AI RESEARCH
CALM: Joint Contextual Acoustic-Linguistic Modeling for Personalization of Multi-Speaker ASR
arXiv CS.CL
•
ArXi:2601.22792v2 Announce Type: replace-cross We present CALM, a joint Contextual Acoustic-Linguistic Modeling framework for multi-speaker automatic speech recognition (ASR). In personalized AI scenarios, the joint availability of acoustic and linguistic cues naturally motivates the integration of target-speaker conditioning with contextual biasing in overlapping conversations. CALM implements this integration in an end-to-end framework through speaker embedding-driven target-speaker extraction and dynamic vocabulary-based contextual biasing.