Yuanchao Li

Yuanchao Li

Final-Year PhD Student at University of Edinburgh

I am a PhD student at the Centre for Speech Technology Research (CSTR), affiliated with the Institute for Language, Cognition and Computation (ILCC), University of Edinburgh. I am fortunate to be advised by Dr. Catherine Lai and Prof. Peter Bell, and fully funded by the School of Informatics. I was an Enrichment student at and a research intern at Audio and Acoustics Research Group .

My research aims to advance spoken language technologies in real-world applications by bridging different but relevant domains such as speech & language, emotion & health, humans & machines, etc. In particular, my work focuses on problems that hinder the broader use of spoken language technologies in the wild.

Before PhD study, I used to research on affective computing and human-robot interaction at Honda Innovation Lab, Hiroshi Ishiguro Lab ATR, and Speech and Audio Processing Lab. I was fortunate to be advised by Prof. Tatsuya Kawahara, Prof. Nigel Ward, and Dr. Carlos Ishi.

🔥 News

  • 09.2024, Our SpandLDeteriorate workshop has been accepted to ACM MM Asia 2024. Looking forward to your papers!
  • 08.2024, Three papers accepted to SLT 2024!
  • 04.2024, Our GenSEC challenge has been accepted to SLT 2024. Looking forward to your papers!
  • 03.2024, We won the 1st place (and $1,000) out of 31 teams in Task 1 - Categorical Emotion Recognition at Odyssey 2024 Emotion Recognition Challenge.  🎉
  • 02.2024, One paper accepted to ICASSP 2024 SASB workshop: Layer-Wise Analysis of Self-Supervised Acoustic Word Embeddings: A Study on Speech Emotion Recognition
  • 01.2024, Our special session Responsible Speech Foundation Models has been accepted to Interspeech 2024. Looking forward to your papers!
  • 11.2023, Microsoft FADTK, a Frechet audio distance toolkit has been released, to which I contributed its speech models.
  • 09.2023, Received the IEEE SPS Scholarship from the IEEE Signal Processing Society.  🎉
  • 09.2023, Received the Outstanding Paper Award at the SAI workshop, ACII 2023, MIT Media Lab.  🎉
  • 06.2023, Our grant proposal (as Co-Investigator) Development of A Human-Centric Elderly Driving Education System has been accepted by the Inter-University Research Institute Corporation, Research Organization of Information and Systems.
  • 03.2023, Received the Gary Marsden Travel Award from ACM SIGCHI.  🎉

🎖 Honors and Awards

  • 2024, 3rd Place Award, 3-Min Thesis Competition, Students of Society for Affective Science
  • 2024, 1st Place Award, Odyssey 2024 Emotion Recognition Challenge
  • 2023, IEEE SPS Scholarship, IEEE Signal Processing Society
  • 2023, Outstanding Paper Award, SAI workshop, ACII 2023
  • 2023, Gary Marsden Travel Award, ACM SIGCHI
  • 2022, Enrichment Student Award, Alan Turing Institute
  • 2021, Fully-Funded PhD Scholarship, University of Edinburgh
  • 2016, Seiwa International Scholarship, Kyoto University
  • 2013, 3rd Class Academic Excellence Scholarship, NUPT

💻 Research Activities

- Organizing Committee -

- Program Committee -

- Journal Review -

  • IEEE Transactions on Affective Computing (2)
  • Computer Speech and Language (1)
  • Speech Communication (1)
  • Journal of Rehabilitation and Assistive Technologies Engineering (1)
  • Pattern Analysis and Applications (1)

- Conference Review -

  • ICASSP’23-25, Interspeech’23-24, ASRU’23, SLT’22-24, UK Speech’22
  • Interspeech Young Female Researchers in Speech Workshop’24 & 22
  • CHI’23 Late-Breaking Work
  • IJCLR’23 CogAI Workshop
  • ICMI’21 Late-Breaking Report & Doctoral Consortium
  • HRI’20 Late-Breaking Report

