CASIA OpenIR

Browse/Search Results:  1-10 of 17 Help

Selected(0)Clear Items/Page:    Sort:
基于深度学习的语音合成方法研究 学位论文
工学博士, 中国科学院自动化研究所: 中国科学院大学, 2019
Authors:  郑艺斌
Adobe PDF(8630Kb)  |  Favorite  |  View/Download:33/1  |  Submit date:2019/06/18
语音合成  深度学习  韵律建模  端到端声学建模  多风格建模  
DTR-GAN: Dilated Temporal Relational Adversarial Network for Video Summarization 会议论文
, Chengdu, China, 2019-5
Authors:  Yujia Zhang;  Michael Kampffmeyer;  Xiaoguang Zhao;  Min Tan
View  |  Adobe PDF(7580Kb)  |  Favorite  |  View/Download:39/6  |  Submit date:2019/05/07
Improving Deep Neural Network Based Speech Synthesis through Contextual Feature Parametrization and Multi-Task Learning 期刊论文
JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY, 2018, 卷号: 90, 期号: 7, 页码: 1025-1037
Authors:  Wen, Zhengqi;  Li, Kehuang;  Huang, Zhen;  Lee, Chin-Hui;  Tao, Jianhua;  Zhengqi Wen
View  |  Adobe PDF(995Kb)  |  Favorite  |  View/Download:82/24  |  Submit date:2018/01/05
Dnn-based Speech Synthesis  Vocoder  Speech Parametrization  Blstm  Phoneme Embedded Vector  Multi-task Learning  Pitch-scaled Spectrum  
Investigating Efficient Feature Representation Methods and Training Objective for BLSTM-Based Phone Duration Prediction 会议论文
, Stockholm, Sweden, August 20–24, 2017
Authors:  Zheng, Yibin;  Tao, Jianhua;  Wen, Zhengqi;  Li, Ya;  Liu, Bin
View  |  Adobe PDF(251Kb)  |  Favorite  |  View/Download:103/25  |  Submit date:2018/01/04
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
Authors:  Wen ZQ(温正棋);  Li Y(李雅);  Tao JH(陶建华);  Wen, Zhengqi
View  |  Adobe PDF(541Kb)  |  Favorite  |  View/Download:87/18  |  Submit date:2016/10/28
Phoneme Embedded Vector  Word Embedding  Speech Synthesis  Blstm-rnn  
First Step Towards End-to-end Parametric TTS Synthesis: Generating Spectral Parameters with Neural Attention 会议论文
, San Francisco, USA, 2016-9-8
Authors:  Wang, Wenfu;  Xu, Shuang;  Xu, Bo
View  |  Adobe PDF(191Kb)  |  Favorite  |  View/Download:95/28  |  Submit date:2018/01/03
Parametric Tts Synthesis  End-to-end  Attention Based Recurrent Neural Network  Acoustic Modeling  
模式分类中的鲁棒损失函数的设计及其在不平衡数据中的应用 学位论文
, 北京: 中国科学院大学, 2016
Authors:  徐贵标
Adobe PDF(2509Kb)  |  Favorite  |  View/Download:158/5  |  Submit date:2016/06/20
异常样本  鲁棒损失函数  不平衡数据  代价敏感学习  代价缺失学习  
自然场景文字切分和文本行识别方法研究 学位论文
, 北京: 中国科学院大学, 2016
Authors:  贺欣
Adobe PDF(2070Kb)  |  Favorite  |  View/Download:209/8  |  Submit date:2016/06/27
场景文字识别  过切分  递归神经网络  
Integration of articulatory knowledge and voicing features based on DNN/HMM for Mandarin speech recognition 会议论文
, Killamey, Ireland, July 12-17 2015
Authors:  Ying-Wei Tan;  Wen-Ju Liu;  Wei Jiang;  Hao Zheng;  Wenju Liu
View  |  Adobe PDF(234Kb)  |  Favorite  |  View/Download:40/6  |  Submit date:2018/01/04
基于变换域分析的噪声鲁棒声源定位方法研究及无人车应用 学位论文
, 中国科学院自动化研究所: 中国科学院大学, 2015
Authors:  雪巍
Adobe PDF(6711Kb)  |  Favorite  |  View/Download:358/1  |  Submit date:2015/09/02
麦克风阵列  声源定位  空间声学  变换域分析  噪声  无人驾驶汽车  Directional Of Arrival  Microphone Arrays  Spatial Audio  Transform Domain Analysis  Noise  Intelligent Vehicle