Data Science Wire

Rethinking Speech-LLM Integration for ASR: Effective Joint Speech-Text Training by Interleaving

arXiv cs.CL4w4 min read

arXiv:2607.01733v1 Announce Type: new Abstract: Speech-LLM integration has shown promising results by leveraging extensive textual pretraining, yet its specific benefits for automatic speech recognition (ASR) remain unclear. We observe that as supervised ASR training data increases, the contribution of LLM priors becomes less evident, and simple speech-text joint training under-utilizes textual knowledge. We therefore propose Joint Speech-Text Interleaved Pretraining (JSTIP), an ASR-oriented pretraining strategy that constructs word-level and segment-level interleaved speech-text sequences wit

Read the full story at arXiv cs.CL

More in Machine Learning