Title :
Pathological voice discrimination using cepstral analysis, vector quantization and Hidden Markov Models
Author :
Costa, Silvana C. ; Neto, Benedito G Aguiar ; Fechine, Joseana M.
Author_Institution :
Fed. Center of Technol. Educ. of Paraiba, Fed. Univ. of Campina Grande, Campina Grande
Abstract :
Pathological voice discrimination has been made using digital signal processing techniques as a complementary tool to videolaringoscopy exams. This method is non-invasive to patients compared to laringoscopy. This paper aims at analyzing the use of cepstral analysis to discriminate voices affected by vocal fold pathologies. A Vector Quantizer using a distortion measurement followed by a Hidden Markov Model-based classifier is employed. Results obtained show an effective and objective way in analyzing voice disorders caused by a vocal fold pathology.
Keywords :
audio signal processing; biology computing; cepstral analysis; hidden Markov models; speech processing; vector quantisation; Hidden Markov Models; cepstral analysis; digital signal processing; pathological voice discrimination; vector quantization; videolaringoscopy exams; Acoustic measurements; Cepstral analysis; Digital signal processing; Distortion measurement; Hidden Markov models; Pathology; Predictive models; Signal analysis; Speech analysis; Vector quantization;
Conference_Titel :
BioInformatics and BioEngineering, 2008. BIBE 2008. 8th IEEE International Conference on
Conference_Location :
Athens
Print_ISBN :
978-1-4244-2844-1
Electronic_ISBN :
978-1-4244-2845-8
DOI :
10.1109/BIBE.2008.4696783
