activity
20202026
most citedInterpreting A Pre-trained Model Is A Key For Model Architecture Optimization: A Case Study On Wav2Vec 2.0

1 citations · 1 across the 3 of their papers we have counts for

collaborators
Showing eess.ASShow all

2 papers · 1 filter

eess.AS2026

Unmixing The Crowd: Learning Persistent Speaker Representations from Mixture-Derived Multi-Speaker Embeddings

Sidharth Sidharth, Meysam Asgari, Hao-Wen Dong +1

We study whether persistent conversational speaker structure can be extracted directly from local overlapping speech mixtures. We propose a teacher-student framework that learns mi…

eess.AS2020

Refining Automatic Speech Recognition System for older adults

Liu Chen, Meysam Asgari

Building a high quality automatic speech recognition (ASR) system with limited training data has been a challenging task particularly for a narrow target population. Open-sourced A…