THE ROBUSTNESS AND APPLICABILITY OF AUDIO SOURCE SEPARATION FROM SINGLE MIXTURES

The separation of audio sources from their single mixture is a great challenge in signal processing research. Many single mixture source separation techniques have been proposed in the past 20 years but unfortunately the results are not pleasing enough for practical applications. In this tutorial-review paper, single-channel audio source separation techniques are divided into three broad categories: separation by auditory scene analysis (ASA), training based separation and blind source separation (BSS). Each of the categories is briefly described to contrast their methodological differences. This study focuses on the limitations and robustness under adverse acoustic environment of the seveal categories. We compare the success and usability of the different techniques in real world applications. Abstract: The separation of audio sources from their single mixture is a great challenge in signal processing research. Many single mixture source separation techniques have been proposed in the past 20 years but unfortunately the results are not pleasing enough for practical applications. In this tutorial-review paper, single-channel audio source separation techniques are divided into three broad categories: separation by auditory scene analysis (ASA), training based separation and blind source separation (BSS). Each of the categories is briefly described to contrast their methodological differences. This study focuses on the limitations and robustness under adverse acoustic environment of the seveal categories. We compare the success and usability of the different techniques in real world applications.

[1]  Albert S. Bregman,et al.  Auditory scene analysis : hearing in complex environments , 1993 .

[2]  Gert Cauwenberghs,et al.  Monaural separation of independent acoustical components , 1999, ISCAS'99. Proceedings of the 1999 IEEE International Symposium on Circuits and Systems VLSI (Cat. No.99CH36349).

[3]  Keikichi Hirose,et al.  Single-Mixture Audio Source Separation by Subspace Decomposition of Hilbert Spectrum , 2007, IEEE Transactions on Audio, Speech, and Language Processing.

[4]  Te-Won Lee,et al.  Blind Speech Separation , 2007, Blind Speech Separation.

[5]  Christian Uhle,et al.  EXTRACTION OF DRUM TRACKS FROM POLYPHONIC MUSIC USING INDEPENDENT SUBSPACE ANALYSIS , 2003 .

[6]  G.-J. Jang,et al.  Single-channel signal separation using time-domain basis functions , 2003, IEEE Signal Processing Letters.

[7]  Martin Cooke,et al.  Modelling auditory processing and organisation , 1993, Distinguished dissertations in computer science.

[8]  Sam T. Roweis,et al.  One Microphone Source Separation , 2000, NIPS.

[9]  DeLiang Wang,et al.  Monaural speech segregation based on pitch tracking and amplitude modulation , 2002, IEEE Transactions on Neural Networks.

[10]  Daniel P. W. Ellis,et al.  Multiband audio modeling for single-channel acoustic source separation , 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[11]  K. Hirose,et al.  Separation of Speech and Interfering Audio Signal from Single Mixture by Subspace Decomposition , 2005 .

[12]  Eric D. Scheirer,et al.  Sound Scene Segmentation by Dynamic Detection of Correlogram Comodulation , 1999 .

[13]  Michael A. Casey,et al.  Separation of Mixed Audio Sources By Independent Subspace Analysis , 2000, ICMC.