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

This document describes version 0.10 of TorchAudio: building blocks for machine learning
applications in the audio and speech processing domain. The objective of TorchAudio is to …

Speech self-supervised models such as wav2vec 2.0 and HuBERT are making revolutionary
progress in Automatic Speech Recognition (ASR). However, they have not been totally …

Speaker modeling is essential for many related tasks, such as speaker recognition and
speaker diarization. The dominant modeling approach is fixed-dimensional vector …

Deep neural networks have shown excellent prospects in speech separation tasks.
However, obtaining good results while keeping a low model complexity remains challenging …

Despite impressive results, deep learning-based technologies also raise severe privacy and
environmental concerns induced by the training procedure often conducted in data centers …

We present AdVerb, a novel audio-visual dereverberation framework that uses visual cues
in addition to the reverberant sound to estimate clean audio. Although audio-only …

Generating vivid and emotional 3D co-speech gestures is crucial for virtual avatar animation
in human-machine interaction applications. While the existing methods enable generating …

Prior researchers show that existing automatic speech recognition (ASR) systems are
vulnerable to adversarial examples. Most existing adversarial attacks against ASR systems …

PaddleSpeech is an open-source all-in-one speech toolkit. It aims at facilitating the
development and research of speech processing technologies by providing an easy-to-use …