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 …

Self-supervised training has shown promising gains in pretraining models and facilitating
the downstream finetuning for speech recognition, like multilingual ASR. Most existing …

Self-supervised learning (SSL) in the pretraining stage using un-annotated speech data has
been successful in low-resource automatic speech recognition (ASR) tasks. However …

Recently, self-supervised learning (SSL) from unlabelled speech data has gained increased
attention in the automatic speech recognition (ASR) community. Typical SSL methods …

State-of-the-art automatic speech recognition (ASR) systems are trained with tens of
thousands of hours of labeled speech data. Human transcription is expensive and time …

Foundation models (FMs), that are trained on broad data at scale and are adaptable to a
wide range of downstream tasks, have brought large interest in the research community …

Training state-of-the-art Automated Speech Recognition (ASR) models typically requires a
substantial amount of transcribed speech. In this work, we demonstrate that a modality …

An effective way to learn representations from untranscribed speech and unspoken text with
linguistic/lexical representations derived from synthesized speech was introduced in …

We propose a neural language modeling system based on low-rank adaptation (LoRA) for
speech recognition output rescoring. Although pretrained language models (LMs) like BERT …

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 …