Shashi Kumar

Context Projector: Complementary Keyword and Dialogue Context Embeddings for LLM-based ASR

Closing the Speech-Text Gap with Limited Audio for Effective Domain Adaptation in LLM-Based ASR

MB using only 10% of the target-domain speech achieves word error rates comparable to, or better than, conventional ASR fine-tuning with the full dataset, indicating that small amounts of speech provide a strong modality-alignment signal.

Generative vs. Encoder Large Language Models for ASR Evaluation: A Comparative Study

The results show that encoder-based metrics remain highly competitive, while generative LLMs perform strongly in hypothesis comparison and improve the interpretability of ASR evaluation.

When Synthetic Speech Is All You Have: Better Call GRPO

This work shows that Group Relative Policy Optimization (GRPO) extracts far more from the same synthetic speech than SFT, and traces the gain to behavior rather than representation: GRPO reduces insertion errors by improving stopping calibration and speech-to-text alignment by better anchoring attention to audio, leavi...