纺织高校基础科学学报2018，Vol.31Issue(1)：103-107,114,6.DOI:10.13338/j.issn.1006-8341.2018.01.017
基于混合DBNN-BLSTM模型的大词汇量连续语音识别
Large vocabulary continuous speech recognition based on deep belief neural networks and bidirectional long-short term memory hybrid
摘要
Abstract
The recognition rate is not ideal when the feature extraction is performed on the deep confidence neural network(DBNN)model and the bidirectional long-short term memory (BLSTM),the long-short term memory(LSTM)and BLSTM can better analyze the character-istics of speech data.By combining the DBNN model with BLSTM,a new acoustic modeling method for large vocabulary continuous speech recognition(LVCSR)is proposed and experi-mentally studied based on Keras deep learning framework.The experimental results show that the improved DBNN-BLSTM model has a high recognition accuracy,and the speech recognition rate is 5% higher than that of BLSTM.关键词
大词汇量/语音识别/深度置信神经网络/双向长短时记忆模型Key words
large vocabulary/speech recognition/DBNN/BLSTM分类
信息技术与安全科学引用本文复制引用
李云红,王成,王延年..基于混合DBNN-BLSTM模型的大词汇量连续语音识别[J].纺织高校基础科学学报,2018,31(1):103-107,114,6.基金项目
陕西省科技工业攻关项目(2016GY-047) （2016GY-047）
陕西省科技厅自然科学基础研究重点项目(2016JZ026) （2016JZ026）
