CONSTRUCTING LONG SHORT-TERM MEMORY BASED DEEP RECURRENT NEURAL NETWORKS FOR LARGE VOCABULARY SPEECH RECOGNITION | |
Li, Xiangang ; Wu, Xihong | |
2015 | |
关键词 | long short-term memory recurrent neural networks deep neural networks acoustic modeling large vocabulary speech recognition |
英文摘要 | Long short-term memory (LSTM) based acoustic modeling methods have recently been shown to give state-of-the-art performance on some speech recognition tasks. To achieve a further performance improvement, in this research, deep extensions on LSTM are investigated considering that deep hierarchical model has turned out to be more efficient than a shallow one. Motivated by previous research on constructing deep recurrent neural networks (RNNs), alternative deep LSTM architectures are proposed and empirically evaluated on a large vocabulary conversational telephone speech recognition task. Meanwhile, regarding to multi-GPU devices, the training process for LSTM networks is introduced and discussed. Experimental results demonstrate that the deep LSTM networks benefit from the depth and yield the state-of-the-art performance on this task.; CPCI-S(ISTP); lixg@cis.pku.edu.on; wxh@cis.pku.edu.on; 4520-4524 |
语种 | 英语 |
出处 | 40th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) |
内容类型 | 其他 |
源URL | [http://ir.pku.edu.cn/handle/20.500.11897/450368] |
专题 | 信息科学技术学院 |
推荐引用方式 GB/T 7714 | Li, Xiangang,Wu, Xihong. CONSTRUCTING LONG SHORT-TERM MEMORY BASED DEEP RECURRENT NEURAL NETWORKS FOR LARGE VOCABULARY SPEECH RECOGNITION. 2015-01-01. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论