Real-time Speaker Diarization on TI OMAP3530

Author

Colagiacomo, Vito ; Principi, Emanuele ; Cifani, Simone ; Squartini, Stefano

Author_Institution

Dept. of Biomedics, Electron. & Telecommun., Polytech. Univ. of Marche, Ancona, Italy

fYear

2010

fDate

1-2 Dec. 2010

Firstpage

215

Lastpage

219

Abstract

In this paper a real-time implementation of a Speaker Diarization algorithm on TI OMAP3530 is discussed. The addressed algorithm is made of two main stages: the acoustic feature extraction and the speech activity classifier. Both of them have been implemented and run on the ARM Cortex-A8 processor of the OMAP3530 chip. Classifier training has been performed offline on a PC by using a suitable speech database (i.e. the AMI Corpus). The acoustic feature extraction process represents the bottleneck in terms of computational burden, that is why the scalability issue has been faced and code optimization (using ARM NEON architecture) adopted to make the algorithm working in real-time. Experimental results prove the effectiveness of the approach.

Keywords

feature extraction; microprocessor chips; signal classification; speaker recognition; ARM Cortex-A8 processor; ARM NEON architecture; TI OMAP3530 chip; acoustic feature extraction process; automatic speech recognition system; classifier training; code optimization; real-time speaker diarization algorithm; speech activity classifier; speech database; Crosstalk; Feature extraction; Optimization; Real time systems; Speech; Training; Vectors;

fLanguage

English

Publisher

ieee

Conference_Titel

Education and Research Conference (EDERC), 2010 4th European

Conference_Location

Nice

Print_ISBN

978-0-9552047-4-6

Type

conf

Filename

6151439