已选(0)清除
条数/页: 排序方式: |
| A novel unit selection method for concatenation speech system using similarity measure 会议论文 , Gurgaon,India, Oct.25-28, 2013 作者: Zhang R(张冉); Tao JH(陶建华) ; Li Y(李雅) ; Wen ZQ(温正棋)![](/image/person.jpg)
![](/themes/default/image/downing1.png) 收藏  |  浏览/下载:60/0  |  提交时间:2020/10/27 |
| A NOVEL HYBRID MANDARIN SPEECH SYNTHESIS SYSTEM USING DIFFERENT BASE UNITS FOR MODEL TRAINING AND CONCATENATION 会议论文 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Italy, 2014 作者: Zhang, Ran; Tao, Jianhua ; Li, Ya ; Wen, Zhengqi![](/image/person.jpg)
![](/themes/default/image/downing1.png) 收藏  |  浏览/下载:87/0  |  提交时间:2020/10/27 |
| A hierarchical Viterbi algorithm for mandarin hybrid speech synthesis system 会议论文 Annual Conference of the International Speech Communication Association (INTERSPEECH), Florance, 2014 作者: Zhang, Ran; Wen, Zhengqi ; Tao, Jianhua ; Li, Ya ; Liu, Bing ; Lou, Xiaoyan; Ran Zhang
![](/themes/default/image/downing1.png) 收藏  |  浏览/下载:158/0  |  提交时间:2020/10/27 Hierarchical Viterbi Algorithm Unit Selection Hidden Markov Models Hybrid Tts Cvs Region |
| Investigating effect of rich syntactic features on Mandarin prosodic phrase boundaries prediction 会议论文 , Singapore, 12-14 Sept. 2014 作者: Che H(车浩); Wen ZQ(温正棋) ; Li Y(李雅) ; Tao JH(陶建华)![](/image/person.jpg)
![](/themes/default/image/downing1.png) 收藏  |  浏览/下载:19/0  |  提交时间:2020/10/27 |
| Context features based pre-selection and weight prediction in concatenation speech synthesis system 会议论文 , Singapore, 12-14 Sept. 2014 作者: Liu SF(刘善峰); Wen ZQ(温正棋) ; Li Y(李雅) ; Tao JH(陶建华) ; Liu B(刘斌)![](/image/person.jpg)
![](/themes/default/image/downing1.png) 收藏  |  浏览/下载:23/0  |  提交时间:2020/10/27 |
| A Novel Method of Artificial Bandwidth Extension Using Deep Architecture 会议论文 , 德国德累斯顿, 20150906-20150910 作者: Liu Bin ; Tao Jianhua ; Wen Zhengqi ; Li Ya ; Danish Bukhari
![](/themes/default/image/downing1.png) 收藏  |  浏览/下载:37/0  |  提交时间:2020/10/27 |
| Long Short Term Memory Recurrent Neural Network based Multimodal Dimensional Emotion Recognition 会议论文 Proceedings of the 5th International Workshop on Audio/Visual Emotion Challenge, Brisbane, Australia, 2015-11 作者: Linlin Chao ; Jianhua Tao ; Minghao Yang ; Ya Li ; Zhengqi Wen![](/image/person.jpg)
Adobe PDF(387Kb)  |   收藏  |  浏览/下载:38/2  |  提交时间:2020/10/27 Multimodal |
| End-to-end Keywords Spotting Based on Connectionist Temporal Classification for Mandarin 会议论文 , 天津, 2016.10 作者: Bai Y(白烨) ; Yi JY(易江燕) ; Ni H(倪浩) ; Wen ZQ(温正棋) ; Liu B(刘斌) ; Li Y(李雅) ; Tao JH(陶建华)![](/image/person.jpg)
![](/themes/default/image/downing1.png) 收藏  |  浏览/下载:57/0  |  提交时间:2020/10/27 |
| Long Short Term Memory Recurrent Neural Network based Encoding Method for Emotion Recognition in Video 会议论文 ICASSP2016, Shanghai, China, 2016-3 作者: Linlin Chao ; Jianhua Tao ; Minghao Yang ; Ya Li ; Zhengqi Wen![](/image/person.jpg)
![](/themes/default/image/downing1.png) 收藏  |  浏览/下载:74/0  |  提交时间:2020/10/27 Emotion Recognition |
| The Parameterized Phoneme Identity Feature as a Continuous Real-Valued Vector for Neural Network based Speech Synthesis 会议论文 INTERSPEECH, San Francisco,USA, Sep 8-12, 2016 作者: Wen ZQ(温正棋) ; Li Y(李雅) ; Tao JH(陶建华) ; Wen, Zhengqi![](/image/person.jpg)
![](/themes/default/image/downing1.png) 收藏  |  浏览/下载:94/0  |  提交时间:2020/10/27 Phoneme Embedded Vector Word Embedding Speech Synthesis Blstm-rnn |