Stability of a voice activity detector based on source separation

Author

Doukas, Nikos ; Stathaki, Tania ; Naylor, Patrick

Author_Institution

Dept. of Electr. Eng., Imperial Coll. of Sci., Technol. & Med., London, UK

Volume

2

fYear

1997

fDate

2-4 Jul 1997

Firstpage

749

Abstract

Source separation techniques been applied to the problem of voice activity detection (VAD) and a method has been developed which is able to perform well in very adverse. Environments (-5 to -10 dB). The optimisation procedure is totally iterative and therefore suitable for use in real-time, dynamically adapting situations. Stability considerations are addressed in this paper and simulation results are given. These show the new technique to be very robust to high levels of additive noise, with a relatively low complexity

Keywords

iterative methods; optimisation; signal detection; speech enhancement; stability; white noise; additive noise; car noise; dynamically adapting situations; iterative method; low complexity; optimisation procedure; real-time situations; signal enhancement; simulation results; source separation; speech processing; voice activity detector stability; white noise; Detectors; Educational institutions; Noise level; Noise robustness; Signal processing; Signal to noise ratio; Source separation; Speech enhancement; Stability; Symmetric matrices;

fLanguage

English

Publisher

ieee

Conference_Titel

Digital Signal Processing Proceedings, 1997. DSP 97., 1997 13th International Conference on

Conference_Location

Santorini

Print_ISBN

0-7803-4137-6

Type

conf

DOI

10.1109/ICDSP.1997.628460

Filename

628460