@inproceedings{e062a9ae88ee46e99b7b7959ede7d94b,
title = "High/Low Model for Scalable Multimicrophone Enhancement of Speech Mixtures",
abstract = "Many speech separation and enhancement methods take advantage of time-frequency sparsity by assuming that only one speech source in a mixture has nonzero power at each time and frequency. This “on/off” model is valuable for systems with more sources than microphones, but many methods that use it do not benefit from the spatial diversity of systems with large numbers of microphones. This work considers the high/low model, in which one source is strongest at each time-frequency index but all sources have nonzero power. A time-varying enhancement method using the high/low model combines the benefits of sparsity and spatial diversity and scales automatically with the number of microphones, resembling a time-frequency mask for underdetermined systems and a linear filter for overdetermined systems. The model is demonstrated using real-room data with up to 10 speech signals and between 1 and 160 microphones.",
keywords = "Microphone arrays, Source separation, Speech enhancement",
author = "Corey, {Ryan M.} and Singer, {Andrew C.}",
note = "Publisher Copyright: {\textcopyright} 2021 European Signal Processing Conference. All rights reserved.; 29th European Signal Processing Conference, EUSIPCO 2021 ; Conference date: 23-08-2021 Through 27-08-2021",
year = "2021",
doi = "10.23919/EUSIPCO54536.2021.9616105",
language = "English (US)",
series = "European Signal Processing Conference",
publisher = "European Signal Processing Conference, EUSIPCO",
pages = "880--884",
booktitle = "29th European Signal Processing Conference, EUSIPCO 2021 - Proceedings",
}