We propose a multi-channel pitch determination algorithm (PDA) that has been tested on three speech databases (OdB SNR telephone speech, speech recorded in a car and clean speech) involving fifty-eight speakers. The system has been compared to AMPEX , to hand-labelled and laryngograph pitch contours. Our PDA comprises an automatic channel selection module and a pitch extraction module that relies on a pseudo-periodic histogram (combination of normalised scalar products for the less corrupted channels) in order to find pitch. It outperformed the reference system on OdB telephone and car speech. The automatic selection of channels was effective on the very noisy telephone speech (OdB) but not on the car speech where the robustness of the system is mainly due to the pitch extraction module in comparison to AMPEX. The paper reports in details the V/UV, UV/V performance and pitch estimation errors for the PDA and the reference system on the three databases.
Bibliographic reference. Rouat, Jean / Liu, Yong Chun / Morissette, Daniel (1995): "A pitch determination and voiced/unvoiced decision algorithm for noisy speech", In EUROSPEECH-1995, 397-400.