The field of speech processing has undergone a transformative shift with the advent of deep
learning. The use of multiple processing layers has enabled the creation of models capable …

Deep learning has become the method of choice to tackle real-world problems in different
domains, partly because of its ability to learn from data and achieve impressive performance …

Deep Neural Networks (DNNs) trained on one dataset (source domain) do not perform well
on another set of data (target domain), which is different but has similar properties as the …

While self-supervised speech representation learning (SSL) models serve a variety of
downstream tasks, these models have been observed to overfit to the domain from which the …

The cross-domain performance of automatic speech recognition (ASR) could be severely
hampered due to the mismatch between training and testing distributions. Since the target …

Modern speech recognition systems exhibit rapid performance degradation under domain
shift. This issue is especially prevalent in data-scarce settings, such as low-resource …

Indian languages share a lot of overlap in acoustic and linguistic content. Though different
languages use different writing systems, the phoneme sets logically overlap. Most of these …

This work examines the development of Automatic Speech Recognition (ASR) systems for
low-resource languages, focusing on Hindi and Marathi, particularly in multilingual and code …

In this work, we explore the impact of different grapheme to phoneme (G2P) conversion
schemes for the task of automatic speech recognition (ASR) in Sanskrit. The performance of …

Speech Activity Detection (SAD) aims to accurately classify audio fragments containing
human speech. Current state-of-the-art systems for the SAD task are mainly based on deep …