The Automatic Detection of Hypernasality in Cleft Palate Speech Based on an Improved Cepstrum Method

Fang-Ling FU, Jia-Hui QIAN, Fei HE, Heng YIN, Xi-Yue WANG, Ling HE
2017 Proceedings of the 3rd Annual International Conference on Electronics, Electrical Engineering and Information Science (EEEIS 2017)   unpublished
Cleft palate is a birth defect with the resonance between the nasal cavity and oral cavity, which causes an additional nasal formant. And the accurate formant extraction method contributes to hypernasality detection. In this sense, we present a method for formant extraction. The proposed approach uses multi-resolution analysis of automatic segmented filtering combining cepstrum method to accurately extract the formants. It can increase the resolution in the low-frequency region, which is
more » ... for extracting the addition nasal formant around 250Hz. The proposed technique is tested on 416 vowels /a/ recorded by the West China Hospital of Stomatology, including 216 vowels for normal speech and 210 vowels for cleft palate speech. The formant frequency and formant amplitude are used as acoustic features for hypernasality detection, and the detection accuracy of hypernasality in cleft palate speech is 97.41%.
doi:10.2991/eeeis-17.2017.60 fatcat:7khlv6lbwnfhtddlgyo5kkfao4