In this paper, a sound source separation method is proposed by using the interaural intensity difference (IID) of stereo audio signal recorded in real environments. First, in order to improve the channel separability, a minimum variance distortionless response (MVDR) beamformer is employed to increase the intensity difference between stereo channels. Then, IID between stereo channels processed by the beamformer is computed and applied to sound source separation. The performance of the proposed sound source separation method is evaluated on the stereo audio source separation evaluation campaign (SASSEC) measures. It is shown from the evaluation that the proposed method outperforms a sound source separation method without applying a beamformer.

Authors: Chun, Chan Jun; Kim, Hong Kook
Affiliations: Gwangju Institute of Science and Technology (GIST), Gwangju, Korea; Gwangju Institute of Science and Tech (GIST), Gwangju, Korea(See document for exact affiliation information.)
AES Convention: 135 (October 2013) Paper Number: 8976
Publication Date: October 16, 2013 Import into BibTeX
Subject: Signal Processing
Permalink: https://www.aes.org/e-lib/browse.cfm?elib=17024

Click to purchase paper as a non-member or login as an AES member. If your company or school subscribes to the E-Library then switch to the institutional version. If you are not an AES member and would like to subscribe to the E-Library then Join the AES!

This paper costs $33 for non-members and is free for AES members and E-Library subscribers.

Learn more about the AES E-Library

E-Library Location: (CD 135Papers)   /conv/135/8976.pdf

Start a discussion about this paper!