@inproceedings{70ece53fd0904f7681204ab4a6dbce54,
title = "Single-channel speech separation based on Gaussian process regression",
abstract = "Gaussian process (GP) is a flexible kernel-based learning method which has found widespread applications in signal processing. In this paper, a supervised approach is proposed to handle single-channel speech separation (SCSS) problem. We focus on modeling a nonlinear mapping between mixed and clean speeches based on GP regression, in which reconstructed audio signal is estimated by the predictive mean of GP model. The nonlinear conjugate gradient method was utilized to perform the hyper-parameter optimization. The experiment on a subset of TIMIT speech dataset is carried out to confirm the validity of the proposed approach.",
keywords = "Gaussian process regression, single-channel speech separation",
author = "Nguyen, {Le Dinh} and Chen, {Sih Huei} and Tai, {Tzu Chiang} and Wang, {Jia Ching}",
note = "Publisher Copyright: {\textcopyright} 2018 IEEE; 20th IEEE International Symposium on Multimedia, ISM 2018 ; Conference date: 10-12-2018 Through 12-12-2018",
year = "2018",
month = jul,
day = "2",
doi = "10.1109/ISM.2018.00040",
language = "???core.languages.en_GB???",
series = "Proceedings - 2018 IEEE International Symposium on Multimedia, ISM 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "275--278",
booktitle = "Proceedings - 2018 IEEE International Symposium on Multimedia, ISM 2018",
}