SPECTRA: A SPEech proCessing plaTform as smaRtphone Application

Author

Bisio, Igor ; Lavagetto, Fabio ; Marchese, Mario ; Sciarrone, Andrea ; Fra, Cristina ; Valla, Massimo

Author_Institution

Department of Electrical, Electronics, and Telecommunications Engineering and Naval Architecture, University of Genoa, Via dell´Opera Pia 13, 16145, ITALY

fYear

2015

fDate

8-12 June 2015

Firstpage

7030

Lastpage

7035

Abstract

In this paper, an Android SPEech proCessing plaTform as smaRtphone Application (SPECTRA) is presented. Such application, developed by the authors, has three main functions: i) Gender Recognition (GR), ii) Speaker Recognition (SR) and iii) Language Recognition (LR). All these recognition functions are performed simultaneously by using unsupervised Support Vector Machine (SVM) classifiers. An innovative point of this paper lies in the automatic re-training of the employed SVMs which are able to dynamically update themselves when a (new) audio from a (new) speaker is provided. This allow to build more robust classifiers, which results in better recognition performances. In terms of accuracy, the GR reaches about 98% of correct classifications, SR performs around 80% while LR shows an accuracy of about 74%.

Keywords

Accuracy; Feature extraction; Mel frequency cepstral coefficient; Speaker recognition; Speech processing; Speech recognition; Support vector machines; Android Apps; Multimedia Applications; Smartphones; Speech Signal Processing; Support Vector Machines;

fLanguage

English

Publisher

ieee

Conference_Titel

Communications (ICC), 2015 IEEE International Conference on

Conference_Location

London, United Kingdom

Type

conf

DOI

10.1109/ICC.2015.7249447

Filename

7249447