2024/09/25 by Prashanth Gurunath Shivakumar, Shivakumar, Prashanth Gurunath, Jari Kolehmainen +11 · 2 citations
Computer Science · #Audio and Speech Processing (eess.AS) #Computation and Language (cs.CL) #FOS: Computer and information sciences #FOS: Electrical engineering #Sound (cs.SD) #Speech Recognition and Synthesis #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2409.16654
openalex publication_date 2024/09/25 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Large language models (LLM) have demonstrated the ability to understand human language by leveraging large amount of text data. Automatic speech recognition (ASR) systems are often limited by available transcribed speech data and benefit from a second pass rescoring using LLM. Recently multi-modal large language models, particularly speech and text foundational models have demonstrated strong spoken language understanding. Speech-Text foundational models leverage large amounts of unlabelled and labelled data both in speech and text modalities to model human language. In this work, we propose novel techniques to use multi-modal LLM for ASR rescoring. We also explore discriminative training to further improve the foundational model rescoring performance. We demonstrate cross-modal knowledge transfer in speech-text LLM can benefit rescoring. Our experiments demonstrate up-to 20% relative improvements over Whisper large ASR and up-to 15% relative improvements over text-only LLM.