Using learning vector quantizers for network bandwidth optimization in the QCELP speech coder

Author

Lathia, Bhavnish ; Kim, Jung H. ; Oh, Hyunseo ; Ham, Byung W.

Author_Institution

Center for Adv. Comput. Studies, Southwestern Louisiana Univ., Lafayette, LA, USA

Volume

1

fYear

1998

fDate

4-8 May 1998

Firstpage

134

Abstract

We attempt to show how average bandwidth usage during network transmissions can be reduced using the QCELP speech coder in conjunction with learning vector quantizers (LVQ). We identify three types of noise which can occur during the process of transmission. We then identify various techniques, some natural and some mathematical, to estimate the speech content of the signal. We then use LVQ to construct decision boundaries. Our simulation results show significant reductions in average bandwidth usage without large degradation in speech quality

Keywords

noise; optimisation; self-organising feature maps; speech coding; vector quantisation; vocoders; Kohonen feature maps; QCELP speech coder; code excited linear prediction; learning vector quantizers; network bandwidth; neural nets; noises; optimization; Adaptive signal detection; Background noise; Bandwidth; Frequency domain analysis; Gaussian noise; Heuristic algorithms; Humans; Intelligent networks; Limiting; Speech enhancement;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks Proceedings, 1998. IEEE World Congress on Computational Intelligence. The 1998 IEEE International Joint Conference on

Conference_Location

Anchorage, AK

ISSN

1098-7576

Print_ISBN

0-7803-4859-1

Type

conf

DOI

10.1109/IJCNN.1998.682250

Filename

682250