Vocalnet-M2: Advancing Low-Latency Spoken Language Modeling via Integrated Multi-Codebook Tokenization and Multi-Token Prediction
Vocalnet-M2: Advancing Low-Latency Spoken Language Modeling via Integrated Multi-Codebook Tokenization and Multi-Token Prediction
Yuhao Wang,Ziyang Cheng,4 Authors,Yu Wang
2026 · DOI: 10.1109/icassp55912.2026.11461309
IEEE International Conference on Acoustics, Speech, and Signal Processing · 0 Citations