- Organizations & Communities -

  • ACM, AAAC, ISCA, IEEE, IEEE Signal Processing Society, SIGCHI, UK Speech, UK-SIGMM, Alan Turing Institute

🎙 Talks

  • 03.2024, “Opportunities and Challenges of Speech Emotion Recognition in the Era of Foundation Models”. Center for Interdisciplinary Research in Language Sciences, University of Science and Technology of China (host: Prof. Jiahong Yuan)
  • 11.2020, “Affective Human-Robot Interaction”. Cognitive Developmental Robotics Lab, University of Tokyo (host: Prof. Yukie Nagai)

💰 Grants

  • 06.2023, “Development of A Human-Centric Elderly Driving Education System”, Co-Investigator, ¥800,000. Strategic Research Project “2023-SRP-06”, Research Organization of Information and Systems

👔 Experiences

- Teaching -

  • TA (Coursework marker), Automatic Speech Recognition, University of Edinburgh, 2023 & 2024
  • TA (Tutor, demonstrator, and project marker), System Design Project, University of Edinburgh, 2023
  • TA (Coursework and exam marker), Machine Learning, University of Edinburgh, 2022 & 2024

- Supervision -

  • Cross-lingual Speech Emotion Recognition and Speech Emotion Diarisation: A Comparative Study between Humans and Machines

    Zhichen Han, MSc dissertation 2024/25 (Distinction), University of Edinburgh

  • Revisiting the Shared Suprasegmental Acoustics Between Emotional Speech and Song through Self-Supervised Learning Models

    Yujia Sun, MSc dissertation 2024/25 (Distinction), University of Edinburgh

  • Layerwise Analysis of HuBERT Acoustic Word Embeddings in the Context of Speech Emotion Recognition

    Alexandra Saliba, MSc dissertation 2023/24 (Distinction), University of Edinburgh

  • Hierarchical Cross-Modal Transformer and A Study of Cross-Modal Attention for Affective Computing

    Yaoting Wang, MSc dissertation 2022/23 (Distinction), University of Edinburgh

  • A Cross-Domain Study of Crossmodal Attention Based Multimodal Emotion Recognition

    Junling Liu, MSc dissertation 2021/22, University of Edinburgh

- Working -

  • Research Intern, Microsoft Research Audio and Acoustics Group
  • Researcher, Honda R&D Innovation Lab
  • R&D Engineer, NTT Data R&D headquarters
  • Student Researcher, ERATO ISHIGURO Symbiotic HRI Project, ATR

📖 Education

  • Ph.D. Candidate, Informatics, University of Edinburgh
  • M.Sc., Intelligence Science and Technology, Kyoto University
  • B.Eng., Electronic and Information Engineering, Nanjing University of Posts and Telecommunications

📝 Publications

- Papers -

- Patents -

- Technical Reports -

  • Crossmodal ASR Error Correction with Discrete Speech Units

    Yuanchao Li, Pinzhen Chen, Peter Bell, Catherine Lai. UK Speech. 2024

  • Multimodal Dyadic Impression Recognition via Listener Adaptive Cross-Domain Fusion

    Yuanchao Li, Peter Bell, Catherine Lai. UK Speech. 2023

  • Exploration of A Self-Supervised Speech Model: A Study on Emotional Corpora

    Yuanchao Li, Yumnah Mohamied, Peter Bell, Catherine Lai. UK Speech. 2022

  • An Extensible End-to-End Multitask Learning Model for Recognizing Driver States

    Yuanchao Li. The 12th Honda R&D Technical Forum. 2019

  • Processing User States in Spoken Dialog Systems for Human-Robot Interaction

    Yuanchao Li. International Design Symposium in Kyoto. 2017

  • Assessment Selection for Human-Robot Interaction based on Emotion Recognition Combining Prosody and Text Information

    Yuanchao Li, Tatsuya Kawahara. The 44th Kansai Joint Speech Seminar. 2016

- Book Translation -

- Media Articles -