Takuya Yoshioka

Ziyi Yang, Yuwei Fang, Chenguang Zhu et al. · gatech, stanford

Human intelligence is multimodal; we integrate visual, linguistic, and acoustic signals to maintain a holistic worldview. Most current pretraining methods, however, are limited to one or two modalities. We present i-Code, a self-supervised pretraining framework where users may flexibly combine the modalities of vision, speech, and language into unified and general-purpose vector representations. In this framework, data from each modality are first given to pretrained single-modality encoders. The encoder outputs are then integrated with a multimodal fusion network, which uses novel attention mechanisms and other architectural innovations to effectively combine information from the different modalities. The entire system is pretrained end-to-end with new objectives including masked modality unit modeling and cross-modality contrastive learning. Unlike previous research using only video for pretraining, the i-Code framework can dynamically process single, dual, and triple-modality data during training and inference, flexibly projecting different combinations of modalities into a single representation space. Experimental results demonstrate how i-Code can outperform state-of-the-art techniques on five video understanding tasks and the GLUE NLP benchmark, improving by as much as 11% and demonstrating the power of integrative multimodal pretraining.

Muqiao Yang, Naoyuki Kanda, Xiaofei Wang et al. · cmu

Multi-talker automatic speech recognition (ASR) has been studied to generate transcriptions of natural conversation including overlapping speech of multiple speakers. Due to the difficulty in acquiring real conversation data with high-quality human transcriptions, a naïve simulation of multi-talker speech by randomly mixing multiple utterances was conventionally used for model training. In this work, we propose an improved technique to simulate multi-talker overlapping speech with realistic speech overlaps, where an arbitrary pattern of speech overlaps is represented by a sequence of discrete tokens. With this representation, speech overlapping patterns can be learned from real conversations based on a statistical language model, such as N-gram, which can be then used to generate multi-talker speech for training. In our experiments, multi-talker ASR models trained with the proposed method show consistent improvement on the word error rates across multiple datasets.

Tuochao Chen, Qirui Wang, Bohan Wu et al.

Extracting the speech of participants in a conversation amidst interfering speakers and noise presents a challenging problem. In this paper, we introduce the novel task of target conversation extraction, where the goal is to extract the audio of a target conversation based on the speaker embedding of one of its participants. To accomplish this, we propose leveraging temporal patterns inherent in human conversations, particularly turn-taking dynamics, which uniquely characterize speakers engaged in conversation and distinguish them from interfering speakers and noise. Using neural networks, we show the feasibility of our approach on English and Mandarin conversation datasets. In the presence of interfering speakers, our results show an 8.19 dB improvement in signal-to-noise ratio for 2-speaker conversations and a 7.92 dB improvement for 2-4-speaker conversations. Code, dataset available at https://github.com/chentuochao/Target-Conversation-Extraction.

Mu Yang, Naoyuki Kanda, Xiaofei Wang et al. · cmu

End-to-end speech translation (ST) for conversation recordings involves several under-explored challenges such as speaker diarization (SD) without accurate word time stamps and handling of overlapping speech in a streaming fashion. In this work, we propose DiariST, the first streaming ST and SD solution. It is built upon a neural transducer-based streaming ST system and integrates token-level serialized output training and t-vector, which were originally developed for multi-talker speech recognition. Due to the absence of evaluation benchmarks in this area, we develop a new evaluation dataset, DiariST-AliMeeting, by translating the reference Chinese transcriptions of the AliMeeting corpus into English. We also propose new metrics, called speaker-agnostic BLEU and speaker-attributed BLEU, to measure the ST quality while taking SD accuracy into account. Our system achieves a strong ST and SD capability compared to offline systems based on Whisper, while performing streaming inference for overlapping speech. To facilitate the research in this new direction, we release the evaluation data, the offline baseline systems, and the evaluation code.

Xiaofei Wang, Manthan Thakker, Zhuo Chen et al.

Recent advancements in generative speech models based on audio-text prompts have enabled remarkable innovations like high-quality zero-shot text-to-speech. However, existing models still face limitations in handling diverse audio-text speech generation tasks involving transforming input speech and processing audio captured in adverse acoustic conditions. This paper introduces SpeechX, a versatile speech generation model capable of zero-shot TTS and various speech transformation tasks, dealing with both clean and noisy signals. SpeechX combines neural codec language modeling with multi-task learning using task-dependent prompting, enabling unified and extensible modeling and providing a consistent way for leveraging textual input in speech enhancement and transformation tasks. Experimental results show SpeechX's efficacy in various tasks, including zero-shot TTS, noise suppression, target speaker extraction, speech removal, and speech editing with or without background noise, achieving comparable or superior performance to specialized models across tasks. See https://aka.ms/speechx for demo samples.

Bandhav Veluri, Justin Chan, Malek Itani et al.

We present the first neural network model to achieve real-time and streaming target sound extraction. To accomplish this, we propose Waveformer, an encoder-decoder architecture with a stack of dilated causal convolution layers as the encoder, and a transformer decoder layer as the decoder. This hybrid architecture uses dilated causal convolutions for processing large receptive fields in a computationally efficient manner while also leveraging the generalization performance of transformer-based architectures. Our evaluations show as much as 2.2-3.3 dB improvement in SI-SNRi compared to the prior models for this task while having a 1.2-4x smaller model size and a 1.5-2x lower runtime. We provide code, dataset, and audio samples: https://waveformer.cs.washington.edu/.

Bandhav Veluri, Malek Itani, Justin Chan et al.

Imagine being able to listen to the birds chirping in a park without hearing the chatter from other hikers, or being able to block out traffic noise on a busy street while still being able to hear emergency sirens and car honks. We introduce semantic hearing, a novel capability for hearable devices that enables them to, in real-time, focus on, or ignore, specific sounds from real-world environments, while also preserving the spatial cues. To achieve this, we make two technical contributions: 1) we present the first neural network that can achieve binaural target sound extraction in the presence of interfering sounds and background noise, and 2) we design a training methodology that allows our system to generalize to real-world use. Results show that our system can operate with 20 sound classes and that our transformer-based network has a runtime of 6.56 ms on a connected smartphone. In-the-wild evaluation with participants in previously unseen indoor and outdoor scenarios shows that our proof-of-concept system can extract the target sounds and generalize to preserve the spatial cues in its binaural output. Project page with code: https://semantichearing.cs.washington.edu

Zhuo Chen, Naoyuki Kanda, Jian Wu et al.

