90 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Centre Inria de l'Université de LorraineFR2 papers
- Centre Inria de l'Université de RennesFR2 papers
- Institut national de recherche en sciences et technologies du numériqueFR2 papers
- Laboratoire Lorrain de Recherche en Informatique et ses ApplicationsFR2 papers
- ROBOTLEARN: Apprentissage, perception et commande pour des robots sociauxFR2 papers
- Bar-Ilan UniversityIL1 paper
- Carnegie Mellon UniversityUS1 paper
- Centre Inria de l'Université Grenoble AlpesFR1 paper
- Centre National de la Recherche ScientifiqueFR1 paper
- Cochlear (Australia)AU1 paper
- École Polytechnique Fédérale de LausanneCH1 paper
- EURECOMFR1 paper
12 papers
A weighted-variance variational autoencoder model for speech enhancement
Ali Golmakani, Mostafa Sadeghi, Xavier Alameda-Pineda +1
We address speech enhancement based on variational autoencoders, which involves learning a speech prior distribution in the time-frequency (TF) domain. A zero-mean complex-valued G…
Signal Inpainting from Fourier Magnitudes
Louis Bahrman, Marina Krémé, Paul Magron +1
Signal inpainting is the task of restoring degraded or missing samples in a signal. In this paper we address signal inpainting when Fourier magnitudes are observed. We propose a ma…
Are disentangled representations all you need to build speaker anonymization systems?
Pierre Champion, Denis Jouvet, Anthony Larcher
Speech signals contain a lot of sensitive information, such as the speaker's identity, which raises privacy concerns when speech data get collected. Speaker anonymization aims to t…
Expression-preserving face frontalization improves visually assisted speech processing
Zhiqi Kang, Mostafa Sadeghi, Radu Horaud +1
Face frontalization consists of synthesizing a frontally-viewed face from an arbitrarily-viewed one. The main contribution of this paper is a frontalization methodology that preser…
The VoicePrivacy 2022 Challenge Evaluation Plan
Natalia Tomashenko, Xin Wang, Xiaoxiao Miao +7
For new participants - Executive summary: (1) The task is to develop a voice anonymization system for speech data which conceals the speaker's voice identity while protecting lingu…
Detecting acoustic reflectors using a robot's ego-noise
Usama Saqib, Antoine Deleforge, Jesper Jensen
In this paper, we propose a method to estimate the proximity of an acoustic reflector, e.g., a wall, using ego-noise, i.e., the noise produced by the moving parts of a listening ro…
dEchorate: a Calibrated Room Impulse Response Database for Echo-aware Signal Processing
Diego Di Carlo, Pinchas Tandeitnik, Cédric Foy +3
This paper presents dEchorate: a new database of measured multichannel Room Impulse Responses (RIRs) including annotations of early echo timings and 3D positions of microphones, re…
DNN-Based Distributed Multichannel Mask Estimation for Speech Enhancement in Microphone Arrays
Nicolas Furnon, Romain Serizel, Irina Illina +1
Multichannel processing is widely used for speech enhancement but several limitations appear when trying to deploy these solutions to the real-world. Distributed sensor arrays that…
MULAN: A Blind and Off-Grid Method for Multichannel Echo Retrieval
Helena Peic Tukuljac, Antoine Deleforge, Rémi Gribonval
This paper addresses the general problem of blind echo retrieval, i.e., given M sensors measuring in the discrete-time domain M mixtures of K delayed and attenuated copies of an un…
Large-Scale Weakly Labeled Semi-Supervised Sound Event Detection in Domestic Environments
Romain Serizel, Nicolas Turpault, Hamid Eghbal-Zadeh +1
This paper presents DCASE 2018 task 4. The task evaluates systems for the large-scale detection of sound events using weakly labeled data (without time boundaries). The target of t…
The fifth 'CHiME' Speech Separation and Recognition Challenge: Dataset, task and baselines
Jon Barker, Shinji Watanabe, Emmanuel Vincent +1
The CHiME challenge series aims to advance robust automatic speech recognition (ASR) technology by promoting research at the interface of speech and language processing, signal pro…
Separake: Source Separation with a Little Help From Echoes
Robin Scheibler, Diego Di Carlo, Antoine Deleforge +1
It is commonly believed that multipath hurts various audio processing algorithms. At odds with this belief, we show that multipath in fact helps sound source separation, even with…