Name
Abstract | ||
|---|---|---|
This paper proposes a new feature extraction method for automatically detecting pathological voice in a normal conversation scenario. Unlike conventional approaches that utilize the static harmonic-to-noise ratio (HNR) characteristics of sustained vowel, the proposed method considers the dynamic movements of articulatory organs depending on the types of phonations. Assuming those movements reflect the health status of subjects, the proposed method utilizes the characteristics of HNR contour within a single sentence-level speech signal. Experimental results show that the proposed method reduces the classification error rate by 35.2 % (relative) compared to the conventional method. |
Year | DOI | Venue |
|---|---|---|
2014 | 10.1109/ICASSP.2014.6854749 | ICASSP |
Keywords | Field | DocType |
pathological speech detection,articulatory organs,harmonic-to-noise ratio,pathological voice detection,contour modeling,feature extraction method,speech synthesis,classification error rate,feature extraction,hnr characteristics,hnr contour,sentence-level speech signal,dynamic characteristic,pathological speech,continuous speech,vibrations,production,support vector machines,speech,gain,pathology,indexes | Pattern recognition,Computer science,Word error rate,Harmonic,Feature extraction,Speech recognition,Artificial intelligence,Vowel | Conference |
ISSN | Citations | PageRank |
1520-6149 | 2 | 0.41 |
References | Authors | |
8 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Jungwon Lee | 1 | 890 | 95.15 |
| Samuel Kim | 2 | 3 | 0.79 |
| Hong-Goo Kang | 3 | 190 | 48.76 |