Self-supervised learning (SSL) methods such as WavLM have shown promising speech separation (SS) results in small-scale simulation-based experiments. In this work, we extend the exploration of the SSL-based SS by massively scaling up both the pre-training data (more than 300K hours) and fine-tuning data (10K hours). We also investigate various techniques to efficiently integrate the pre-trained model with the SS network under a limited computation budget, including a low frame rate SSL model training setup and a fine-tuning scheme using only the part of the pre-trained model. Compared with a supervised baseline and the WavLM-based SS model using feature embeddings obtained with the previously released 94K hours trained WavLM, our proposed model obtains 15.9% and 11.2% of relative word error rate (WER) reductions, respectively, for a simulated far-field speech mixture test set. For conversation transcription on real meeting recordings using continuous speech separation, the proposed model achieves 6.8% and 10.6% of relative WER reductions over the purely supervised baseline on AMI and ICSI evaluation sets, respectively, while reducing the computational cost by 38%.

Dongmei Wang, Xiong Xiao, Naoyuki Kanda et al.

This paper describes a speaker diarization model based on target speaker voice activity detection (TS-VAD) using transformers. To overcome the original TS-VAD model's drawback of being unable to handle an arbitrary number of speakers, we investigate model architectures that use input tensors with variable-length time and speaker dimensions. Transformer layers are applied to the speaker axis to make the model output insensitive to the order of the speaker profiles provided to the TS-VAD model. Time-wise sequential layers are interspersed between these speaker-wise transformer layers to allow the temporal and cross-speaker correlations of the input speech signal to be captured. We also extend a diarization model based on end-to-end neural diarization with encoder-decoder based attractors (EEND-EDA) by replacing its dot-product-based speaker detection layer with the transformer-based TS-VAD. Experimental results on VoxConverse show that using the transformers for the cross-speaker modeling reduces the diarization error rate (DER) of TS-VAD by 11.3%, achieving a new state-of-the-art (SOTA) DER of 4.57%. Also, our extended EEND-EDA reduces DER by 6.9% on the CALLHOME dataset relative to the original EEND-EDA with a similar model size, achieving a new SOTA DER of 11.18% under a widely used training data setting.

Naoyuki Kanda, Jian Wu, Xiaofei Wang et al.

This paper presents a novel streaming automatic speech recognition (ASR) framework for multi-talker overlapping speech captured by a distant microphone array with an arbitrary geometry. Our framework, named t-SOT-VA, capitalizes on independently developed two recent technologies; array-geometry-agnostic continuous speech separation, or VarArray, and streaming multi-talker ASR based on token-level serialized output training (t-SOT). To combine the best of both technologies, we newly design a t-SOT-based ASR model that generates a serialized multi-talker transcription based on two separated speech signals from VarArray. We also propose a pre-training scheme for such an ASR model where we simulate VarArray's output signals based on monaural single-talker ASR training data. Conversation transcription experiments using the AMI meeting corpus show that the system based on the proposed framework significantly outperforms conventional ones. Our system achieves the state-of-the-art word error rates of 13.7% and 15.5% for the AMI development and evaluation sets, respectively, in the multiple-distant-microphone setting while retaining the streaming inference capability.

Sanyuan Chen, Yu Wu, Zhuo Chen et al.

Transformer has been successfully applied to speech separation recently with its strong long-dependency modeling capacity using a self-attention mechanism. However, Transformer tends to have heavy run-time costs due to the deep encoder layers, which hinders its deployment on edge devices. A small Transformer model with fewer encoder layers is preferred for computational efficiency, but it is prone to performance degradation. In this paper, an ultra fast speech separation Transformer model is proposed to achieve both better performance and efficiency with teacher student learning (T-S learning). We introduce layer-wise T-S learning and objective shifting mechanisms to guide the small student model to learn intermediate representations from the large teacher model. Compared with the small Transformer model trained from scratch, the proposed T-S learning method reduces the word error rate (WER) by more than 5% for both multi-channel and single-channel speech separation on LibriCSS dataset. Utilizing more unlabeled speech data, our ultra fast speech separation models achieve more than 10% relative WER reduction.

Xiaofei Wang, Dongmei Wang, Naoyuki Kanda et al.

Existing multi-channel continuous speech separation (CSS) models are heavily dependent on supervised data - either simulated data which causes data mismatch between the training and real-data testing, or the real transcribed overlapping data, which is difficult to be acquired, hindering further improvements in the conversational/meeting transcription tasks. In this paper, we propose a three-stage training scheme for the CSS model that can leverage both supervised data and extra large-scale unsupervised real-world conversational data. The scheme consists of two conventional training approaches -- pre-training using simulated data and ASR-loss-based training using transcribed data -- and a novel continuous semi-supervised training between the two, in which the CSS model is further trained by using real data based on the teacher-student learning framework. We apply this scheme to an array-geometry-agnostic CSS model, which can use the multi-channel data collected from any microphone array. Large-scale meeting transcription experiments are carried out on both Microsoft internal meeting data and the AMI meeting corpus. The steady improvement by each training stage has been observed, showing the effect of the proposed method that enables leveraging real conversational data for CSS model training.

Naoyuki Kanda, Takuya Yoshioka, Yang Liu

This paper presents a novel optimization framework for automatic speech recognition (ASR) with the aim of reducing hallucinations produced by an ASR model. The proposed framework optimizes the ASR model to maximize an expected factual consistency score between ASR hypotheses and ground-truth transcriptions, where the factual consistency score is computed by a separately trained estimator. Experimental results using the AMI meeting corpus and the VoxPopuli corpus show that the ASR model trained with the proposed framework generates ASR hypotheses that have significantly higher consistency scores with ground-truth transcriptions while maintaining the word error rates close to those of cross entropy-trained ASR models. Furthermore, it is shown that training the ASR models with the proposed framework improves the speech summarization quality as measured by the factual consistency of meeting conversation summaries generated by a large language model.

