A new algorithm for voicing detection and voice pitch estimation based on the neocognitron

Abstract

One of the more widely used cochlear implants is the Nucleus multielectrode implant, developed by the University of Melbourne and Cochlear Pty Ltd. The speech processor used with this implant is the MSP, programmed with the multipeak strategy. This device incorporates circuits to estimate the fundamental frequency (F0) of speech signals and to decide whether voicing is present. The authors describe a new F0 estimator and voicing detection algorithm based on the neocognitron. Performance was compared with that of three other F0 estimation algorithms: linear predictive coding, cepstral analysis, and the algorithm used in the Multipeak-MSP processor. For the speech samples tested, the neocognitron performed more reliably than the other three systems.<>