Despite the recent advancements in Automatic Speech Recognition (ASR), t...
Recent advances in using language models to obtain cross-modal audio-tex...
In this paper, we explore self-supervised learning (SSL) for analyzing a...
This paper describes the Ubenwa CryCeleb dataset - a labeled collection ...
In this paper, we introduce a new approach, called "Posthoc Interpretati...
Transformers have recently achieved state-of-the-art performance in spee...
In this paper, we present a self-supervised learning framework for
conti...
Transformers have enabled major improvements in deep learning. They ofte...
In recent years, deep learning based source separation has achieved
impr...
SpeechBrain is an open-source and all-in-one speech toolkit. It is desig...
Recurrent Neural Networks (RNNs) have long been the dominant architectur...
In this paper, we propose a two-step training procedure for source separ...
Continual learning consists in incrementally training a model on a seque...
Popular generative model learning methods such as Generative Adversarial...
Generative source separation methods such as non-negative matrix
factori...