activity
20172022
most citedLibriMix: An Open-Source Dataset for Generalizable Speech Separation

183 citations · 507 across the 18 of their papers we have counts for

collaborators
Showing cs.SDShow all

10 papers · 1 filter

cs.SD2021

Blind Room Parameter Estimation Using Multiple-Multichannel Speech Recordings

Prerak Srivastava, Antoine Deleforge, Emmanuel Vincent

Knowing the geometrical and acoustical parameters of a room may benefit applications such as audio augmented reality, speech dereverberation or audio forensics. In this paper, we s…

cs.SD202097 cited

CHiME-6 Challenge:Tackling Multispeaker Speech Recognition for Unsegmented Recordings

Shinji Watanabe, Michael Mandel, Jon Barker +18

Following the success of the 1st, 2nd, 3rd, 4th and 5th CHiME challenges we organize the 6th CHiME Speech Separation and Recognition Challenge (CHiME-6). The new challenge revisits…

cs.SD2020

Limitations of weak labels for embedding and tagging

Nicolas Turpault, Romain Serizel, Emmanuel Vincent

Many datasets and approaches in ambient sound analysis use weakly labeled data.Weak labels are employed because annotating every data sample with a strong label is too expensive.Ye…

cs.SD2019

Joint NN-Supported Multichannel Reduction of Acoustic Echo, Reverberation and Noise

Guillaume Carbajal, Romain Serizel, Emmanuel Vincent +1

We consider the problem of simultaneous reduction of acoustic echo, reverberation and noise. In real scenarios, these distortion sources may occur simultaneously and reducing them…

cs.SD2019

Filterbank design for end-to-end speech separation

Manuel Pariente, Samuele Cornell, Antoine Deleforge +1

Single-channel speech separation has recently made great progress thanks to learned filterbanks as used in ConvTasNet. In parallel, parameterized filterbanks have been proposed for…

cs.SD2019

A Statistically Principled and Computationally Efficient Approach to Speech Enhancement using Variational Autoencoders

Manuel Pariente, Antoine Deleforge, Emmanuel Vincent

Recent studies have explored the use of deep generative models of speech spectra based of variational autoencoders (VAEs), combined with unsupervised noise models, to perform speec…