Vidya Srinivas, Malek Itani, Tuochao Chen et al.

Models for low-latency, streaming applications could benefit from the knowledge capacity of larger models, but edge devices cannot run these models due to resource constraints. A possible solution is to transfer hints during inference from a large model running remotely to a small model running on-device. However, this incurs a communication delay that breaks real-time requirements and does not guarantee that both models will operate on the same data at the same time. We propose knowledge boosting, a novel technique that allows a large model to operate on time-delayed input during inference, while still boosting small model performance. Using a streaming neural network that processes 8 ms chunks, we evaluate different speech separation and enhancement tasks with communication delays of up to six chunks or 48 ms. Our results show larger gains where the performance gap between the small and large models is wide, demonstrating a promising method for large-small model collaboration for low-latency applications. Code, dataset, and audio samples available at https://knowledgeboosting.cs.washington.edu/.

Bandhav Veluri, Malek Itani, Tuochao Chen et al.

In crowded settings, the human brain can focus on speech from a target speaker, given prior knowledge of how they sound. We introduce a novel intelligent hearable system that achieves this capability, enabling target speech hearing to ignore all interfering speech and noise, but the target speaker. A naive approach is to require a clean speech example to enroll the target speaker. This is however not well aligned with the hearable application domain since obtaining a clean example is challenging in real world scenarios, creating a unique user interface problem. We present the first enrollment interface where the wearer looks at the target speaker for a few seconds to capture a single, short, highly noisy, binaural example of the target speaker. This noisy example is used for enrollment and subsequent speech extraction in the presence of interfering speakers and noise. Our system achieves a signal quality improvement of 7.01 dB using less than 5 seconds of noisy enrollment audio and can process 8 ms of audio chunks in 6.24 ms on an embedded CPU. Our user studies demonstrate generalization to real-world static and mobile speakers in previously unseen indoor and outdoor multipath environments. Finally, our enrollment interface for noisy examples does not cause performance degradation compared to clean examples, while being convenient and user-friendly. Taking a step back, this paper takes an important step towards enhancing the human auditory perception with artificial intelligence. We provide code and data at: https://github.com/vb000/LookOnceToHear.

Harishchandra Dubey, Vishak Gopal, Ross Cutler et al.

The Deep Noise Suppression (DNS) challenge is designed to foster innovation in the area of noise suppression to achieve superior perceptual speech quality. This is the 4th DNS challenge, with the previous editions held at INTERSPEECH 2020, ICASSP 2021, and INTERSPEECH 2021. We open-source datasets and test sets for researchers to train their deep noise suppression models, as well as a subjective evaluation framework based on ITU-T P.835 to rate and rank-order the challenge entries. We provide access to DNSMOS P.835 and word accuracy (WAcc) APIs to challenge participants to help with iterative model improvements. In this challenge, we introduced the following changes: (i) Included mobile device scenarios in the blind test set; (ii) Included a personalized noise suppression track with baseline; (iii) Added WAcc as an objective metric; (iv) Included DNSMOS P.835; (v) Made the training datasets and test sets fullband (48 kHz). We use an average of WAcc and subjective scores P.835 SIG, BAK, and OVRL to get the final score for ranking the DNS models. We believe that as a research community, we still have a long way to go in achieving excellent speech quality in challenging noisy real-world scenarios.

Shinji Watanabe, Michael Mandel, Jon Barker et al.

Following the success of the 1st, 2nd, 3rd, 4th and 5th CHiME challenges we organize the 6th CHiME Speech Separation and Recognition Challenge (CHiME-6). The new challenge revisits the previous CHiME-5 challenge and further considers the problem of distant multi-microphone conversational speech diarization and recognition in everyday home environments. Speech material is the same as the previous CHiME-5 recordings except for accurate array synchronization. The material was elicited using a dinner party scenario with efforts taken to capture data that is representative of natural conversational speech. This paper provides a baseline description of the CHiME-6 challenge for both segmented multispeaker speech recognition (Track 1) and unsegmented multispeaker speech recognition (Track 2). Of note, Track 2 is the first challenge activity in the community to tackle an unsegmented multispeaker speech recognition scenario with a complete set of reproducible open source baselines providing speech enhancement, speaker diarization, and speech recognition modules.

Francis McCann Ramirez, Luka Chkhetiani, Andrew Ehrenberg et al. · deepmind

This paper describes AssemblyAI's industrial-scale automatic speech recognition (ASR) system, designed to meet the requirements of large-scale, multilingual ASR serving various application needs. Our system leverages a diverse training dataset comprising unsupervised (12.5M hours), supervised (188k hours), and pseudo-labeled (1.6M hours) data across four languages. We provide a detailed description of our model architecture, consisting of a full-context 600M-parameter Conformer encoder pre-trained with BEST-RQ and an RNN-T decoder fine-tuned jointly with the encoder. Our extensive evaluation demonstrates competitive word error rates (WERs) against larger and more computationally expensive models, such as Whisper large and Canary-1B. Furthermore, our architectural choices yield several key advantages, including an improved code-switching capability, a 5x inference speedup compared to an optimized Whisper baseline, a 30% reduction in hallucination rate on speech data, and a 90% reduction in ambient noise compared to Whisper, along with significantly improved time-stamp accuracy. Throughout this work, we adopt a system-centric approach to analyzing various aspects of fully-fledged ASR models to gain practically relevant insights useful for real-world services operating at scale.

Yash Khare, Taufiquzzaman Peyash, Andrea Vanzo et al.

This paper introduces an all-neural text formatting (TF) model designed for commercial automatic speech recognition (ASR) systems, encompassing punctuation restoration (PR), truecasing, and inverse text normalization (ITN). Unlike traditional rule-based or hybrid approaches, this method leverages a two-stage neural architecture comprising a multi-objective token classifier and a sequence-to-sequence (seq2seq) model. This design minimizes computational costs and reduces hallucinations while ensuring flexibility and robustness across diverse linguistic entities and text domains. Developed as part of the Universal-2 ASR system, the proposed method demonstrates superior performance in TF accuracy, computational efficiency, and perceptual quality, as validated through comprehensive evaluations using both objective and subjective methods. This work underscores the importance of holistic TF models in enhancing ASR usability in practical settings.

