Invited Talk at Muroran Institute of Technology (Co-organized)

#AI
Share

An invited talk by Associate Professor Xin Wang, National Institute of Informatics, Japan, will be held on June 10, 2026, in Room R205, Education & Research Building No. 8, Muroran Institute of Technology, 27-1 Mizumoto-cho, Muroran, Hokkaido, 0508585 Japan.  Professor Cheng‐Te Li will share some interesting ideas about Progress of Speech Generative AI and Countermeasures against Speech Deepfake.

CO-ORGANIZED BY:

IEEE Muroran Institute of Technology Student Branch (SB)

IEEE Systems, Man, and Cybernetics Society Muroran Institute of Technology Student Branch Chapter

IEEE Computer Society Muroran Institute of Technology Student Branch Chapter

IEEE Sapporo Section Young Professionals (YP)

The Center for Computer Science (CCS), Muroran Institute of Technology


  Date and Time

  Location

  Hosts

  Registration


  • Add_To_Calendar_icon Add Event to Calendar
  • 27-1 Mizumoto-cho, Muroran, Hokkaido
  • Muroran, Hokkaido
  • Japan 0508585
  • Building: R205
  • Contact Event Hosts
  • Starts 10 June 2026 01:10 AM UTC
  • Ends 10 June 2026 01:25 AM UTC
  • No Admission Charge

  Speakers

Associate Professor Xin Wang of National Institute of Informatics, Japan

Topic:

Progress of Speech Generative AI and Countermeasures against Speech Deepfake

Generating natural-sounding speech using computational algorithms has been the holy grail of speech synthesis for the past decades. This task has largely been solved by recent deep learning–based speech synthesis algorithms. It has also become easier for non-expert users to generate speech that sounds like another person, i.e., voice cloning. However, the misuse of voice cloning in the form of speech deepfakes is increasing. This tutorial-like talk briefly summarizes the progress of speech synthesis, explains the issues surrounding speech deepfakes, and introduces countermeasures such as passive deepfake detection, watermarking, and voice anonymization.

Biography:

Xin Wang (https ://researchmap.jp/wangxin) is a Project Associate Professor and a JST PRESTO researcher at the National Institute of Informatics, Japan. He received his PhD from SOKENDAI, Japan. Since then, he has been conducting research at the National Institute of Informatics, Japan. He is one of the organizers of the last three ASVspoof Challenges, the largest international competition on speech deepfake detection. He is also a member of the organizing team for the last three VoicePrivacy Challenges, an international joint effort on speech privacy. His research focuses on speech audio generation, text-to-speech synthesis, anti-spoofing, and other speech security and privacy related tasks.

Address:Japan