Conformer has proven to be effective in many speech processing tasks. It combines the
benefits of extracting local dependencies using convolutions and global dependencies …

Conformer-based models have become the dominant end-to-end architecture for speech
processing tasks. With the objective of enhancing the conformer architecture for efficient …

Speech conveys more information than just text, as the same word can be uttered in various
voices to convey diverse information. Compared to traditional text-to-speech (TTS) methods …

Recently, large pretrained language models have demonstrated strong language
understanding capabilities. This is particularly reflected in their zero-shot and in-context …

This paper considers contrastive training for cross-modal 0-shot transfer wherein a pre-
trained model in one modality is used for representation learning in another domain using …

We propose the (): S emantically-A ligned M ultimodal U tterance-level Cross-L ingual S
peech R epresentation learning framework. Unlike previous works on speech representation …

Spoken language understanding (SLU) tasks have been studied for many decades in the
speech research community, but have not received as much attention as lower-level tasks …

This paper explores the capability of Mamba, a recently proposed architecture based on
state space models (SSMs), as a competitive alternative to Transformer-based models. In …

This paper presents BERT-CTC, a novel formulation of end-to-end speech recognition that
adapts BERT for connectionist temporal classification (CTC). Our formulation relaxes the …

Self-supervised speech representation learning (SSL) has shown to be effective in various
downstream tasks, but SSL models are usually large and slow. Model compression …