神经网络法汉语孤立音识别的研究

本文对神经网络法语音识别中的网络结构、特征提取以及学习算法进行了初步的研究.文中提出了一种带非均匀窗形式的金字塔状多层神经网络模型I研究了两种特征提取方法的向量规整问题,改进了Polak—Rjbiere学习算法并证明它能够保证连结权向量不收敛到非稳定局部极小点.特定人方式的试验表明,用神经网络方法识别五个元音和十个数字时,识别率都高于99.0％.用遍布25个省市的90个说话者的数字话音所进行的非特定人方式试验表明;加窗后识别率可以提高1.0％,达到90.3％,说明带预处理窗的模型更加适合于语音识别.

Study on the Recognitions of Isolated Chinese Syllables by Neural Nets

The neural net model, the feature extraction and the learning algorithm for the speech recognition by neural nets are investigated in this paper. A non-uniformly windowed pyramidical architecture is proposed, the normalizations of the feature vectors of two extraction algorithms are investgated and the Polak-Ribiere learning algorithm is modified to guarantee the weight vector not to converge to non-stable local minima. Speaker-dependent experments show that over 99% accuracy can be achieved for recognizing five vowels and ten digits. Speaker-independent experiments involved 90 speakers from 25 provinces of China show that 90.3% accuracy can be obtained for the digit recognition, and the performance can be increased by 1.0% after the pre-processing window is employed. The windowed model is more applicable for speech recognitions.