Speaker phone mode classification using Gaussian mixture models

Author

Eghbal-zadeh, H. ; Sobhan-manesh, F. ; Sameti, H. ; BabaAli, B.

Author_Institution

Shiraz Univ., Shiraz, Iran

fYear

2011

fDate

29-30 Sept. 2011

Firstpage

1

Lastpage

6

Abstract

This study focuses on the mode classification of phones speaker modes using GMM. In this regard, speech data in both enabled and disabled speaker modes of cell phones and telephones were collected, processed and classified into two different categories. The different mixture numbers (1 to 4) of GMM and wave files sizes of 10, 20, 40 and 80 kb were tested in order to obtain an optimal condition for classification. The GMM method attained 87.99% correct classification rate on test data. This classification is important for speech enabled IVR systems [1], dialog systems and many systems in speech processing in the sense that it could help to load an optimum model for increasing system accuracy.

Keywords

Gaussian processes; cellular radio; interactive systems; signal classification; speaker recognition; telephone equipment; GMM; Gaussian mixture model; cell phone; classification rate; dialog system; disabled speaker mode; enabled speaker mode; interactive voice response; speaker phone mode classification; speech data; speech enabled IVR system; speech processing; system accuracy; telephone; wave file; Accuracy; Data models; Hidden Markov models; Speech processing; Speech recognition; Support vector machine classification; Training; dialogue systems; speech enabled IVR; telephony device classification; telephony speech recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Signal Processing Algorithms, Architectures, Arrangements, and Applications Conference Proceedings (SPA), 2011

Conference_Location

Poznan

Print_ISBN

978-1-4577-1486-3

Type

conf

Filename

6190945