Abstract
A simple and efficient algorithm is presented to separate concurrent speeches. The parameters of mixed speeches are estimated by searching in the neighbor area of given pitches to minimize the error between the original and the synthetic spectrums. The effectiveness of the proposed algorithm to separate close frequencies is demonstrated.
References
A. J. W. Van der Kouwe, D. L. Wang, G. J. Brown, A comparison of auditory and blind separation techniques for speech segregation, IEEE Trans. on Speech and audio processing, 9(2001)3, 189–195.
G. J. Brown, M. Cooke, Computational auditory scene analysis, Computer Speech and Language, 8(1994), 297–336.
R. Meddis, L. O’Mard, Psychophysically Faithful Methods for Extracting Pitch, in Computational Auditory Scene Analysis (eds: D. Rosenthal & H. Okuno), Lawrence Erlbaum. 1998, 43–58.
D. W. Griffith, J. S. Lim, Multiband excitation vocoder, IEEE Trans. on ASSP, 36(1988)8, 1223–1235.
R. J. McAulay, T. F. Quatieri, Speech analysis/synthesis based on a sinusoidal representation, IEEE Trans. on ASSP, 34(1986)4, 744–754.
Author information
Authors and Affiliations
Additional information
Supported by the National Natural Science Foundation of China (No.60172048)
About this article
Cite this article
Huang, X., Wei, G. Speech separation algorithm for auditory scene analysis. J. of Electron.(China) 21, 261–264 (2004). https://doi.org/10.1007/BF02687881
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF02687881