基于LSTMP语音识别方法的研究与改进

Research and Improvement of Speech Recognition Method Based on LSTMP

当前LSTMP是基于LSTM增加了Projection层,并将这个层连接到LSTM的输入,通过循环连接投影层,对高维度的信息进行降维,减小细胞单元的维度,从而减小相关参数矩阵的参数数目。但LSTMP网络结构的缺点在于Projection层的输出需要完成两个功能,既需要充当历史信息,又需要作为下一层的输入。针对以上问题,笔者提出了一种Re-dimension的方法,让网络自己选择一部分参数作为历史信息,并获得了一定程度的提升。采用该方法后,能提高语音识别率相对4-5%左右。

Currently,LSTMP is based on LSTM,which adds a project layer and connects this layer to the input of LSTM. By circularly connecting the projection layer,it reduces the dimension of high-dimensional information,reduces the dimension of cell units, and thus reduces the number of parameters of the related parameter matrix. However,the disadvantage of LSTMP network structure is that the output of the Projection layer needs to complete two functions,which need to act as both historical information and input of the next layer. In view of the above problems,the author proposes a Re-dimension method,which allows the network to select some parameters as historical information,and has achieved a certain degree of improvement. With this method,the speech recognition rate can be improved by about 4-5%.