Chenda Li, Yao Qian, Zhuo Chen et al.

State-of-the-art large-scale universal speech models (USMs) show a decent automatic speech recognition (ASR) performance across multiple domains and languages. However, it remains a challenge for these models to recognize overlapped speech, which is often seen in meeting conversations. We propose an approach to adapt USMs for multi-talker ASR. We first develop an enhanced version of serialized output training to jointly perform multi-talker ASR and utterance timestamp prediction. That is, we predict the ASR hypotheses for all speakers, count the speakers, and estimate the utterance timestamps at the same time. We further introduce a lightweight adapter module to maintain the multilingual property of the USMs even when we perform the adaptation with only a single language. Experimental results obtained using the AMI and AliMeeting corpora show that our proposed approach effectively transfers the USMs to a strong multilingual multi-talker ASR model with timestamp prediction capability.

Yuwei Fang, Mahmoud Khademi, Chenguang Zhu et al.

Artificial General Intelligence (AGI) requires comprehensive understanding and generation capabilities for a variety of tasks spanning different modalities and functionalities. Integrative AI is one important direction to approach AGI, through combining multiple models to tackle complex multimodal tasks. However, there is a lack of a flexible and composable platform to facilitate efficient and effective model composition and coordination. In this paper, we propose the i-Code Studio, a configurable and composable framework for Integrative AI. The i-Code Studio orchestrates multiple pre-trained models in a finetuning-free fashion to conduct complex multimodal tasks. Instead of simple model composition, the i-Code Studio provides an integrative, flexible, and composable setting for developers to quickly and easily compose cutting-edge services and technologies tailored to their specific requirements. The i-Code Studio achieves impressive results on a variety of zero-shot multimodal tasks, such as video-to-text retrieval, speech-to-speech translation, and visual question answering. We also demonstrate how to quickly build a multimodal agent based on the i-Code Studio that can communicate and personalize for users.

Ziyi Yang, Mahmoud Khademi, Yichong Xu et al.

The convergence of text, visual, and audio data is a key step towards human-like artificial intelligence, however the current Vision-Language-Speech landscape is dominated by encoder-only models which lack generative abilities. We propose closing this gap with i-Code V2, the first model capable of generating natural language from any combination of Vision, Language, and Speech data. i-Code V2 is an integrative system that leverages state-of-the-art single-modality encoders, combining their outputs with a new modality-fusing encoder in order to flexibly project combinations of modalities into a shared representational space. Next, language tokens are generated from these representations via an autoregressive decoder. The whole framework is pretrained end-to-end on a large collection of dual- and single-modality datasets using a novel text completion objective that can be generalized across arbitrary combinations of modalities. i-Code V2 matches or outperforms state-of-the-art single- and dual-modality baselines on 7 multimodal tasks, demonstrating the power of generative multimodal pretraining across a diversity of tasks and signals.

Naoyuki Kanda, Jian Wu, Yu Wu et al.

This paper presents a streaming speaker-attributed automatic speech recognition (SA-ASR) model that can recognize ``who spoke what'' with low latency even when multiple people are speaking simultaneously. Our model is based on token-level serialized output training (t-SOT) which was recently proposed to transcribe multi-talker speech in a streaming fashion. To further recognize speaker identities, we propose an encoder-decoder based speaker embedding extractor that can estimate a speaker representation for each recognized token not only from non-overlapping speech but also from overlapping speech. The proposed speaker embedding, named t-vector, is extracted synchronously with the t-SOT ASR model, enabling joint execution of speaker identification (SID) or speaker diarization (SD) with the multi-talker transcription with low latency. We evaluate the proposed model for a joint task of ASR and SID/SD by using LibriSpeechMix and LibriCSS corpora. The proposed model achieves substantially better accuracy than a prior streaming model and shows comparable or sometimes even superior results to the state-of-the-art offline SA-ASR model.

Naoyuki Kanda, Jian Wu, Yu Wu et al.

This paper proposes a token-level serialized output training (t-SOT), a novel framework for streaming multi-talker automatic speech recognition (ASR). Unlike existing streaming multi-talker ASR models using multiple output branches, the t-SOT model has only a single output branch that generates recognition tokens (e.g., words, subwords) of multiple speakers in chronological order based on their emission times. A special token that indicates the change of ``virtual'' output channels is introduced to keep track of the overlapping utterances. Compared to the prior streaming multi-talker ASR models, the t-SOT model has the advantages of less inference cost and a simpler model architecture. Moreover, in our experiments with LibriSpeechMix and LibriCSS datasets, the t-SOT-based transformer transducer model achieves the state-of-the-art word error rates by a significant margin to the prior results. For non-overlapping speech, the t-SOT model is on par with a single-talker ASR model in terms of both accuracy and computational cost, opening the door for deploying one model for both single- and multi-talker scenarios.

Takuya Yoshioka, Xiaofei Wang, Dongmei Wang

This paper proposes PickNet, a neural network model for real-time channel selection for an ad hoc microphone array consisting of multiple recording devices like cell phones. Assuming at most one person to be vocally active at each time point, PickNet identifies the device that is spatially closest to the active person for each time frame by using a short spectral patch of just hundreds of milliseconds. The model is applied to every time frame, and the short time frame signals from the selected microphones are concatenated across the frames to produce an output signal. As the personal devices are usually held close to their owners, the output signal is expected to have higher signal-to-noise and direct-to-reverberation ratios on average than the input signals. Since PickNet utilizes only limited acoustic context at each time frame, the system using the proposed model works in real time and is robust to changes in acoustic conditions. Speech recognition-based evaluation was carried out by using real conversational recordings obtained with various smartphones. The proposed model yielded significant gains in word error rate with limited computational cost over systems using a block-online beamformer and a single distant microphone.

Heming Wang, Yao Qian, Xiaofei Wang et al.

