QQ客服 官方微博 反馈留言

浏览/检索结果: 共7条，第1-7条 帮助 限定条件 发表日期：2015    专题：北京大学    第一署名单位    第一作者单位    通讯作者单位     已选(0)清除 条数/页：5101520253035404550556065707580859095100   排序方式：请选择作者升序作者降序题名升序题名降序发表日期升序发表日期降序提交时间升序提交时间降序 A comparative study on selecting acoustic modeling units in deep neural networks based large vocabulary Chinese speech recognition 其他 2015-01-01 Li, Xiangang; Yang, Yuning; Pang, Zaihu; Wu, Xihong 收藏  |  浏览/下载：14/0  |  提交时间：2017/12/03 Deep neural networks  Multi-task learning  Chinese automatic speech recognition  Acoustic modeling units  Syllable   Constructing long short-term memory based deep recurrent neural networks for large vocabulary speech recognition 其他 2015-01-01 Li, Xiangang; Wu, Xihong 收藏  |  浏览/下载：4/0  |  提交时间：2017/12/03 Improving long short-term memory networks using maxout units for large vocabulary speech recognition 其他 2015-01-01 Li, Xiangang; Wu, Xihong 收藏  |  浏览/下载：2/0  |  提交时间：2017/12/03 Hybrid-Indexing Multi-type Features for Large-Scale Image Search 其他 2015-01-01 Luo, Qingjun; Zhang, Shiliang; Huang, Tiejun; Gao, Wen; Tian, Qi 收藏  |  浏览/下载：3/0  |  提交时间：2017/12/03 RETRIEVAL   CONSTRUCTING LONG SHORT-TERM MEMORY BASED DEEP RECURRENT NEURAL NETWORKS FOR LARGE VOCABULARY SPEECH RECOGNITION 其他 2015-01-01 Li, Xiangang; Wu, Xihong 收藏  |  浏览/下载：4/0  |  提交时间：2017/12/03 long short-term memory  recurrent neural networks  deep neural networks  acoustic modeling  large vocabulary speech recognition   Long short-term memory based convolutional recurrent neural networks for large vocabulary speech recognition 其他 2015-01-01 Li, Xiangang; Wu, Xihong 收藏  |  浏览/下载：5/0  |  提交时间：2017/12/03 A comparative study on selecting acoustic modeling units in deep neural networks based large vocabulary Chinese speech recognition 期刊论文 International Conference on Intelligent Science and Intelligent Data Engineering (IScIDE), 2015 Li, Xiangang; Yang, Yuning; Pang, Zaihu; Wu, Xihong 收藏  |  浏览/下载：8/0  |  提交时间：2017/12/03 Deep neural networks  Multi-task learning  Chinese automatic speech recognition  Acoustic modeling units  Syllable