Robust voice activity detection for DTX operation of speech coders

Author

Basbug, Filiz ; Nandkumar, S. ; Swaminathan, Karthik

Author_Institution

Hughes Network Syst. Inc., Germantown, MD, USA

fYear

1999

fDate

1999

Firstpage

58

Lastpage

60

Abstract

Robust detection of voice activity for short-term speech frames is essential for discontinuous transmission (DTX) mode of operation of vocoders such as IS-641. A reference VAD for the IS-641 coder has been chosen for such a purpose and is based on the GSM-EFR (enhance full rate) VAD. We show by developing a comprehensive evaluation procedure that the reference VAD is sensitive to speech level variations. For example, a significant increase is seen in frames falsely classified as active at speech levels of 10 dB above or below nominal level. We propose a solution based on automatic gain control to reduce level sensitivity. Objective performance measures confirm the robustness of our proposed VAD

Keywords

acoustic signal detection; automatic gain control; speech coding; vocoders; DTX operation; GSM-EFR VAD; IS-641 coder; automatic gain control; discontinuous transmission mode; enhance full rate; objective performance measures; robust detection; sensitivity reduction; short-term speech frames; speech coders; speech level variations; vocoders; voice activity detection; Base stations; Battery charge measurement; GSM; Gain control; Robust control; Robustness; Speech analysis; Speech enhancement; Statistics; Vocoders;

fLanguage

English

Publisher

ieee

Conference_Titel

Speech Coding Proceedings, 1999 IEEE Workshop on

Conference_Location

Porvoo

Print_ISBN

0-7803-5651-9

Type

conf

DOI

10.1109/SCFT.1999.781483

Filename

781483