Interspeech'2005 - Eurospeech

Lisbon, Portugal
September 4-8, 2005

Harmonic Filtering for Joint Estimation of Pitch and Voiced Source with Single-Microphone Input

S. W. Lee (1), Frank K. Soong (2), P. C. Ching (1)

(1) Chinese University of Hong Kong, China; (2) Microsoft Research Asia, China

Standard correlation based methods are not effective in estimating pitch tracks of multiple speech sources from a single-microphone input In this paper, an adaptive harmonic filtering is proposed to jointly estimate the source signals and their corresponding fundamental frequencies. By exploiting the harmonic structure of voiced speech, pitch information of one source is extracted from the pitch prediction filter and the output residual becomes the estimate of the other source. The procedure is iterated successively with a summation constraint. From the evolution of pitch prediction filter, it is shown that the iterative harmonic filtering with the summation constraint is effective to separate multiple pitch tracks into individual ones.

Full Paper

Bibliographic reference.  Lee, S. W. / Soong, Frank K. / Ching, P. C. (2005): "Harmonic filtering for joint estimation of pitch and voiced source with single-microphone input", In INTERSPEECH-2005, 309-312.