Noise robustness is essential for deploying automatic speech recognition (ASR) systems in real-world environments. One way to reduce the effect of noise interference is to employ a preprocessing module that conducts speech enhancement, and then feed the enhanced speech to an ASR backend. In this work, instead of suppressing background noise with a conventional cascaded pipeline, we employ a noise-robust representation learned by a refined self-supervised framework for noisy speech recognition. We propose to combine a reconstruction module with contrastive learning and perform multi-task continual pre-training on noisy data. The reconstruction module is used for auxiliary learning to improve the noise robustness of the learned representation and thus is not required during inference. Experiments demonstrate the effectiveness of our proposed method. Our model substantially reduces the word error rate (WER) for the synthesized noisy LibriSpeech test sets, and yields around 4.1/7.5% WER reduction on noisy clean/other test sets compared to data augmentation. For the real-world noisy speech from the CHiME-4 challenge (1-channel track), we have obtained the state of the art ASR performance without any denoising front-end. Moreover, we achieve comparable performance to the best supervised approach reported with only 16% of labeled data.

Yixuan Zhang, Zhuo Chen, Jian Wu et al.

While permutation invariant training (PIT) based continuous speech separation (CSS) significantly improves the conversation transcription accuracy, it often suffers from speech leakages and failures in separation at "hot spot" regions because it has a fixed number of output channels. In this paper, we propose to apply recurrent selective attention network (RSAN) to CSS, which generates a variable number of output channels based on active speaker counting. In addition, we propose a novel block-wise dependency extension of RSAN by introducing dependencies between adjacent processing blocks in the CSS framework. It enables the network to utilize the separation results from the previous blocks to facilitate the current block processing. Experimental results on the LibriCSS dataset show that the RSAN-based CSS (RSAN-CSS) network consistently improves the speech recognition accuracy over PIT-based models. The proposed block-wise dependency modeling further boosts the performance of RSAN-CSS.

Wangyou Zhang, Zhuo Chen, Naoyuki Kanda et al.

Multi-talker conversational speech processing has drawn many interests for various applications such as meeting transcription. Speech separation is often required to handle overlapped speech that is commonly observed in conversation. Although the original utterancelevel permutation invariant training-based continuous speech separation approach has proven to be effective in various conditions, it lacks the ability to leverage the long-span relationship of utterances and is computationally inefficient due to the highly overlapped sliding windows. To overcome these drawbacks, we propose a novel training scheme named Group-PIT, which allows direct training of the speech separation models on the long-form speech with a low computational cost for label assignment. Two different speech separation approaches with Group-PIT are explored, including direct long-span speech separation and short-span speech separation with long-span tracking. The experiments on the simulated meeting-style data demonstrate the effectiveness of our proposed approaches, especially in dealing with a very long speech input.

Sanyuan Chen, Chengyi Wang, Zhengyang Chen et al.

Self-supervised learning (SSL) achieves great success in speech recognition, while limited exploration has been attempted for other speech processing tasks. As speech signal contains multi-faceted information including speaker identity, paralinguistics, spoken content, etc., learning universal representations for all speech tasks is challenging. To tackle the problem, we propose a new pre-trained model, WavLM, to solve full-stack downstream speech tasks. WavLM jointly learns masked speech prediction and denoising in pre-training. By this means, WavLM does not only keep the speech content modeling capability by the masked speech prediction, but also improves the potential to non-ASR tasks by the speech denoising. In addition, WavLM employs gated relative position bias for the Transformer structure to better capture the sequence ordering of input speech. We also scale up the training dataset from 60k hours to 94k hours. WavLM Large achieves state-of-the-art performance on the SUPERB benchmark, and brings significant improvements for various speech processing tasks on their representative benchmarks. The code and pre-trained models are available at https://aka.ms/wavlm.

Hassan Taherian, Sefik Emre Eskimez, Takuya Yoshioka et al.

With the recent surge of video conferencing tools usage, providing high-quality speech signals and accurate captions have become essential to conduct day-to-day business or connect with friends and families. Single-channel personalized speech enhancement (PSE) methods show promising results compared with the unconditional speech enhancement (SE) methods in these scenarios due to their ability to remove interfering speech in addition to the environmental noise. In this work, we leverage spatial information afforded by microphone arrays to improve such systems' performance further. We investigate the relative importance of speaker embeddings and spatial features. Moreover, we propose a new causal array-geometry-agnostic multi-channel PSE model, which can generate a high-quality enhanced signal from arbitrary microphone geometry. Experimental results show that the proposed geometry agnostic model outperforms the model trained on a specific microphone array geometry in both speech quality and automatic speech recognition accuracy. We also demonstrate the effectiveness of the proposed approach for unseen array geometries.

Sefik Emre Eskimez, Takuya Yoshioka, Huaming Wang et al.

Personalized speech enhancement (PSE) models utilize additional cues, such as speaker embeddings like d-vectors, to remove background noise and interfering speech in real-time and thus improve the speech quality of online video conferencing systems for various acoustic scenarios. In this work, we propose two neural networks for PSE that achieve superior performance to the previously proposed VoiceFilter. In addition, we create test sets that capture a variety of scenarios that users can encounter during video conferencing. Furthermore, we propose a new metric to measure the target speaker over-suppression (TSOS) problem, which was not sufficiently investigated before despite its critical importance in deployment. Besides, we propose multi-task training with a speech recognition back-end. Our results show that the proposed models can yield better speech recognition accuracy, speech intelligibility, and perceptual quality than the baseline models, and the multi-task training can alleviate the TSOS issue in addition to improving the speech recognition accuracy.

Zhuohuang Zhang, Takuya Yoshioka, Naoyuki Kanda et al.

