Speech Prosody 2004

Nara, Japan
March 23-26, 2004

Multi-Pitch Detection Algorithm Using Constrained Gaussian Mixture Model and Information Criterion for Simultaneous Speech

Hirokazu Kameoka, Takuya Nishimoto, Shigeki Sagayama

Graduate School of Information Science and Technology, The University of Tokyo, Japan

In this paper, a co-channel multi-pitch detection algorithm is described. We suggest the importance of this when prosodic information is need to be extracted separately from respective F0 patterns of concurrent utterances. Though temporal continuity of speech prosody should be considered, we discuss a process done independently on each single frame as the first step. A model of multiple harmonic structures is constructed with a mixture of tied Gaussian mixtures with which a single harmonic structure is modeled. Our algorithm enables to detect both a number of concurrent speakers, and each spectral envelope of underlying harmonic structure based on a maximum likelihood estimation of the model parameters using EM algorithm and an information criterion. It operates without a priori information of F0 contours and a restriction of a number of speakers, and it also extracts accurate F0s as continuous values with simple procedures in spectral domain. Experiments showed our algorithm outperformed well-known cepstrum for both speech signals of a single speaker and simultaneous two speakers.

Full Paper

Bibliographic reference.  Kameoka, Hirokazu / Nishimoto, Takuya / Sagayama, Shigeki (2004): "Multi-pitch detection algorithm using constrained Gaussian mixture model and information criterion for simultaneous speech", In SP-2004, 533-536.