Abstract
The purpose of this chapter is to the applicability of the self-organizing map (SOM) to the modeling of perceived similarity relationships among voice qualities. Voice samples representing healthy and pathological voices were divided into five classes using the six-dimensional auditory ratings of six speech pathologists. The acoustic categorizations were made with twenty spectral features, which were selected using simulated annealing and learning vector quantization to maximize the classification accuracy. An accuracy of about 80 per cent was reached. The selection improved the match between the auditory categorization and clustering of samples on acoustic feature maps. Further improvement of the map models requires the addition of new types of acoustic features, and a larger data basis.
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.
