Takuya Yoshioka

Continuous Speech Separation with Ad Hoc Microphone Arrays

Speech separation has been shown effective for multi-talker speech recog...
03/03/2021 ∙ by Dongmei Wang, et al. ∙ 0 ∙ share

read it
Hypothesis Stitcher for End-to-End Speaker-attributed ASR on Long-form Multi-talker Recordings

An end-to-end (E2E) speaker-attributed automatic speech recognition (SA-...
01/06/2021 ∙ by Xuankai Chang, et al. ∙ 0 ∙ share

read it
Exploring End-to-End Multi-channel ASR with Bias Information for Meeting Transcription

Joint optimization of multi-channel front-end and automatic speech recog...
11/05/2020 ∙ by Xiaofei Wang, et al. ∙ 0 ∙ share

read it
Minimum Bayes Risk Training for End-to-End Speaker-Attributed ASR

Recently, an end-to-end speaker-attributed automatic speech recognition ...
11/03/2020 ∙ by Naoyuki Kanda, et al. ∙ 0 ∙ share

read it
Integration of speech separation, diarization, and recognition for multi-speaker meetings: System description, comparison, and analysis

Multi-speaker speech recognition of unsegmented recordings has diverse a...
11/03/2020 ∙ by Desh Raj, et al. ∙ 0 ∙ share

read it
Don't shoot butterfly with rifles: Multi-channel Continuous Speech Separation with Early Exit Transformer

With its strong modeling capacity that comes from a multi-head and multi...
10/23/2020 ∙ by Sanyuan Chen, et al. ∙ 0 ∙ share

read it
Microsoft Speaker Diarization System for the VoxCeleb Speaker Recognition Challenge 2020

This paper describes the Microsoft speaker diarization system for monaur...
10/22/2020 ∙ by Xiong Xiao, et al. ∙ 0 ∙ share

read it
An End-to-end Architecture of Online Multi-channel Speech Separation

Multi-speaker speech recognition has been one of the keychallenges in co...
09/07/2020 ∙ by Jian Wu, et al. ∙ 0 ∙ share

read it
Investigation of End-To-End Speaker-Attributed ASR for Continuous Multi-Talker Recordings

Recently, an end-to-end (E2E) speaker-attributed automatic speech recogn...
08/11/2020 ∙ by Naoyuki Kanda, et al. ∙ 0 ∙ share

read it
Joint Speaker Counting, Speech Recognition, and Speaker Identification for Overlapped Speech of Any Number of Speakers

We propose an end-to-end speaker-attributed automatic speech recognition...
06/19/2020 ∙ by Naoyuki Kanda, et al. ∙ 0 ∙ share

read it
Neural Speech Separation Using Spatially Distributed Microphones

This paper proposes a neural network based speech separation method usin...
04/28/2020 ∙ by Dongmei Wang, et al. ∙ 0 ∙ share

read it
Serialized Output Training for End-to-End Overlapped Speech Recognition

This paper proposes serialized output training (SOT), a novel framework ...
03/28/2020 ∙ by Naoyuki Kanda, et al. ∙ 0 ∙ share

read it
Continuous speech separation: dataset and analysis

This paper describes a dataset and protocols for evaluating continuous s...
01/30/2020 ∙ by Zhuo Chen, et al. ∙ 0 ∙ share

read it
Advances in Online Audio-Visual Meeting Transcription

This paper describes a system that generates speaker-annotated transcrip...
12/10/2019 ∙ by Takuya Yoshioka, et al. ∙ 15 ∙ share

read it
End-to-end Microphone Permutation and Number Invariant Multi-channel Speech Separation

An important problem in ad-hoc microphone speech separation is how to gu...
10/30/2019 ∙ by Yi Luo, et al. ∙ 0 ∙ share

read it
Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separation

Recent studies in deep learning-based speech separation have proven the ...
10/14/2019 ∙ by Yi Luo, et al. ∙ 0 ∙ share

read it
DOVER: A Method for Combining Diarization Outputs

Speech recognition and other natural language tasks have long benefited ...
09/17/2019 ∙ by Andreas Stolcke, et al. ∙ 0 ∙ share

read it
Meeting Transcription Using Virtual Microphone Arrays

We describe a system that generates speaker-annotated transcripts of mee...
05/03/2019 ∙ by Takuya Yoshioka, et al. ∙ 0 ∙ share

read it
Low-Latency Speaker-Independent Continuous Speech Separation

Speaker independent continuous speech separation (SI-CSS) is a task of c...
04/13/2019 ∙ by Takuya Yoshioka, et al. ∙ 0 ∙ share

read it
Recognizing Overlapped Speech in Meetings: A Multichannel Separation Approach Using Neural Networks

The goal of this work is to develop a meeting transcription system that ...
10/08/2018 ∙ by Takuya Yoshioka, et al. ∙ 0 ∙ share

read it
Cracking the cocktail party problem by multi-beam deep attractor network

While recent progresses in neural network approaches to single-channel s...
03/29/2018 ∙ by Zhuo Chen, et al. ∙ 0 ∙ share

read it

Takuya Yoshioka

Featured Co-authors

Jun Zhang

Shinji Watanabe

Lei Xie

Zhuo Chen

Jinyu Li

Yu Wu

Yifan Gong

Jian Wu

Jun Du

Xiaofei Wang

Yi Luo

Continuous Speech Separation with Ad Hoc Microphone Arrays

Hypothesis Stitcher for End-to-End Speaker-attributed ASR on Long-form Multi-talker Recordings

Exploring End-to-End Multi-channel ASR with Bias Information for Meeting Transcription

Minimum Bayes Risk Training for End-to-End Speaker-Attributed ASR

Integration of speech separation, diarization, and recognition for multi-speaker meetings: System description, comparison, and analysis

Don't shoot butterfly with rifles: Multi-channel Continuous Speech Separation with Early Exit Transformer

Microsoft Speaker Diarization System for the VoxCeleb Speaker Recognition Challenge 2020

An End-to-end Architecture of Online Multi-channel Speech Separation

Investigation of End-To-End Speaker-Attributed ASR for Continuous Multi-Talker Recordings

Joint Speaker Counting, Speech Recognition, and Speaker Identification for Overlapped Speech of Any Number of Speakers

Neural Speech Separation Using Spatially Distributed Microphones

Serialized Output Training for End-to-End Overlapped Speech Recognition

Continuous speech separation: dataset and analysis

Advances in Online Audio-Visual Meeting Transcription

End-to-end Microphone Permutation and Number Invariant Multi-channel Speech Separation

Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separation

DOVER: A Method for Combining Diarization Outputs

Meeting Transcription Using Virtual Microphone Arrays

Low-Latency Speaker-Independent Continuous Speech Separation

Recognizing Overlapped Speech in Meetings: A Multichannel Separation Approach Using Neural Networks

Cracking the cocktail party problem by multi-beam deep attractor network