Ambuj Mehrish

Control accent strength in zero-shot TTS with a single model and inference-time weight, outperforming cascaded systems on out-of-domain accents without sacrificing speaker identity.

Transforming test-time reinforcement learning from a simplistic voting mechanism into a sophisticated consensus-based reward system could redefine how we approach model evaluation and training.

Retrieval-guided initialization in RAG-Audio nearly matches the performance of direct retrieval in brain-to-audio tasks, revolutionizing how we reconstruct audio from neural signals.