Comparison of non-uniform optimal quantizer designs for speech coding with adaptive critics and particle swarm

Author

Zha, Wenwei ; Venayagamoorthy, Ganesh K.

Author_Institution

Dept. of Electr. & Comput. Eng., Missouri Univ., Rolla, MO, USA

Volume

1

fYear

2005

fDate

2-6 Oct. 2005

Firstpage

674

Abstract

This paper presents the design of a companding non-uniform optimal scalar quantizer for speech coding. The quantizer is designed using two neural networks to perform the nonlinear transformation. These neural networks are used in the front and back ends of a uniform quantizer. Two approaches are presented in this paper namely adaptive critic designs (ACD) and particle swarm optimization (PSO), aiming to maximize the signal to noise ratio (SNR). The comparison of these optimal quantizer designs over bit rate range of 3 to 6 is presented. The perceptual quality of the coding is evaluated by the International Telecommunication Union´s Perceptual Evaluation of Speech Quality (PESQ) standard.

Keywords

adaptive codes; hearing; neural nets; particle swarm optimisation; quantisation (signal); speech coding; transform coding; International Telecommunication Unions Perceptual Evaluation; PSO; SNR; Speech Quality standard; adaptive critic design; neural network; nonlinear transformation; nonuniform optimal scalar quantizer; particle swarm optimization; perceptual quality; signal to noise ratio; speech coding; Bit rate; Humans; Neural networks; Particle swarm optimization; Quantization; Signal resolution; Signal to noise ratio; Speech analysis; Speech coding; Telecommunication standards;

fLanguage

English

Publisher

ieee

Conference_Titel

Industry Applications Conference, 2005. Fourtieth IAS Annual Meeting. Conference Record of the 2005

ISSN

0197-2618

Print_ISBN

0-7803-9208-6

Type

conf

DOI

10.1109/IAS.2005.1518380

Filename

1518380