Optimal multi-pitch estimation using the EM algorithm for co-channel speech separation

Authors:
Dan Chazan;Yoram Stettiner;David Malah
Affiliations:
IBM Science and Technology Center, Technion City, Haifa, Israel;Dept. of Electrical Engineering, Technion-Israel Institute for Technology, Technion City, Haifa, Israel and Nexus Telecommunication Systems Ltd., Givataim, Israel;Dept. of Electrical Engineering, Technion-Israel Institute of Technology, Haifa, Israel
Venue:
ICASSP'93 Proceedings of the 1993 IEEE international conference on Acoustics, speech, and signal processing: speech processing - Volume II
Year:
1993

Citing 2
Cited 1

An effective speech separation system which requires no a priori information

ICASSP '91 Proceedings of the Acoustics, Speech, and Signal Processing, 1991. ICASSP-91., 1991 International Conference
Super resolution pitch determination of speech signals

IEEE Transactions on Signal Processing

Estimation of the parameters of a long-term model for accurate representation of voiced speech

ICASSP'93 Proceedings of the 1993 IEEE international conference on Acoustics, speech, and signal processing: speech processing - Volume II

Quantified Score

Hi-index	0.00

Visualization

Abstract

The paper addresses the problem of optimally estimating (in the ML sense) the pitch of each of several speakers talking simultaneously. This information is needed in systems which perform co-channel speech separation. We propose a multi-pitch model which is used in conjunction with an EM-based iterative estimation scheme. In addition, the pitch period of each speaker is allowed to vary linearly in the analysis interval, thus offering improved co-channel speech separation. The proposed algorithm is shown to outperform standard pitch detection algorithms, in detecting the pitch of simulataneous speakers.