Sourav Bhattacharya

Augmenting Conversational Agents with Ambient Acoustic Contexts

2020

Conversational agents are rich in content today. However, they are entirely oblivious to users’ situational context, limiting their ability to adapt their response and interaction style. To this end, we explore the design space for …

Benchmarking Rotary Position Embeddings for Automatic Speech Recognition

2025 · arXiv (Cornell University)

Self-attention relies on positional embeddings to encode input order. Relative Position (RelPos) embeddings are widely used in Automatic Speech Recognition (ASR). However, RelPos has quadratic time complexity to input length and is often incompatible with …