2026
ADVANCING SPEECH UNDERSTANDING IN SPEECH-AWARE LANGUAGE MODELS WITH GRPO
ICASSP 2026poster
In this paper, we introduce a Group Relative Policy Optimization (GRPO)-based method for training Speech-Aware Large Language Models (SALLMs) on open-format speech understanding tasks, such as Spoken Question Answering and Automatic Speech Translation. SALLMs have proven highly effective for speech…