MMM: Multi-Layer Multi-Residual Multi-Stream Discrete Speech Representation from Self-supervised Learning Model.

Jiatong Shi Xutai Ma Hirofumi Inaguma Anna Sun Shinji Watanabe 0001 MMM: Multi-Layer Multi-Residual Multi-Stream Discrete Speech Representation from Self-supervised Learning Model. 2024 INTERSPEECH https://doi.org/10.21437/Interspeech.2024-2251 conf/interspeech/2024 db/conf/interspeech/interspeech2024.html#ShiMIS024