Finding Maximum Margin Segments in Speech

Author

Estevan, Yago Pereiro ; Wan, Vincent ; Scharenborg, Odette

Author_Institution

Dept. of Signal Theory & Commun., Universidad Carlos III de Madrid

Volume

4

fYear

2007

fDate

15-20 April 2007

Abstract

Maximum margin clustering (MMC) is a relatively new and promising kernel method. In this paper, we apply MMC to the task of unsupervised speech segmentation. We present three automatic speech segmentation methods based on MMC, which are tested on TIMIT and evaluated on the level of phoneme boundary detection. The results show that MMC is highly competitive with existing unsupervised methods for the automatic detection of phoneme boundaries. Furthermore, initial analyses show that MMC is a promising method for the automatic detection of sub-phonetic information in the speech signal.

Keywords

pattern clustering; speech processing; unsupervised learning; TIMIT; automatic detection; automatic speech segmentation methods; kernel method; maximum margin clustering; phoneme boundary detection; speech signal; subphonetic information; unsupervised speech segmentation; Automatic speech recognition; Automatic testing; Clustering methods; Computer science; Information analysis; Kernel; Signal analysis; Speech analysis; Speech processing; Support vector machines; clustering methods; speech processing; unsupervised learning;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech and Signal Processing, 2007. ICASSP 2007. IEEE International Conference on

Conference_Location

Honolulu, HI

ISSN

1520-6149

Print_ISBN

1-4244-0727-3

Electronic_ISBN

1520-6149

Type

conf

DOI

10.1109/ICASSP.2007.367225

Filename

4218256