← Back to feed

GSLM2 MultiStream Speech Rep Learning and Gen Spoken Language Modeling

AI · Research · 2026-11-03 13:33

arXiv 新论文提出 GSLM2，用多流语音表征做生成式口语语言建模，作者为 Yosuke Higuchi 等 17 人，附音频摘要。

Source: arxiv.org

Auto-generated summary for reference only. RSS