← Search

Aswin Sivaraman

2 accepted papers

2023

The Potential of Neural Speech Synthesis-Based Data Augmentation for Personalized Speech Enhancement

ICASSP 2023accepted

With the advances in deep learning, speech enhancement systems benefited from large neural network architectures and achieved state-of-the-art quality. However, speaker-agnostic methods are not always desirable, both in terms of quality and their complexity, when they are to be used in a resource-co…

Cited by 0SourceScholar
2022

Adapting Speech Separation to Real-World Meetings using Mixture Invariant Training

ICASSP 2022accepted

The recently-proposed mixture invariant training (MixIT) is an unsupervised method for training single-channel sound separation models because it does not require ground-truth isolated reference sources. In this paper, we investigate using MixIT to adapt a separation model on real far-field overlapp…

Cited by 26SourceScholar