Continuous speech separation (CSS) aims to separate overlapping voices from a continuous influx of conversational audio containing an unknown number of utterances spoken by an unknown number of speakers. A common application scenario is transcribing a meeting conversation recorded by a microphone array. Prior studies explored various deep learning models for time-frequency mask estimation, followed by a minimum variance distortionless response (MVDR) filter to improve the automatic speech recognition (ASR) accuracy. The performance of these methods is fundamentally upper-bounded by MVDR's spatial selectivity. Recently, the all deep learning MVDR (ADL-MVDR) model was proposed for neural beamforming and demonstrated superior performance in a target speech extraction task using pre-segmented input. In this paper, we further adapt ADL-MVDR to the CSS task with several enhancements to enable end-to-end neural beamforming. The proposed system achieves significant word error rate reduction over a baseline spectral masking system on the LibriCSS dataset. Moreover, the proposed neural beamformer is shown to be comparable to a state-of-the-art MVDR-based system in real meeting transcription tasks, including AMI, while showing potentials to further simplify the runtime implementation and reduce the system latency with frame-wise processing.

Takuya Yoshioka, Xiaofei Wang, Dongmei Wang et al.

Continuous speech separation using a microphone array was shown to be promising in dealing with the speech overlap problem in natural conversation transcription. This paper proposes VarArray, an array-geometry-agnostic speech separation neural network model. The proposed model is applicable to any number of microphones without retraining while leveraging the nonlinear correlation between the input channels. The proposed method adapts different elements that were proposed before separately, including transform-average-concatenate, conformer speech separation, and inter-channel phase differences, and combines them in an efficient and cohesive way. Large-scale evaluation was performed with two real meeting transcription tasks by using a fully developed transcription system requiring no prior knowledge such as reference segmentations, which allowed us to measure the impact that the continuous speech separation system could have in realistic settings. The proposed model outperformed a previous approach to array-geometry-agnostic modeling for all of the geometry configurations considered, achieving asclite-based speaker-agnostic word error rates of 17.5% and 20.4% for the AMI development and evaluation sets, respectively, in the end-to-end setting using no ground-truth segmentations.

Naoyuki Kanda, Xiong Xiao, Yashesh Gaur et al.

This paper presents Transcribe-to-Diarize, a new approach for neural speaker diarization that uses an end-to-end (E2E) speaker-attributed automatic speech recognition (SA-ASR). The E2E SA-ASR is a joint model that was recently proposed for speaker counting, multi-talker speech recognition, and speaker identification from monaural audio that contains overlapping speech. Although the E2E SA-ASR model originally does not estimate any time-related information, we show that the start and end times of each word can be estimated with sufficient accuracy from the internal state of the E2E SA-ASR by adding a small number of learnable parameters. Similar to the target-speaker voice activity detection (TS-VAD)-based diarization method, the E2E SA-ASR model is applied to estimate speech activity of each speaker while it has the advantages of (i) handling unlimited number of speakers, (ii) leveraging linguistic information for speaker diarization, and (iii) simultaneously generating speaker-attributed transcriptions. Experimental results on the LibriCSS and AMI corpora show that the proposed method achieves significantly better diarization error rate than various existing speaker diarization methods when the number of speakers is unknown, and achieves a comparable performance to TS-VAD when the number of speakers is given in advance. The proposed method simultaneously generates speaker-attributed transcription with state-of-the-art accuracy.

Naoyuki Kanda, Xiong Xiao, Jian Wu et al.

Speaker-attributed automatic speech recognition (SA-ASR) is a task to recognize "who spoke what" from multi-talker recordings. An SA-ASR system usually consists of multiple modules such as speech separation, speaker diarization and ASR. On the other hand, considering the joint optimization, an end-to-end (E2E) SA-ASR model has recently been proposed with promising results on simulation data. In this paper, we present our recent study on the comparison of such modular and joint approaches towards SA-ASR on real monaural recordings. We develop state-of-the-art SA-ASR systems for both modular and joint approaches by leveraging large-scale training data, including 75 thousand hours of ASR training data and the VoxCeleb corpus for speaker representation learning. We also propose a new pipeline that performs the E2E SA-ASR model after speaker clustering. Our evaluation on the AMI meeting corpus reveals that after fine-tuning with a small real data, the joint system performs 8.9--29.9% better in accuracy compared to the best modular system while the modular system performs better before such fine-tuning. We also conduct various error analyses to show the remaining issues for the monaural SA-ASR.

Jian Wu, Zhuo Chen, Sanyuan Chen et al.

Speech separation has been successfully applied as a frontend processing module of conversation transcription systems thanks to its ability to handle overlapped speech and its flexibility to combine with downstream tasks such as automatic speech recognition (ASR). However, a speech separation model often introduces target speech distortion, resulting in a sub-optimum word error rate (WER). In this paper, we describe our efforts to improve the performance of a single channel speech separation system. Specifically, we investigate a two-stage training scheme that firstly applies a feature level optimization criterion for pretraining, followed by an ASR-oriented optimization criterion using an end-to-end (E2E) speech recognition model. Meanwhile, to keep the model light-weight, we introduce a modified teacher-student learning technique for model compression. By combining those approaches, we achieve a absolute average WER improvement of 2.70% and 0.77% using models with less than 10M parameters compared with the previous state-of-the-art results on the LibriCSS dataset for utterance-wise evaluation and continuous evaluation, respectively

Naoyuki Kanda, Guoli Ye, Yashesh Gaur et al.

This paper presents our recent effort on end-to-end speaker-attributed automatic speech recognition, which jointly performs speaker counting, speech recognition and speaker identification for monaural multi-talker audio. Firstly, we thoroughly update the model architecture that was previously designed based on a long short-term memory (LSTM)-based attention encoder decoder by applying transformer architectures. Secondly, we propose a speaker deduplication mechanism to reduce speaker identification errors in highly overlapped regions. Experimental results on the LibriSpeechMix dataset shows that the transformer-based architecture is especially good at counting the speakers and that the proposed model reduces the speaker-attributed word error rate by 47% over the LSTM-based baseline. Furthermore, for the LibriCSS dataset, which consists of real recordings of overlapped speech, the proposed model achieves concatenated minimum-permutation word error rates of 11.9% and 16.3% with and without target speaker profiles, respectively, both of which are the state-of-the-art results for LibriCSS with the monaural setting.

Naoyuki Kanda, Guoli Ye, Yu Wu et al.

