Personal Website of Yiwei Guo

🙋‍♂️Hi! My name is Yiwei Guo.

I am currently a Ph.D. candidate in Shanghai Jiao Tong University (SJTU) and a member in Cross Media (X-) Language Intelligence Lab (X-LANCE) of the Department of Computer Science and Engineering, supervised by Prof. Kai Yu and working closely with Prof. Xie Chen.

I obtained my B.Eng. degree from the Artificial Intelligence (Excellent Talent Pilot Class) major in SJTU on June, 2023 before I started the journey of pursuing the doctorate. I am very lucky that as one of the first graduates from this major, I had abundant chances to devote myself into academic research and looking for the field that I ardently love during the undergraduate period. And this very field is speech synthesis, including text-to-speech, voice conversion and end-to-end speech dialogue systems. I am also interested in diffusion (together with flow matching) generative models and discrete generative models, which appear to the two foundational pillars of speech synthesis these days.

⚠️This website is still under construction.

📣 News

  • [2024.08] I gave a tutorial at NCMMSC 2024 in Urumqi, China. Check it out and thanks to all the contributors!
  • [2024.08] 1 paper is accepted at SLT 2024.
  • [2024.06] 2 papers are accepted at Interspeech 2024.
  • [2023.12] UniCATS is accepted at AAAI 2024. It is open-sourced. See you in Vancouver!
  • [2023.12] 4 papers are accepted at ICASSP 2024. VoiceFlow is open-sourced. See you in Seoul!
  • [2023.08] 1 article is published at IEEE/ACM TASLP.
  • [2023.05] 1 paper is accepted at Interspeech 2023. See you in Dublin!
  • [2023.02] 3 papers are accepted at ICASSP 2023. See you in Rhodes Island!
  • [2023.02] We won the first place on two tracks in LIMMITS'23 challenge. Check it out!
  • [2022.06] VQTTS is accepted at Interspeech 2022.
  • [2022.01] My first paper is accepted at ICASSP 2022!

Academic Service

Conference Reviewer

  • ACL Rolling Review (ACL ARR) 2024.
  • IEEE Spoken Language Technology Workshop (SLT) 2024.
  • National Conference on Man-Machine Speech Communication (NCMMSC) 2023, 2024.

Journal Reviewer

  • IEEE/ACM Transactions on Audio, Speech and Language Processing (TASLP).