TY - GEN
T1 - Alpha-Stable Low-Rank Plus Residual Decomposition for Speech Enhancement
AU - Simsekli, Umut
AU - Erdogan, Halil
AU - Leglaive, Simon
AU - Liutkus, Antoine
AU - Badeau, Roland
AU - Richard, Gael
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2018/9/10
Y1 - 2018/9/10
N2 - In this study, we propose a novel probabilistic model for separating clean speech signals from noisy mixtures by decomposing the mixture spectra into a structured speech part and a more flexible residual part. The main novelty in our model is that it uses a family of heavy-tailed distributions, so called the α-stable distributions, for modeling the residual signal. We develop an expectation-maximization algorithm for parameter estimation and a Monte Carlo scheme for posterior estimation of the clean speech. Our experiments show that the proposed method outperforms relevant factorization-based algorithms by a significant margin.
AB - In this study, we propose a novel probabilistic model for separating clean speech signals from noisy mixtures by decomposing the mixture spectra into a structured speech part and a more flexible residual part. The main novelty in our model is that it uses a family of heavy-tailed distributions, so called the α-stable distributions, for modeling the residual signal. We develop an expectation-maximization algorithm for parameter estimation and a Monte Carlo scheme for posterior estimation of the clean speech. Our experiments show that the proposed method outperforms relevant factorization-based algorithms by a significant margin.
KW - Alpha-stable distributions
KW - Audio source separation
KW - Monte Carlo Expectation-Maximization
KW - Speech enhancement
UR - https://www.scopus.com/pages/publications/85048545410
U2 - 10.1109/ICASSP.2018.8461539
DO - 10.1109/ICASSP.2018.8461539
M3 - Conference contribution
AN - SCOPUS:85048545410
SN - 9781538646588
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 651
EP - 655
BT - 2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018
Y2 - 15 April 2018 through 20 April 2018
ER -