Shirish Karande

Towards Improving NAM-to-Speech Synthesis Intelligibility using Self-Supervised Speech Models

2024 · arXiv (Cornell University)

We propose a novel approach to significantly improve the intelligibility in the Non-Audible Murmur (NAM)-to-speech conversion task, leveraging self-supervision and sequence-to-sequence (Seq2Seq) learning techniques. Unlike conventional methods that explicitly record ground-truth speech, our methodology relies …