1.9k citations · 3.6k across the 72 of their papers we have counts for
19 papers · 1 filter
Separating Long-Form Speech with Group-Wise Permutation Invariant Training
Wangyou Zhang, Zhuo Chen, Naoyuki Kanda +8
Multi-talker conversational speech processing has drawn many interests for various applications such as meeting transcription. Speech separation is often required to handle overlap…
Continuous Speech Separation with Recurrent Selective Attention Network
Yixuan Zhang, Zhuo Chen, Jian Wu +4
While permutation invariant training (PIT) based continuous speech separation (CSS) significantly improves the conversation transcription accuracy, it often suffers from speech lea…
VarArray: Array-Geometry-Agnostic Continuous Speech Separation
Takuya Yoshioka, Xiaofei Wang, Dongmei Wang +4
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 propose…
One model to enhance them all: array geometry agnostic multi-channel personalized speech enhancement
Hassan Taherian, Sefik Emre Eskimez, Takuya Yoshioka +3
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…
Personalized Speech Enhancement: New Models and Comprehensive Evaluation
Sefik Emre Eskimez, Takuya Yoshioka, Huaming Wang +3
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…
All-neural beamformer for continuous speech separation
Zhuohuang Zhang, Takuya Yoshioka, Naoyuki Kanda +4
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 unkn…
UniSpeech-SAT: Universal Speech Representation Learning with Speaker Aware Pre-Training
Sanyuan Chen, Yu Wu, Chengyi Wang +8
Self-supervised learning (SSL) is a long-standing goal for speech processing, since it utilizes large-scale unlabeled data and avoids extensive human labeling. Recent years witness…
WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing
Sanyuan Chen, Chengyi Wang, Zhengyang Chen +15
Self-supervised learning (SSL) achieves great success in speech recognition, while limited exploration has been attempted for other speech processing tasks. As speech signal contai…
Transcribe-to-Diarize: Neural Speaker Diarization for Unlimited Number of Speakers using End-to-End Speaker-Attributed ASR
Naoyuki Kanda, Xiong Xiao, Yashesh Gaur +4
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…
Continuous Streaming Multi-Talker ASR with Dual-path Transducers
Desh Raj, Liang Lu, Zhuo Chen +2
Streaming recognition of multi-talker conversations has so far been evaluated only for 2-speaker single-turn sessions. In this paper, we investigate it for multi-turn meetings cont…
Target-speaker Voice Activity Detection with Improved I-Vector Estimation for Unknown Number of Speaker
Maokui He, Desh Raj, Zili Huang +3
Target-speaker voice activity detection (TS-VAD) has recently shown promising results for speaker diarization on highly overlapped speech. However, the original model requires a fi…
Investigation of Practical Aspects of Single Channel Speech Separation for ASR
Jian Wu, Zhuo Chen, Sanyuan Chen +5
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 flex…
A Comparative Study of Modular and Joint Approaches for Speaker-Attributed ASR on Monaural Long-Form Audio
Naoyuki Kanda, Xiong Xiao, Jian Wu +6
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…
Human Listening and Live Captioning: Multi-Task Training for Speech Enhancement
Sefik Emre Eskimez, Xiaofei Wang, Min Tang +5
With the surge of online meetings, it has become more critical than ever to provide high-quality speech audio and live captioning under various noise conditions. However, most mona…
Large-Scale Pre-Training of End-to-End Multi-Talker ASR for Meeting Transcription with Single Distant Microphone
Naoyuki Kanda, Guoli Ye, Yu Wu +5
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).…
End-to-End Speaker-Attributed ASR with Transformer
Naoyuki Kanda, Guoli Ye, Yashesh Gaur +4
This paper presents our recent effort on end-to-end speaker-attributed automatic speech recognition, which jointly performs speaker counting, speech recognition and speaker identif…
AISHELL-4: An Open Source Dataset for Speech Enhancement, Separation, Recognition and Speaker Diarization in Conference Scenario
Yihui Fu, Luyao Cheng, Shubo Lv +10
In this paper, we present AISHELL-4, a sizable real-recorded Mandarin speech dataset collected by 8-channel circular microphone array for speech processing in conference scenario.…
Continuous Speech Separation with Ad Hoc Microphone Arrays
Dongmei Wang, Takuya Yoshioka, Zhuo Chen +3
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 asynchrono…
Dual-Path Modeling for Long Recording Speech Separation in Meetings
Chenda Li, Zhuo Chen, Yi Luo +6
The continuous speech separation (CSS) is a task to separate the speech sources from a long, partially overlapped recording, which involves a varying number of speakers. A straight…