The reviewed record of science sign in
Pith

arxiv: 2410.03798 · v2 · pith:TWBG5UEU · submitted 2024-10-04 · cs.CL · cs.SD· eess.AS

Self-Powered LLM Modality Expansion for Large Speech-Text Models

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:TWBG5UEUrecord.jsonopen to challenge →

classification cs.CL cs.SDeess.AS
keywords speechlsmsdatalargemodelsself-poweredspeech-texttasks
0
0 comments X
read the original abstract

Large language models (LLMs) exhibit remarkable performance across diverse tasks, indicating their potential for expansion into large speech-text models (LSMs) by integrating speech capabilities. Although unified speech-text pre-training and multimodal data instruction-tuning offer considerable benefits, these methods generally entail significant resource demands and tend to overfit specific tasks. This study aims to refine the use of speech datasets for LSM training by addressing the limitations of vanilla instruction tuning. We explore the instruction-following dynamics within LSMs, identifying a critical issue termed speech anchor bias-a tendency for LSMs to over-rely on speech inputs, mistakenly interpreting the entire speech modality as directives, thereby neglecting textual instructions. To counteract this bias, we introduce a self-powered LSM that leverages augmented automatic speech recognition data generated by the model itself for more effective instruction tuning. Our experiments across a range of speech-based tasks demonstrate that self-powered LSM mitigates speech anchor bias and improves the fusion of speech and text modalities in LSMs. Data, code and scripts are freely available at https://github.com/ytf-philp/Self-powered-LSM.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.