research
∙
05/28/2023
Stochastic Pitch Prediction Improves the Diversity and Naturalness of Speech in Glow-TTS
Flow-based generative models are widely used in text-to-speech (TTS) sys...
share
research
∙
11/30/2022
How to (virtually) train your sound source localizer
Learning-based methods have become ubiquitous in sound source localizati...
research
∙
10/12/2022
Can we use Common Voice to train a Multi-Speaker TTS system?
Training of multi-speaker text-to-speech (TTS) systems relies on curated...
research
∙
07/19/2022
Realistic sources, receivers and walls improve the generalisability of virtually-supervised blind acoustic parameter estimators
Blind acoustic parameter estimation consists in inferring the acoustic p...
research
∙
05/14/2022
The VoicePrivacy 2020 Challenge Evaluation Plan
The VoicePrivacy Challenge aims to promote the development of privacy pr...
research
∙
03/23/2022
The VoicePrivacy 2022 Challenge Evaluation Plan
For new participants - Executive summary: (1) The task is to develop a v...
research
∙
02/23/2022
Differentially Private Speaker Anonymization
Sharing real-world speech utterances is key to the training and deployme...
research
∙
09/01/2021
The VoicePrivacy 2020 Challenge: Results and findings
This paper presents the results and analyses stemming from the first Voi...
research
∙
09/01/2021
Benchmarking and challenges in security and privacy for voice biometrics
For many decades, research in speech technologies has focused upon impro...
research
∙
07/29/2021
Blind Room Parameter Estimation Using Multiple-Multichannel Speech Recordings
Knowing the geometrical and acoustical parameters of a room may benefit ...
research
∙
07/26/2020
UIAI System for Short-Duration Speaker Verification Challenge 2020
In this work, we present the system description of the UIAI entry for th...
research
∙
05/18/2020
Design Choices for X-vector Based Speaker Anonymization
The recently proposed x-vector based anonymization scheme converts any i...
research
∙
05/11/2020
Foreground-Background Ambient Sound Scene Separation
Ambient sound scenes typically comprise multiple short events occurring ...
research
∙
05/08/2020
Asteroid: the PyTorch-based audio source separation toolkit for researchers
This paper describes Asteroid, the PyTorch-based audio source separation...
research
∙
05/04/2020
Introducing the VoicePrivacy Initiative
The VoicePrivacy initiative aims to promote the development of privacy p...
research
∙
04/20/2020
CHiME-6 Challenge:Tackling Multispeaker Speech Recognition for Unsegmented Recordings
Following the success of the 1st, 2nd, 3rd, 4th and 5th CHiME challenges...
research
∙
02/05/2020
Limitations of weak labels for embedding and tagging
While many datasets and approaches in ambient sound analysis use weakly ...
research
∙
11/20/2019
Joint DNN-Based Multichannel Reduction of Acoustic Echo, Reverberation and Noise
We consider the problem of simultaneous reduction of acoustic echo, reve...
research
∙
11/12/2019
Privacy-Preserving Adversarial Representation Learning in ASR: Reality or Illusion?
Automatic speech recognition (ASR) is a key technology in many services ...
research
∙
11/10/2019
Evaluating Voice Conversion-based Privacy Protection against Informed Attackers
Speech signals are a rich source of speaker-related information includin...
research
∙
11/06/2019
The Speed Submission to DIHARD II: Contributions Lessons Learned
This paper describes the speaker diarization systems developed for the S...
research
∙
10/23/2019
Filterbank design for end-to-end speech separation
Single-channel speech separation has recently made great progress thanks...
research
∙
10/16/2019
Lead2Gold: Towards exploiting the full potential of noisy transcriptions for speech recognition
The transcriptions used to train an Automatic Speech Recognition (ASR) s...
research
∙
05/10/2019
AI in the media and creative industries
Thanks to the Big Data revolution and increasing computing capacities, A...
research
∙
05/03/2019
A Statistically Principled and Computationally Efficient Approach to Speech Enhancement using Variational Autoencoders
Recent studies have explored the use of deep generative models of speech...
research
∙
02/15/2019
An improved uncertainty propagation method for robust i-vector based speaker recognition
The performance of automatic speaker recognition systems degrades when f...
research
∙
03/28/2018
The fifth 'CHiME' Speech Separation and Recognition Challenge: Dataset, task and baselines
The CHiME challenge series aims to advance robust automatic speech recog...
research
∙
10/25/2017
Relative Transfer Function Inverse Regression from Low Dimensional Manifold
In room acoustic environments, the Relative Transfer Functions (RTFs) ar...
research
∙
07/01/2017
Rank-1 Constrained Multichannel Wiener Filter for Speech Recognition in Noisy Environments
Multichannel linear filters, such as the Multichannel Wiener Filter (MWF...
research
∙
07/22/2016
Experiments on the DCASE Challenge 2016: Acoustic Scene Classification and Sound Event Detection in Real Life Recording
In this paper we present our work on Task 1 Acoustic Scene Classi- ficat...
research
∙
12/28/2011
A general framework for online audio source separation
We consider the problem of online audio source separation. Existing algo...
research
∙
12/01/2009