Reducing Speaker and Temporal Redundancy in Discrete Speech Tokenization

Add to your list(s) Download to your calendar using vCal

• Yiwei Guo, Shanghai Jiaotong University
• Monday 20 October 2025, 16:00-17:00
• Hybrid: Cambridge University Engineering Department, LT6 or Zoom: https://cam-ac-uk.zoom.us/j/83363886282?pwd=eCJD8vmmxI29vSZMX92lmQjWWUgZgw.1.

If you have a question about this talk, please contact Brian Sun.

Discrete speech tokens have emerged as a fundamental representation for various downstream speech processing tasks, particularly in speech generation. However, most existing tokens encode dense, fixed-rate acoustic information, which introduces substantial redundancy and limits their efficiency. In this talk, I will first provide a brief review on the taxonomy of current discrete speech tokens, then present our works exploring the reduction of this information redundancy in two critical directions: (1) Speaker timbre disentanglement, introducing a low-bitrate, single-codebook and speaker-decoupled codec for speech. (2) Variable-rate temporal compression, exploring methods to dynamically adjust the frame rate of discrete tokens for better compactness and bitrate-performance tradeoff. Together, these efforts highlight pathways toward more efficient and controllable discrete speech representations, paving the way for the next generation of speech technologies.

This talk is part of the CUED Speech Group Seminars series.

This talk is included in these lists:

• CUED Speech Group Seminars
• Cambridge Forum of Science and Humanities
• Cambridge Language Sciences
• Cambridge talks
• Chris Davis' list
• Guy Emerson's list
• Hybrid: Cambridge University Engineering Department, LT6 or Zoom: https://cam-ac-uk.zoom.us/j/83363886282?pwd=eCJD8vmmxI29vSZMX92lmQjWWUgZgw.1
• Hybrid: LT6, Engineering Department or Zoom: https://cam-ac-uk.zoom.us/j/83363886282?pwd=eCJD8vmmxI29vSZMX92lmQjWWUgZgw.1
• Information Engineering Division seminar list
• PhD related

Note that ex-directory lists are not shown.