Applying Batch Normalization to Hybrid NN-HMM Model For Speech Recognition

摘要：

　　Batch Normalization has showed success in image classification and other image processing areas by reducing internal covariate shift in deep network models training procedure.In this paper,we propose to apply batch normalization to speech recognition within the hybrid NNHMM model.We evaluate the performance of this new method in the acoustic model of the hybrid system with a speaker-independent speech recognition task using some Chinese datasets.Compared to the former best model we used in the Chinese datasets,it shows that with batch normalization we can reach lower word error rate(WER)of 8%-13%relatively,meanwhile we just need 60% iterations of original model to finish the training procedure.

作者: Hongjian Zhan Guilin Chen Yue Lu

作者单位: Shanghai Key Laboratory of Multidimensional Information Processing,Department of Computer Science an Shanghai Youngtone Technology Co.,Ltd,Shanghai,China

会议类型: 国际会议

会议名称: 第七届全国模式识别学术会议(The 7th Chinese Conference on Pattern Recognition,CCPR2016)

会议地点: 成都

会议语种:英文

页码: 427-435

在线出版日期: 2016-11-03（万方平台首次上网日期，不代表论文的发表时间）