ASSET: Adaptive Speech Segmentation via Reinforcement Learning

arXiv:2610.14309v1 Announce Type: new Abstract: Speech large language models (LLMs) are often built using pretrained acoustic encoders as an audio interface to an LLM decoder. However, LLMs scale poorly with input sequence length, while acoustic encoders tend to produce substantially longer sequence

arXiv cs.CLMittwoch 06:00 · 14.10.1 Min. Lesezeit