SOURCE-LINKED INTELLIGENCE

Encoder Awakening via Adapters: Effective Domain-Adaptive Fine-tuning of Speech-LLMs

arXiv · AI, language, vision and robotics · article · Sep 16, 2026 · UTC

Speech Large Language Models (Speech-LLMs), typically built from a pre-trained speech encoder, a modality projector, and an LLM fine-tuned with Low-Rank Adapters (LoRA), have shown strong Automatic Speech Recognition (ASR) performance on general-domain speech. However, adapting them to domain-shifted speech, such as child or dialectal speech, remains challenging under limited target-domain data. Given the dominant role of the LLM in Speech-LLMs, with cross-entropy loss applied only at the LLM output, the speech encoder may receive insufficient adaptation to new acoustic conditions. In this pap

Read original source ↗ Open in workspace

recordType

paper

region

Global