Shuai Wang

Shuai Wang

Research Scientist

SRIBD, CUHK(SZ)

Biography

I obtained my Ph.D. degree in Shanghai Jiao Tong University in 2020.09, under the supervision of Kai Yu and Yanmin Qian. During the Ph.D. my research interests include deep learning based approaches for speaker recognition, speaker diarization and voice activity detection. After my graduation, I joined Tencent Games as a senior researcher, where I (informally) led a speech group and extended the research interest to speech synthesis, voice conversion, music generation and audio retrivial. Currently, I am with the SpeechLab in Shenzhen Research Institute of Big Data, Chinese University of Hong Kong (Shenzhen) led by Haizhou Li.

I am the creator of Wespeaker, a research and product oriented speaker representation learning toolkit. You can check my tutorial to see what you can do using speaker modeling and how to easily apply wespeaker to your tasks. Welcome to use and contribute!

Services: I serve as a regular reviewer for speech/deep learning related conferences/journals: Interspeech, ICASSP, ICME, SPL, TASLP, Neural Networks and Pattern Recognition. I will serve as the publication chair for SLT 2024.

Openings: We are actively seeking self-motivated students to join our team as research assistants, visiting students and potential Ph.D. students. Multiple positions are immediately available in Shenzhen, with competitive salary and benefits. If you are interested, please drop me an email with your CV.

Interests

  • Voice conversion
  • Speech synthesis
  • Speaker recognition
  • Speaker diarization
  • Target speech extraction

Education

  • PhD in Computer Science and Technology, 2020

    Shanghai Jiao Tong University

  • BSc in Software Engineering, 2014

    Northwestern Polytechnical University

Experience

 
 
 
 
 

Research Scientist

Shenzhen Research Institute of Big Data, Chinese University of Hong Kong (Shenzhen)

May 2023 – Present Shenzhen, China
 
 
 
 
 

Senior Research Scientist

Tencent

Oct 2020 – Apr 2023 Shenzhen, China
Led the speech team, working on Speech Synthesis, Voice Conversion, Spoken Emotion Recognition, Audio Generation/Retrivial, Symbolic Music Generation, etc. Serving Products of Tencent Games such as League of legends, Game for Peace, DouDiZhu, etc.
 
 
 
 
 

Research assistant

Speech@FIT in Brno University of Technology

Feb 2019 – Oct 2019 Brno, Czech Republic

Work on several research papers and contribute to

  • The VoxSRC 2019 speaker recognition challenge (1st place in 2 tracks)
  • The DIHARD 2019 speaker diarization challenge (1st place in 4 tracks)
  • The NIST SRE 2019 speaker recognition challenge

Recent Talks

Speaker Representation Learning: Theories, Applications and Practice

I was invited to give a tutorial on speaker representation learning at the National Conference on Man-Machine Speech Communication (NCMMSC2023).
Dec 8, 2023 9:00 AM
Shuai Wang, Bing Han
PDF Code NCMMSC Tutorial Link
Speaker Representation Learning: Theories, Applications and Practice

Featured Publications

Chenpeng Du, Yiwei Guo, Feiyu Shen, Zhijun Liu, Zheng Liang, Xie Chen, Shuai Wang, Hui Zhang, Kai Yu
February 2024 AAAI 2024 (Accepted) tts
UniCATS: A Unified Context-Aware Text-to-Speech Framework with Contextual VQ-Diffusion and Vocoding

UniCATS: A Unified Context-Aware Text-to-Speech Framework with Contextual VQ-Diffusion and Vocoding

AAAI 2024
PDF Code Project
Hongji Wang, Chengdong Liang, Shuai Wang, Zhengyang Chen, Binbin Zhang, Xu Xiang, Yanlei Deng, Yanmin Qian
May 2023 ICASSP 2023 SEL

Wespeaker: A Research and Production oriented Speaker Embedding Learning Toolkit

PDF Code
Yufei Liu, Chengzhu Yu, Shuai Wang, Zhenchuan Yang, Chao Yang, Weibin Zhang
September 2021 Interspeech 2021 vc

