摘要
本文对神经网络语音识别中的语音特征提取、网络结构以及学习算法进行了初步的研究,提出了一种用于语音特征矢量量化的简化和改进的自组织神经网络模型VQNN. VQNN 中引入了动态规划法估计语音样本矢量的码本类中心初值并确定网络的初始权矩阵,可构造出256 个量化等级的码本矢量.该方法具有较强的鲁棒性且矢量量化过程简单迅速.对28 个地名的语音量化识别实验结果表明了这种量化方法对语音识别的有效性.
This paper investigates the speech feature extraction , the neural network structure and the learning algorithm for the neural network speech recognition, proposes a simplifing and improving self organization neural network model that is used to speech feature vector quantization VQNN. In VQNN, the dynamic programming method is introduced to estimate the initial value of the speech sample vector cluster center and to determine initial weight matrix, and the code vector that is 256 quantization degrees is built. This method possesses more robust and the vector quantization process is simple and quick. The experiment results for the speech quantization recognition of 28 place name demonstrate the efficiency of this quantization method for speech recognition.
出处
《小型微型计算机系统》
CSCD
北大核心
1999年第12期941-944,共4页
Journal of Chinese Computer Systems
基金
国家自然科学基金!(69675019)
国家863 项目!(863-306-03-06-1)
关键词
语音识别
矢量量化
神经网络
语音信号
Speech recognition Vector quantization Neural network model