Multipitch Tracking for Noisy and Reverberant Speech
Abstract
Multipitch tracking in real environments is critical for speech signal processing. Determining pitch in reverberant and noisy speech is a particularly challenging task. In this paper, we propose a robust algorithm for multipitch tracking in the presence of both background noise and room reverberation. An auditory front-end and a new channel selection method are utilized to extract periodicity features. We derive the conditional probability given each pitch state, which estimates the likelihood of the observed periodicity features given pitch candidates. A hidden Markov model integrates these probabilities and searches for the best pitch state sequence. Our algorithm can reliably detect single and double pitch contours in noisy and reverberant conditions. Quantitative evaluations show that our approach significantly outperforms existing ones, particularly in reverberant conditions.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jan 01, 2009
- Accession Number
- AD1001191
Entities
People
- DeLiang Wang
- Zhaozhang Jin
Organizations
- Ohio State University