combining ASR with Text-to-Speech (TTS) models. In particular, this work proposes a new semi-supervised loss combining an end-to-end differentiable ASR$\rightarrow$TTS loss with TTS$\rightarrow$ASR loss. The method is able to leverage both unpaired speech and text data to outperform recently proposed related techniques in terms of \%WER. We provide extensive results analyzing the impact of data quantity and speech and text modalities and show consistent gains across WSJ and Librispeech corpora. Our code is provided in ESPnet to reproduce the experiments.

Lucas Ondel, Hari Krishna Vydana, Lukáš Burget et al.

This work tackles the problem of learning a set of language specific acoustic units from unlabeled speech recordings given a set of labeled recordings from other languages. Our approach may be described by the following two steps procedure: first the model learns the notion of acoustic units from the labelled data and then the model uses its knowledge to find new acoustic units on the target language. We implement this process with the Bayesian Subspace Hidden Markov Model (SHMM), a model akin to the Subspace Gaussian Mixture Model (SGMM) where each low dimensional embedding represents an acoustic unit rather than just a HMM's state. The subspace is trained on 3 languages from the GlobalPhone corpus (German, Polish and Spanish) and the AUs are discovered on the TIMIT corpus. Results, measured in equivalent Phone Error Rate, show that this approach significantly outperforms previous HMM based acoustic units discovery systems and compares favorably with the Variational Auto Encoder-HMM.

Ondrej Novotny, Oldrich Plchot, Ondrej Glembek et al.

In this work, we present an analysis of a DNN-based autoencoder for speech enhancement, dereverberation and denoising. The target application is a robust speaker verification (SV) system. We start our approach by carefully designing a data augmentation process to cover wide range of acoustic conditions and obtain rich training data for various components of our SV system. We augment several well-known databases used in SV with artificially noised and reverberated data and we use them to train a denoising autoencoder (mapping noisy and reverberated speech to its clean version) as well as an x-vector extractor which is currently considered as state-of-the-art in SV. Later, we use the autoencoder as a preprocessing step for text-independent SV system. We compare results achieved with autoencoder enhancement, multi-condition PLDA training and their simultaneous use. We present a detailed analysis with various conditions of NIST SRE 2010, 2016, PRISM and with re-transmitted data. We conclude that the proposed preprocessing can significantly improve both i-vector and x-vector baselines and that this technique can be used to build a robust SV system for various target domains.

Murali Karthick Baskar, Lukáš Burget, Shinji Watanabe et al.

In this paper, we present promising accurate prefix boosting (PAPB), a discriminative training technique for attention based sequence-to-sequence (seq2seq) ASR. PAPB is devised to unify the training and testing scheme in an effective manner. The training procedure involves maximizing the score of each partial correct sequence obtained during beam search compared to other hypotheses. The training objective also includes minimization of token (character) error rate. PAPB shows its efficacy by achieving 10.8\% and 3.8\% WER with and without RNNLM respectively on Wall Street Journal dataset.

Hossein Zeinali, Lukas Burget, Johan Rohdin et al.

Recently, speaker embeddings extracted with deep neural networks became the state-of-the-art method for speaker verification. In this paper we aim to facilitate its implementation on a more generic toolkit than Kaldi, which we anticipate to enable further improvements on the method. We examine several tricks in training, such as the effects of normalizing input features and pooled statistics, different methods for preventing overfitting as well as alternative non-linearities that can be used instead of Rectifier Linear Units. In addition, we investigate the difference in performance between TDNN and CNN, and between two types of attention mechanism. Experimental results on Speaker in the Wild, SRE 2016 and SRE 2018 datasets demonstrate the effectiveness of the proposed implementation.

Hossein Zeinali, Lukas Burget, Jan Cernocky

In this paper, the Brno University of Technology (BUT) team submissions for Task 1 (Acoustic Scene Classification, ASC) of the DCASE-2018 challenge are described. Also, the analysis of different methods on the leaderboard set is provided. The proposed approach is a fusion of two different Convolutional Neural Network (CNN) topologies. The first one is the common two-dimensional CNNs which is mainly used in image classification. The second one is a one-dimensional CNN for extracting fixed-length audio segment embeddings, so called x-vectors, which has also been used in speech processing, especially for speaker recognition. In addition to the different topologies, two types of features were tested: log mel-spectrogram and CQT features. Finally, the outputs of different systems are fused using a simple output averaging in the best performing system. Our submissions ranked third among 24 teams in the ASC sub-task A (task1a).

Hossein Zeinali, Lukas Burget, Hossein Sameti et al.

The task of spoken pass-phrase verification is to decide whether a test utterance contains the same phrase as given enrollment utterances. Beside other applications, pass-phrase verification can complement an independent speaker verification subsystem in text-dependent speaker verification. It can also be used for liveness detection by verifying that the user is able to correctly respond to a randomly prompted phrase. In this paper, we build on our previous work on i-vector based text-dependent speaker verification, where we have shown that i-vectors extracted using phrase specific Hidden Markov Models (HMMs) or using Deep Neural Network (DNN) based bottle-neck (BN) features help to reject utterances with wrong pass-phrases. We apply the same i-vector extraction techniques to the stand-alone task of speaker-independent spoken pass-phrase classification and verification. The experiments on RSR2015 and RedDots databases show that very simple scoring techniques (e.g. cosine distance scoring) applied to such i-vectors can provide results superior to those previously published on the same data.

Murali Karthick Baskar, Martin Karafiat, Lukas Burget et al.

Training deep recurrent neural network (RNN) architectures is complicated due to the increased network complexity. This disrupts the learning of higher order abstracts using deep RNN. In case of feed-forward networks training deep structures is simple and faster while learning long-term temporal information is not possible. In this paper we propose a residual memory neural network (RMN) architecture to model short-time dependencies using deep feed-forward layers having residual and time delayed connections. The residual connection paves way to construct deeper networks by enabling unhindered flow of gradients and the time delay units capture temporal information with shared weights. The number of layers in RMN signifies both the hierarchical processing depth and temporal depth. The computational complexity in training RMN is significantly less when compared to deep recurrent networks. RMN is further extended as bi-directional RMN (BRMN) to capture both past and future information. Experimental analysis is done on AMI corpus to substantiate the capability of RMN in learning long-term information and hierarchical information. Recognition performance of RMN trained with 300 hours of Switchboard corpus is compared with various state-of-the-art LVCSR systems. The results indicate that RMN and BRMN gains 6 % and 3.8 % relative improvement over LSTM and BLSTM networks.