Quantization is a crucial link in the process of digital speech communication. Non-uniform quantizer such as the logarithm quantizers are commonly used in practice. In this paper, a companding non-uniform quantizer is designed using two neural networks to perform the nonlinear transformation. Particle swarm optimization is applied to find the weights of neural networks such that the signal to noise ratio (SNR) is maximized. Simulation results on different speech samples are presented and the proposed quantizer design is compared with the logarithm quantizer for bit rates ranging from 3 to 8.
W. Zha and G. K. Venayagamoorthy, "Neural Networks Based Non-Uniform Scalar Quantizer Design with Particle Swarm Optimization," Proceedings 2005 IEEE Swarm Intelligence Symposium, 2005. SIS 2005, Institute of Electrical and Electronics Engineers (IEEE), Jan 2005.
The definitive version is available at https://doi.org/10.1109/SIS.2005.1501614
2005 IEEE Swarm Intelligence Symposium, 2005. SIS 2005
Electrical and Computer Engineering
Keywords and Phrases
Digital Speech Communication; Learning (Artificial Intelligence); Logarithm Quantizer; Neural Nets; Neural Network; Nonlinear Transformation; Nonuniform Scalar Quantizer Design; Particle Swarm Optimisation; Particle Swarm Optimization; Quantisation (Signal); Signal to Noise Ratio; Speech Coding
Article - Conference proceedings
© 2005 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.