A parallel model combination scheme with improved delta parameter compensation

Author

Ning, Geng-xin ; Leung, Shu-hung ; Chu, Kam-keung ; Gang Welt

Author_Institution

Sch. of Electron. & Inf. Eng., South China Univ. of Technol.

fYear

2006

fDate

21-24 May 2006

Abstract

Parallel model combination (PMC) techniques have been successfully and popularly used in noisy speech recognition. Previous PMC methods such as the log-normal PMC and the log-add PMC generally use approximate compensation for delta parameters. In this paper we propose a PMC scheme with improved delta parameter compensation (PMC-IDC), which employs the log-normal PMC method for the static distribution compensation and a new delta parameter compensation. By using this new PMC-IDC scheme, improvement over the other PMC methods can be obtained in different additive noises at the expense of slight increase in computational complexity

Keywords

computational complexity; noise abatement; speech recognition; additive noises; approximate compensation; computational complexity; delta parameter compensation; log-add PMC; log-normal PMC; noisy speech recognition; parallel model combination scheme; static distribution compensation; Additive noise; Background noise; Cepstral analysis; Computational complexity; Degradation; Electronic mail; Hidden Markov models; Signal to noise ratio; Speech enhancement; Speech recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Circuits and Systems, 2006. ISCAS 2006. Proceedings. 2006 IEEE International Symposium on

Conference_Location

Island of Kos

Print_ISBN

0-7803-9389-9

Type

conf

DOI

10.1109/ISCAS.2006.1693888

Filename

1693888