About me

I am a PhD student from the Human Language Technology Lab (HLT) of the Department of Electrical and Computer Engineering in National University of Singapore (NUS). I am under the supervision of Prof. Haizhou Li (National University of Singapore & The Chinese University of HongKong (Shenzhen)). My latest CV can be abtained here. Before joining NUS, I got my bachelor's degree in Electronic Information Engineering from University of Electronic Science and Technology of China (UESTC) in 2018.

Feel free to contact me via email.

Research interests

My current research interests mainly focus on emotion analysis and synthesis in speech, which includes:

  • Voice Conversion (VC): Emotional Voice Conversion.
  • Text-to-Speech (TTS): Emotional Text-to-Speech.

News

Experiences

  • Mar 2023 - June 2023, University of Bremen, Visiting Scholar, Bremen, Germany. (Supervisor: Prof. Tanja Schultz)
  • Sept 2022 - Jan 2023, The University of Texas at Dallas, Visiting Scholar, Texas, U.S.A. (Supervisor: Prof. John Hansen, Assistant Prof. Berrak Sisman)
  • Aug 2019 - Present, National University of Singapore, PhD student, Singapore. (Main Supervisor: Prof. Haizhou Li; Co-Supervisor: Assistant Prof. Berrak Sisman)
  • Aug 2018 - May 2019, National University of Singapore, Master student, Singapore. (Main Supervisor: Prof. Haizhou Li; Co-Supervisor: Dr. Emre Yilmaz)
  • Sept 2017 - May 2018, National University of Singapore Research Institution (Suzhou), Research student, Suzhou, China.
  • Sept 2014 - June 2018, University of Electronic Science and Technology of China, Undergraduate student, Chengdu, China.

Selected Publications [Google Scholar]

  • Speech Synthesis with Mixed Emotions [Pretprint]
          Kun Zhou, Berrak Sisman, Rajib Rana, Bjorn Schuller, Haizhou Li. (IEEE Transactions on Affective Computing)
  • Emotion Intensity and its Control for Emotional Voice Conversion [Pretprint][Postprint]
          Kun Zhou, Berrak Sisman, Rajib Rana, Bjorn Schuller, Haizhou Li. (IEEE Transactions on Affective Computing)
  • Emotional Voice Conversion: Theory, Databases and ESD [Postprint]
          Kun Zhou, Berrak Sisman, Rui Liu, Haizhou Li. (Speech Communication)
  • Limited Data Emotional Voice Conversion Leveraging Text-to-Speech: Two-Stage Sequence-to-Sequence Training [paper][Speech Samples][poster]
          Kun Zhou, Berrak Sisman, Haizhou Li. (22th Annual Conference of the International Speech Communication Association (Interspeech) 2021, Brno, Czech)
  • Seen and Unseen Emotional Style Transfer for Voice Conversion with a New Emotional Speech Dataset [paper][slides][poster]
          Kun Zhou, Berrak Sisman, Rui Liu, Haizhou Li. (IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2021, Toronto, Canada)
  • VAW-GAN for Disentanglement and Recomposition of Emotional Elements in Speech [paper][slides]
          Kun Zhou, Berrak Sisman, Haizhou Li. (IEEE Spoken Language Workshop (SLT) 2021, Shenzhen, China)
  • Converting Anyone's Emotion: Towards Speaker-Independent Emotional Voice Conversion [paper][code]
          Kun Zhou, Berrak Sisman, Mingyang Zhang, Haizhou Li. (21th Annual Conference of the International Speech Communication Association (Interspeech) 2020, Shanghai, China)
  • Transforming Spectrum and Prosody for Emotional Voice Conversion with Non-Parallel Training Data [paper][code]
          Kun Zhou, Berrak Sisman, Haizhou Li. (Speaker Odyssey 2020, Tokyo, Japan)

Honors & Awards

  • Aug 2022, PRMIA Best Student Paper Award awarded by Pattern Recognition and Machine Intelligence Association (PRMIA).
  • May 2017, Outstanding Award for Undergraduate Researcher given by University of Electrial Science and Technology of China.
  • Oct 2016, Remin Scholorship awarded by Ministry of Education of the People's Republic of China.
  • Sept 2015, Special Reward of Social Activities awarded by People's Government of Sichuan Province.
  • Oct 2015, Remin Scholorship awarded by Ministry of Education of the People's Republic of China.
  • Professional Services

      Local Arrangment Co-chair
  • May 2022, Local Arrangment Co-chair of IEEE ICASSP 2022 in Singapore.
  • July 2021, Local Arrangment Co-chair of O-COCOSDA 2021 in Singapore.
  • July 2021, Local Arrangment Co-chair of SIGDIAL 2021 in Singapore.
  • Nov 2021, Local Arrangment Co-chair of IWSDS 2021 in Singapore.
  • Dec 2019, Local Arrangment Co-chair of IEEE ASRU 2019 in Singapore.
    • Reviewer
    ICASSP, INTERSPEECH, SLT, Transactions on Audio, Speech and Language Processing (TASLP), Speech Communication, IEEE Signal Processing Letters, Computer Speech and Language

    Invited Talk

  • June 2023, "Emotion Modelling for Speech Generation" at Cognitive Systems Lab, University of Bremen, Germany (Host: Prof. Tanja Schultz)
  • May 2023, "Emotion Modelling for Speech Generation" at Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Germany (Host: Prof. Bjorn Schuller)
  • Dec 2022, "Emotion Modelling for Speech Generation" at Audio Information Research Lab, University of Rochester, USA (Host: Prof. Zhiyao Duan)
  • Aug 2022, "Emotional Speech Conversion and Synthesis" at Huawei, Shenzhen (Host: Prof. Haizhou Li)
  • Languages

      Chinese, English, German

    Address

      Address: 4 Engineering Drive 3 Block E4, #06-20 Singapore, 117583