Transcribing meetings containing overlapped speech with only a single distant microphone (SDM) has been one of the most challenging problems for automatic speech recognition (ASR). While various approaches have been proposed, all previous studies on the monaural overlapped speech recognition problem were based on either simulation data or small-scale real data. In this paper, we extensively investigate a two-step approach where we first pre-train a serialized output training (SOT)-based multi-talker ASR by using large-scale simulation data and then fine-tune the model with a small amount of real meeting data. Experiments are conducted by utilizing 75 thousand (K) hours of our internal single-talker recording to simulate a total of 900K hours of multi-talker audio segments for supervised pre-training. With fine-tuning on the 70 hours of the AMI-SDM training data, our SOT ASR model achieves a word error rate (WER) of 21.2% for the AMI-SDM evaluation set while automatically counting speakers in each test segment. This result is not only significantly better than the previous state-of-the-art WER of 36.4% with oracle utterance boundary information but also better than a result by a similarly fine-tuned single-talker ASR model applied to beamformed audio.

Dongmei Wang, Takuya Yoshioka, Zhuo Chen et al.

Speech separation has been shown effective for multi-talker speech recognition. Under the ad hoc microphone array setup where the array consists of spatially distributed asynchronous microphones, additional challenges must be overcome as the geometry and number of microphones are unknown beforehand. Prior studies show, with a spatial-temporalinterleaving structure, neural networks can efficiently utilize the multi-channel signals of the ad hoc array. In this paper, we further extend this approach to continuous speech separation. Several techniques are introduced to enable speech separation for real continuous recordings. First, we apply a transformer-based network for spatio-temporal modeling of the ad hoc array signals. In addition, two methods are proposed to mitigate a speech duplication problem during single talker segments, which seems more severe in the ad hoc array scenarios. One method is device distortion simulation for reducing the acoustic mismatch between simulated training data and real recordings. The other is speaker counting to detect the single speaker segments and merge the output signal channels. Experimental results for AdHoc-LibiCSS, a new dataset consisting of continuous recordings of concatenated LibriSpeech utterances obtained by multiple different devices, show the proposed separation method can significantly improve the ASR accuracy for overlapped speech with little performance degradation for single talker segments.

Xuankai Chang, Naoyuki Kanda, Yashesh Gaur et al.

An end-to-end (E2E) speaker-attributed automatic speech recognition (SA-ASR) model was proposed recently to jointly perform speaker counting, speech recognition and speaker identification. The model achieved a low speaker-attributed word error rate (SA-WER) for monaural overlapped speech comprising an unknown number of speakers. However, the E2E modeling approach is susceptible to the mismatch between the training and testing conditions. It has yet to be investigated whether the E2E SA-ASR model works well for recordings that are much longer than samples seen during training. In this work, we first apply a known decoding technique that was developed to perform single-speaker ASR for long-form audio to our E2E SA-ASR task. Then, we propose a novel method using a sequence-to-sequence model, called hypothesis stitcher. The model takes multiple hypotheses obtained from short audio segments that are extracted from the original long-form input, and it then outputs a fused single hypothesis. We propose several architectural variations of the hypothesis stitcher model and compare them with the conventional decoding methods. Experiments using LibriSpeech and LibriCSS corpora show that the proposed method significantly improves SA-WER especially for long-form multi-talker recordings.

Xiaofei Wang, Naoyuki Kanda, Yashesh Gaur et al.

Joint optimization of multi-channel front-end and automatic speech recognition (ASR) has attracted much interest. While promising results have been reported for various tasks, past studies on its meeting transcription application were limited to small scale experiments. It is still unclear whether such a joint framework can be beneficial for a more practical setup where a massive amount of single channel training data can be leveraged for building a strong ASR back-end. In this work, we present our investigation on the joint modeling of a mask-based beamformer and Attention-Encoder-Decoder-based ASR in the setting where we have 75k hours of single-channel data and a relatively small amount of real multi-channel data for model training. We explore effective training procedures, including a comparison of simulated and real multi-channel training data. To guide the recognition towards a target speaker and deal with overlapped speech, we also explore various combinations of bias information, such as direction of arrivals and speaker profiles. We propose an effective location bias integration method called deep concatenation for the beamformer network. In our evaluation on various meeting recordings, we show that the proposed framework achieves a substantial word error rate reduction.

Naoyuki Kanda, Zhong Meng, Liang Lu et al.

Recently, an end-to-end speaker-attributed automatic speech recognition (E2E SA-ASR) model was proposed as a joint model of speaker counting, speech recognition and speaker identification for monaural overlapped speech. In the previous study, the model parameters were trained based on the speaker-attributed maximum mutual information (SA-MMI) criterion, with which the joint posterior probability for multi-talker transcription and speaker identification are maximized over training data. Although SA-MMI training showed promising results for overlapped speech consisting of various numbers of speakers, the training criterion was not directly linked to the final evaluation metric, i.e., speaker-attributed word error rate (SA-WER). In this paper, we propose a speaker-attributed minimum Bayes risk (SA-MBR) training method where the parameters are trained to directly minimize the expected SA-WER over the training data. Experiments using the LibriSpeech corpus show that the proposed SA-MBR training reduces the SA-WER by 9.0 % relative compared with the SA-MMI-trained model.

Desh Raj, Pavel Denisov, Zhuo Chen et al.

Multi-speaker speech recognition of unsegmented recordings has diverse applications such as meeting transcription and automatic subtitle generation. With technical advances in systems dealing with speech separation, speaker diarization, and automatic speech recognition (ASR) in the last decade, it has become possible to build pipelines that achieve reasonable error rates on this task. In this paper, we propose an end-to-end modular system for the LibriCSS meeting data, which combines independently trained separation, diarization, and recognition components, in that order. We study the effect of different state-of-the-art methods at each stage of the pipeline, and report results using task-specific metrics like SDR and DER, as well as downstream WER. Experiments indicate that the problem of overlapping speech for diarization and ASR can be effectively mitigated with the presence of a well-trained separation module. Our best system achieves a speaker-attributed WER of 12.7%, which is close to that of a non-overlapping ASR.

Sanyuan Chen, Yu Wu, Zhuo Chen et al.

