By Topic

Single-channel speech separation using phase-based methods

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
Yun-Kyung Lee ; Dept. of Control & Robot Eng., Chungbuk Nat. Univ., Cheongju, South Korea ; In Sung Lee ; Oh-Wook Kwon

This paper addresses the problem of single-channel speech separation to extract and enhance the desired speech signal from mixed speech signals. We propose a new speech separation algorithm by utilizing both magnitude and phase information, which can be applied to multimedia mobile communication and navigation systems. Conventionally, phase information has been neglected in speech signal processing. However, in the proposed method, we formulate a probabilistic phase-based speech estimator based on zero-phase models to improve the speech separation performance. In the speech separation experiments, the proposed method is shown to improve speaker-to-interference ratio (SIR) by 2.2 dB compared to the system using magnitude models only. When only phase-based speech estimator is used for speech separation, the SIR was improved by 0.8 dB. This result justify that the proposed phase-based speech estimator achieves significant SIR improvement compared with the previous magnitude-based method.

Published in:

Consumer Electronics, IEEE Transactions on  (Volume:56 ,  Issue: 4 )