Abstract
A biologically inspired pitch determination algorithm is presented. This algorithm combines existing models of the cochlea and inner‐hair‐cell based spike generation [Lopez et al., J. Acoust. Soc. Am. 110, 3107 (2001); Sumner et al., ibid. 113, 893–901 (2003)] to model spike trains in the auditory nerve. The pitch and its salience are then estimated using a method proposed by Cariani [Cariani et al., J. Neurophysiol. 76, 1698–1716], which computes a summary autocorrelation function over the spike trains. Unlike Cariani’s work, where spike trains are obtained experimentally, we simulate the spike trains from biologically inspired models. The main contribution of our approach is to combine models of the auditory system and a pitch estimation method based on neural spike trains. The proposed algorithm was tested using standard synthesized sounds, speech, and singing voices. Results show that this algorithm better matches human performance as compared to traditional pitch detection algorithms used in automatic speech processing.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
