SKIP-SALSA: Skip Synchronous Fusion of ASR LLM DecodersAshish MittalDarshan Prabhuet al.2025INTERSPEECH 2025
In-situ text-only adaptation of speech models with low-overhead speech imputationsAshish MittalSunita Sarawagiet al.2023ICLR 2023
Deep Indexed Active Learning for Matching Heterogeneous Entity RepresentationsArjit JainSunita Sarawagiet al.2022VLDB 2022