K子空间和时延自相关器的英汉音素识别

提出了用于音素识别的K子空间和时延自相关器神经网络结构，用将时延设计加入线性自相关器，以扩展音素滤波神经网络的方法，产生p维子空间，并采用迭代过程修改划分，以便捕获语音信号中的时间序列信息。这种带不分类训练过程的体系结构提供了一种高识别性能的方法，没有大多数常规语音识别神经网络所常有的网络输出值不表示候选者似然性的缺陷。通过英语音素和汉语音素的初步试验，识别正确率为84.38%，比音素滤波神经网络方法好。

A neural network architecture, K-subspaces and time-delay auto-associators, is proposed for phoneme recognition. It extends the phoneme filter neural networks approach by adding linear auto-associators to create p-dimension subspace, and an iteration is employed to improve the decision. It is good to capture the time-sequence information in speech signal. The architecture proposed could provide a high recognition performance without traditional neural network’s shortcoming. Some recognition simulations for both English and Chinese phonemes are conducted, and the recognition rate is 84.38% which is better than phoneme filter neural networks approach.