Non-Parallel Any-to-Many Voice Conversion by Replacing Speaker Statistics

We introduce the speaker modeling method (statistics based) into the voice conversion
PDF
Federico Landini, Shuai Wang, Mireia Diez, Lukáš Burget, Pavel Matějka, Kateřina Žmolíková, Ladislav Mošner, Anna Silnova, Oldřich Plchot, Ondřej Novotný, Hossein Zeinali, Johan Rohdin
June 2020 ICASSP 2020 diarization

But System for the Second Dihard Speech Diarization Challenge

This paper describes the winning systems developed by the BUT team for the four tracks of the Second DIHARD Speech Diarization Challenge, with source code available
PDF Code DOI
Yexin Yang*, Shuai Wang*, Xun Gong, Yanmin Qian, Kai Yu
June 2020 ICASSP 2020 SEL

Text Adaptation for Speaker Verification with Speaker-Text Factorized Embeddings

We proposed the text-adptation speaker verification task and an intital solution called Speaker-text factorization network, which could deal with different text-mismatch conditions
PDF DOI
Hossein Zeinali, Shuai Wang, Anna Silnova, Pavel Matějka, Oldřich Plchot
June 2019 SEL

BUT system description to voxceleb speaker recognition challenge 2019

This paper describes the winning systems developed by the BUT team for the two tracks of the First VoxSRC Speaker Recognition Challenge, we proposed r-vector in this paper. Update: I lanuched an open-source project wespeaker, where the implementation can be found
Preprint Code
Shuai Wang, Johan Rohdin, Lukáš Burget, Oldřich Plchot, Yanmin Qian, Kai Yu
June 2019 Interspeech 2019 SEL

On the Usage of Phonetic Information for Text-independent Speaker Embedding Extraction

We proposed the segment-level representation for phonetic information and the corresponding segment-level multi-task/adversarial training framework, we revisited the usage the phonetic information for the text-independent embedding learning and designed experiments to verify the assumption: For TI-SV, it could be benificial to remove the phonetic variation in the final speaker embeddings
PDF DOI
Shuai Wang, Yanmin Qian and Kai Yu
June 2017 InterSpeech 2017 SEL

What Does the Speaker Embedding Encode?

The first attempt to systematically analyze the information encoded in speaker embeddings (prior to x-vector), detailed analysis on x-vectors could be refered to the paper Probing the Information Encoded in X-vectors from JHU
PDF DOI

Recent Publications

Quickly discover relevant content by filtering publications.

Audio-Visual Active Speaker Extraction for Sparsely Overlapped Multi-talker Speech

Junjie Li, Ruijie Tao, Zexu Pan, Meng Ge, Shuai Wang, Haizhou Li

AutoPrep: An Automatic Preprocessing Framework for In-the-Wild Speech Data

Jianwei Yu, Hangting Chen, Yanyao Bian, Xiang Li, Yi Luo, Jinchuan Tian, Mengyang Liu, Jiayi Jiang, Shuai Wang

DualVC 2: Dynamic Masked Convolution for Unified Streaming and Non-Streaming Voice Conversion

Ziqian Ning, Yuepeng Jiang, Pengcheng Zhu, Shuai Wang, Jixun Yao, Lei Xie, Mengxiao Bi

Leveraging In-the-Wild Data for Effective Self-Supervised Pretraining in Speaker Recognition

Shuai Wang, Qibing Bai, Qi Liu, Jianwei Yu, Zhengyang Chen, Bing Han, Yanmin Qian, Haizhou Li
PDF Code

UniCATS: A Unified Context-Aware Text-to-Speech Framework with Contextual VQ-Diffusion and Vocoding

AAAI 2024
Chenpeng Du, Yiwei Guo, Feiyu Shen, Zhijun Liu, Zheng Liang, Xie Chen, Shuai Wang, Hui Zhang, Kai Yu
PDF Code Project
UniCATS: A Unified Context-Aware Text-to-Speech Framework with Contextual VQ-Diffusion and Vocoding
See all publications

Contact