Search Results for author: Francois Grondin

Found 5 papers, 3 papers with code

Exploring Self-Attention Mechanisms for Speech Separation

1 code implementation6 Feb 2022 Cem Subakan, Mirco Ravanelli, Samuele Cornell, Francois Grondin, Mirko Bronzi

In particular, we extend our previous findings on the SepFormer by providing results on more challenging noisy and noisy-reverberant datasets, such as LibriMix, WHAM!, and WHAMR!.

Denoising Speech Enhancement +1

Audio scene monitoring using redundant ad-hoc microphone array networks

no code implementations2 Mar 2021 Peter Gerstoft, Yihan Hu, Michael J. Bianco, Chaitanya Patil, Ardel Alegre, Yoav Freund, Francois Grondin

The DOAs are fed to a fusion center, concatenated, and used to perform the localization based on two proposed methods, which require only few labeled source locations (anchor points) for training.

GEV Beamforming Supported by DOA-based Masks Generated on Pairs of Microphones

1 code implementation19 May 2020 Francois Grondin, Jean-Samuel Lauzon, Jonathan Vincent, Francois Michaud

The solution presented in this paper is to train a neural network on pairs of microphones with different spacing and acoustic environmental conditions, and then use this network to estimate a time-frequency mask from all the pairs of microphones forming the array with an arbitrary shape.

speech-recognition Speech Recognition +1

Lightweight and Optimized Sound Source Localization and Tracking Methods for Open and Closed Microphone Array Configurations

1 code implementation1 Dec 2018 Francois Grondin, Francois Michaud

For sound source tracking, this paper presents a modified 3D Kalman (M3K) method capable of simultaneously tracking in 3D the directions of sound sources.

Audio and Speech Processing Sound

A Study of Enhancement, Augmentation, and Autoencoder Methods for Domain Adaptation in Distant Speech Recognition

no code implementations13 Jun 2018 Hao Tang, Wei-Ning Hsu, Francois Grondin, James Glass

Speech recognizers trained on close-talking speech do not generalize to distant speech and the word error rate degradation can be as large as 40% absolute.

Data Augmentation Distant Speech Recognition +3

Cannot find the paper you are looking for? You can Submit a new open access paper.