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 …

Although supervised deep learning has revolutionized speech and audio processing, it has
necessitated the building of specialist models for individual tasks and application scenarios …

SpeechBrain is an open-source and all-in-one speech toolkit. It is designed to facilitate the
research and development of neural speech processing technologies by being simple …

Self-supervised learning (SSL) has proven vital for advancing research in natural language
processing (NLP) and computer vision (CV). The paradigm pretrains a shared model on …

Contrastive learning (CL) is one of the most successful paradigms for self-supervised
learning (SSL). In a principled way, it considers two augmented “views” of the same image …

Recently proposed self-supervised learning approaches have been successful for pre-
training speech representation models. The utility of these learned representations has been …

Spoken Language Understanding infers semantic meaning directly from audio data, and
thus promises to reduce error propagation and misunderstandings in end-user applications …

We present the MASSIVE dataset--Multilingual Amazon Slu resource package (SLURP) for
Slot-filling, Intent classification, and Virtual assistant Evaluation. MASSIVE contains 1M …

Abstract Machine learning is traditionally studied at the model level: researchers measure
and improve the accuracy, robustness, bias, efficiency, and other dimensions of specific …

As Automatic Speech Processing (ASR) systems are getting better, there is an increasing
interest of using the ASR output to do downstream Natural Language Processing (NLP) …