Abstract | ||
---|---|---|
Irregular phonation (also called creaky voice, glottalization and laryngealization) may have various communicative functions in speech. Thus the automatic classification of phonation type into regular and irregular can have a number of applications in speech technology. In this paper, we propose such a classifier that extracts six acoustic cues from vowels and then labels them as regular or irregular by means of a support vector machine. We integrated cues from earlier phonation type classifiers and improved their performance in five out of the six cases. The classifier with the improved cue set produced a 98.85% hit rate and a 3.47% false alarm rate on a subset of the TIMIT corpus. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1007/978-3-642-11509-7_6 | NOLISP |
Keywords | Field | DocType |
hit rate,phonation type classifier,phonation type,irregular phonation,timit corpus,false alarm rate,acoustic cue,improved cue,automatic classification,speech technology,support vector machine,glottalization,voice quality | Hit rate,Glottalization,TIMIT,Pattern recognition,Computer science,Support vector machine,Creaky voice,Speech recognition,Artificial intelligence,Phonation,Constant false alarm rate,Speech technology | Conference |
Volume | ISSN | ISBN |
5933 | 0302-9743 | 3-642-11508-X |
Citations | PageRank | References |
6 | 0.47 | 5 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Tamás Bohm | 1 | 14 | 2.00 |
Zoltán Both | 2 | 6 | 0.47 |
Géza Németh | 3 | 102 | 25.57 |