Using neural networks for vector quantization in low rate speech coders

Authors:
Jes Thyssen;Steffen Duus Hansen
Affiliations:
Telecommunications Research Laboratory, Hørsholm, Denmark;Electronics Institute, Technical University of Denmark, Lyngby, Denmark
Venue:
ICASSP'93 Proceedings of the 1993 IEEE international conference on Acoustics, speech, and signal processing: speech processing - Volume II
Year:
1993

Citing 4
Cited 0

Self-organization and associative memory: 3rd edition

Self-organization and associative memory: 3rd edition
Vector quantization and signal compression

Vector quantization and signal compression
Structure Level Adaptation for Artificial Neural Networks

Structure Level Adaptation for Artificial Neural Networks
Efficient vector quantization of LPC parameters at 24 bits/frame

ICASSP '91 Proceedings of the Acoustics, Speech, and Signal Processing, 1991. ICASSP-91., 1991 International Conference

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we address the problem of reducing the complexity of the codebook search in low rate speech coders. The paper focuses on vector quantization of the short term parameters (spectral parameters) where the increasing demand for higher performance necessitates codebook sizes of approximately 220. As full-search is unpractical a new path search algorithm is proposed. It is based on a multidimensional version of Kohonen's self-organizing feature map, utilizing the ordering aspects of the map. A comparison with the well-known full-search LBG algorithm shows a substantial reduction in search complexity with only a minor degradation in speech quality.