With its strong modeling capacity that comes from a multi-head and multi-layer structure, Transformer is a very powerful model for learning a sequential representation and has been successfully applied to speech separation recently. However, multi-channel speech separation sometimes does not necessarily need such a heavy structure for all time frames especially when the cross-talker challenge happens only occasionally. For example, in conversation scenarios, most regions contain only a single active speaker, where the separation task downgrades to a single speaker enhancement problem. It turns out that using a very deep network structure for dealing with signals with a low overlap ratio not only negatively affects the inference efficiency but also hurts the separation performance. To deal with this problem, we propose an early exit mechanism, which enables the Transformer model to handle different cases with adaptive depth. Experimental results indicate that not only does the early exit mechanism accelerate the inference, but it also improves the accuracy.

Xiong Xiao, Naoyuki Kanda, Zhuo Chen et al.

This paper describes the Microsoft speaker diarization system for monaural multi-talker recordings in the wild, evaluated at the diarization track of the VoxCeleb Speaker Recognition Challenge(VoxSRC) 2020. We will first explain our system design to address issues in handling real multi-talker recordings. We then present the details of the components, which include Res2Net-based speaker embedding extractor, conformer-based continuous speech separation with leakage filtering, and a modified DOVER (short for Diarization Output Voting Error Reduction) method for system fusion. We evaluate the systems with the data set provided by VoxSRCchallenge 2020, which contains real-life multi-talker audio collected from YouTube. Our best system achieves 3.71% and 6.23% of the diarization error rate (DER) on development set and evaluation set, respectively, being ranked the 1st at the diarization track of the challenge.

Jian Wu, Zhuo Chen, Jinyu Li et al.

Multi-speaker speech recognition has been one of the keychallenges in conversation transcription as it breaks the singleactive speaker assumption employed by most state-of-the-artspeech recognition systems. Speech separation is consideredas a remedy to this problem. Previously, we introduced a sys-tem, calledunmixing,fixed-beamformerandextraction(UFE),that was shown to be effective in addressing the speech over-lap problem in conversation transcription. With UFE, an inputmixed signal is processed by fixed beamformers, followed by aneural network post filtering. Although promising results wereobtained, the system contains multiple individually developedmodules, leading potentially sub-optimum performance. In thiswork, we introduce an end-to-end modeling version of UFE. Toenable gradient propagation all the way, an attentional selectionmodule is proposed, where an attentional weight is learnt foreach beamformer and spatial feature sampled over space. Ex-perimental results show that the proposed system achieves com-parable performance in an offline evaluation with the originalseparate processing-based pipeline, while producing remark-able improvements in an online evaluation.

Sanyuan Chen, Yu Wu, Zhuo Chen et al.

Continuous speech separation plays a vital role in complicated speech related tasks such as conversation transcription. The separation model extracts a single speaker signal from a mixed speech. In this paper, we use transformer and conformer in lieu of recurrent neural networks in the separation system, as we believe capturing global information with the self-attention based method is crucial for the speech separation. Evaluating on the LibriCSS dataset, the conformer separation model achieves state of the art results, with a relative 23.5% word error rate (WER) reduction from bi-directional LSTM (BLSTM) in the utterance-wise evaluation and a 15.4% WER reduction in the continuous evaluation.

Naoyuki Kanda, Xuankai Chang, Yashesh Gaur et al.

Recently, an end-to-end (E2E) speaker-attributed automatic speech recognition (SA-ASR) model was proposed as a joint model of speaker counting, speech recognition and speaker identification for monaural overlapped speech. It showed promising results for simulated speech mixtures consisting of various numbers of speakers. However, the model required prior knowledge of speaker profiles to perform speaker identification, which significantly limited the application of the model. In this paper, we extend the prior work by addressing the case where no speaker profile is available. Specifically, we perform speaker counting and clustering by using the internal speaker representations of the E2E SA-ASR model to diarize the utterances of the speakers whose profiles are missing from the speaker inventory. We also propose a simple modification to the reference labels of the E2E SA-ASR training which helps handle continuous multi-talker recordings well. We conduct a comprehensive investigation of the original E2E SA-ASR and the proposed method on the monaural LibriCSS dataset. Compared to the original E2E SA-ASR with relevant speaker profiles, the proposed method achieves a close performance without any prior speaker knowledge. We also show that the source-target attention in the E2E SA-ASR model provides information about the start and end times of the hypotheses.

Naoyuki Kanda, Yashesh Gaur, Xiaofei Wang et al.

We propose an end-to-end speaker-attributed automatic speech recognition model that unifies speaker counting, speech recognition, and speaker identification on monaural overlapped speech. Our model is built on serialized output training (SOT) with attention-based encoder-decoder, a recently proposed method for recognizing overlapped speech comprising an arbitrary number of speakers. We extend SOT by introducing a speaker inventory as an auxiliary input to produce speaker labels as well as multi-speaker transcriptions. All model parameters are optimized by speaker-attributed maximum mutual information criterion, which represents a joint probability for overlapped speech recognition and speaker identification. Experiments on LibriSpeech corpus show that our proposed method achieves significantly better speaker-attributed word error rate than the baseline that separately performs overlapped speech recognition and speaker identification.

Dongmei Wang, Zhuo Chen, Takuya Yoshioka

This paper proposes a neural network based speech separation method using spatially distributed microphones. Unlike with traditional microphone array settings, neither the number of microphones nor their spatial arrangement is known in advance, which hinders the use of conventional multi-channel speech separation neural networks based on fixed size input. To overcome this, a novel network architecture is proposed that interleaves inter-channel processing layers and temporal processing layers. The inter-channel processing layers apply a self-attention mechanism along the channel dimension to exploit the information obtained with a varying number of microphones. The temporal processing layers are based on a bidirectional long short term memory (BLSTM) model and applied to each channel independently. The proposed network leverages information across time and space by stacking these two kinds of layers alternately. Our network estimates time-frequency (TF) masks for each speaker, which are then used to generate enhanced speech signals either with TF masking or beamforming. Speech recognition experimental results show that the proposed method significantly outperforms baseline multi-channel speech separation systems.