Flow-based generative models are widely used in text-to-speech (TTS) sys...
Learning-based methods have become ubiquitous in sound source localizati...
Training of multi-speaker text-to-speech (TTS) systems relies on curated...
Blind acoustic parameter estimation consists in inferring the acoustic
p...
The VoicePrivacy Challenge aims to promote the development of privacy
pr...
For new participants - Executive summary: (1) The task is to develop a v...
Sharing real-world speech utterances is key to the training and deployme...
This paper presents the results and analyses stemming from the first
Voi...
For many decades, research in speech technologies has focused upon impro...
Knowing the geometrical and acoustical parameters of a room may benefit
...
In this work, we present the system description of the UIAI entry for th...
The recently proposed x-vector based anonymization scheme converts any i...
Ambient sound scenes typically comprise multiple short events occurring ...
This paper describes Asteroid, the PyTorch-based audio source separation...
The VoicePrivacy initiative aims to promote the development of privacy
p...
Following the success of the 1st, 2nd, 3rd, 4th and 5th CHiME challenges...
While many datasets and approaches in ambient sound analysis use weakly
...
We consider the problem of simultaneous reduction of acoustic echo,
reve...
Automatic speech recognition (ASR) is a key technology in many services ...
Speech signals are a rich source of speaker-related information includin...
This paper describes the speaker diarization systems developed for the S...
Single-channel speech separation has recently made great progress thanks...
The transcriptions used to train an Automatic Speech Recognition (ASR) s...
Thanks to the Big Data revolution and increasing computing capacities,
A...
Recent studies have explored the use of deep generative models of speech...
The performance of automatic speaker recognition systems degrades when f...
The CHiME challenge series aims to advance robust automatic speech
recog...
In room acoustic environments, the Relative Transfer Functions (RTFs) ar...
Multichannel linear filters, such as the Multichannel Wiener Filter (MWF...
In this paper we present our work on Task 1 Acoustic Scene Classi- ficat...
We consider the problem of online audio source separation. Existing
algo...
This article addresses the modeling of reverberant recording environment...