基于神经元网络的高效语音压缩系统

A Highly Effective System for Speech Coding Based on Neural Network

随着现代社会的高速发展,我们正处于一个信息爆炸的社会中,高效的语音压缩系统正发挥着极其重要的作用.神经元网络(Neural Network)因其并行处理能力以及分布式存储信息和自组织自学习的特点,使其在各个领域中有着广泛的应用.本文建立在MPE-LPC语音编码器中对数面积比参数(G参数)和间接激励参数(R_(Lx)参数)的概率分布特性上,提出了一种新的综合神经网络结构-分类神经元网络(Classification NeuralNetwork-CNN),使编码器质量有了明显的提高.

Today, we are living with a informational society. Highly effective speech coding system isbecoming more and more important. Because of special characters of neural network (NN) such as parallel pro-cessing.distributed register and self-adapting capability etc, neural network has greatest potential in many area.Based on the pdf of speech parameters, a new neural network, Classification Neural Network-CNN, is presentedin the paper, and the quality for apeech coder makes improvement significantly.