Over the past decades, a particular focus is given to research on machine learning
techniques for speech processing applications. However, in the past few years, research …

Eliminating the negative effect of non-stationary environmental noise is a long-standing
research topic for automatic speech recognition but still remains an important challenge …

We propose TF-GridNet for speech separation. The model is a novel deep neural network
(DNN) integrating full-and sub-band modeling in the time-frequency (TF) domain. It stacks …

This paper proposes attentive statistics pooling for deep speaker embedding in text-
independent speaker verification. In conventional speaker embedding, frame-level features …

Abstract We introduce SoundSpaces 2.0, a platform for on-the-fly geometry-based audio
rendering for 3D environments. Given a 3D mesh of a real-world environment …

This paper proposes a full-band and sub-band fusion model, named as FullSubNet, for
single-channel real-time speech enhancement. Full-band and sub-band refer to the models …

Recently, convolution-augmented transformer (Conformer) has achieved promising
performance in automatic speech recognition (ASR) and time-domain speech enhancement …

Public evaluation campaigns and datasets promote active development in target research
areas, allowing direct comparison of algorithms. The second edition of the challenge on …

Real-world audio recordings are often degraded by factors such as noise, reverberation,
and equalization distortion. This paper introduces HiFi-GAN, a deep learning method to …

Recent development of speech signal processing, such as speech recognition, speaker
diarization, etc., has inspired numerous applications of speech technologies. The meeting …