Abstract

The use of extracted acoustic features as descriptors of abnormal voice quality was explored by correlating voice quality ratings with the measurements. Sixteen talkers with no history of speech problems and 52 talkers with documented laryngeal pathologies recorded the vowel /ɑ/ using their typical pitch and loudness. Estimates of the excitation for each vowel were obtained using the linear prediction technique of inverse filtering, and the acoustic measurements, known as residue features, were calculated from this waveform. Voice quality estimates were obtained from a panel of judges who rated each vowel on 11 voice quality scales that have been described in the literature. The residue features were used as predictors of average voice quality rating in multiple linear regression analyses. The results are discussed in terms of the voice quality scales that were used most reliably by the judges and the ability of the features to distinguish among various voice quality categories.

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 call

Disclaimer: 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.