CASIA OpenIR
(本次检索基于用户作品认领结果)

浏览/检索结果: 共32条,第1-10条 帮助

限定条件        
已选(0)清除 条数/页:   排序方式:
VLP2MSA: Expanding vision-language pre-training to multimodal sentiment analysis 期刊论文
KNOWLEDGE-BASED SYSTEMS, 2024, 卷号: 283, 页码: 9
作者:  Yi, Guofeng;  Fan, Cunhang;  Zhu, Kang;  Lv, Zhao;  Liang, Shan;  Wen, Zhengqi;  Pei, Guanxiong;  Li, Taihao;  Tao, Jianhua
收藏  |  浏览/下载:47/0  |  提交时间:2024/02/22
Multimodal sentiment analysis  Vision-language  Multimodal fusion  
Exploiting the directional coherence function for multichannel source extraction 期刊论文
SPEECH COMMUNICATION, 2021, 卷号: 128, 页码: 1-14
作者:  Liang, Shan;  Li, Guanjun;  Nie, Shuai;  Yang, ZhanLei;  Liu, WenJu;  Tao, Jianhua
收藏  |  浏览/下载:183/0  |  提交时间:2021/05/06
Directional coherence function  Coherent-to-Diffuse Ratio  General sidelobe canceller  Desired Speech Presence Probability  
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
作者:  Wen, Zhengqi;  Li, Kehuang;  Huang, Zhen;  Lee, Chin-Hui;  Tao, Jianhua;  Zhengqi Wen
收藏  |  浏览/下载:87/0  |  提交时间:2020/10/27
Dnn-based Speech Synthesis  Vocoder  Speech Parametrization  Blstm  Phoneme Embedded Vector  Multi-task Learning  Pitch-scaled Spectrum  
Investigating Deep Neural Network Adaptation for Generating Exclamatory and Interrogative Speech in Mandarin 期刊论文
JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY, 2018, 卷号: 90, 期号: 7, 页码: 1039-1052
作者:  Zheng, Yibin;  Li, Ya;  Wen, Zhengqi;  Liu, Bin;  Tao, Jianhua;  Jianhua Tao
收藏  |  浏览/下载:100/0  |  提交时间:2020/10/27
Speech Synthesis  Excitation Parameters  Deep Neural Network Adaptation  Exclamatory Speech  Interrogative Speech  
基于静音时长和文本特征融合的韵律边界自动标注 期刊论文
清华大学学报(自然科学版), 2018, 卷号: 58, 期号: 1, 页码: 61-66,74
作者:  傅睿博;  陶建华;  李雅;  温正棋
浏览  |  Adobe PDF(1160Kb)  |  收藏  |  浏览/下载:277/103  |  提交时间:2020/06/21
韵律边界标注  决策融合  静音时长  语料库构建  语音合成  
基于静音时长和文本特征融合的韵律边界自动标注 会议论文
, 江苏连云港, 2017-10
作者:  傅睿博;  李雅;  温正棋;  陶建华
浏览  |  Adobe PDF(877Kb)  |  收藏  |  浏览/下载:217/80  |  提交时间:2020/06/27
Continuous multimodal emotion prediction based on long short term memory recurrent neural network 会议论文
, Mountain View, CA, USA, 2017.10.23-2017.10.27
作者:  Huang, Jian;  Li, Ya;  Tao, Jianhua;  Lian, Zheng;  Wen, Zhengqi;  Yang, Minghao;  Yi, Jianyan
浏览  |  Adobe PDF(1063Kb)  |  收藏  |  浏览/下载:226/60  |  提交时间:2020/06/20
基于注意力的端到端韵律结构和重音联合预测方法 会议论文
, 中国连云港, 2017 年10 月
作者:  郑艺斌;  陶建华;  李雅;  温正棋;  刘斌
收藏  |  浏览/下载:45/0  |  提交时间:2020/10/27
Investigating Efficient Feature Representation Methods and Training Objective for BLSTM-Based Phone Duration Prediction 会议论文
, Stockholm, Sweden, August 20–24, 2017
作者:  Zheng, Yibin;  Tao, Jianhua;  Wen, Zhengqi;  Li, Ya;  Liu, Bin
收藏  |  浏览/下载:37/0  |  提交时间:2020/10/27
The NLPR Speech Synthesis entry for Blizzard Challenge 2017 会议论文
, Stockholm, Sweden, 2017.8.25
作者:  Jianhua Tao;  Ruibo Fu;  Yibin Zheng;  Zhengqi Wen;  Ya Li;  Biu Liu
收藏  |  浏览/下载:67/0  |  提交时间:2020/10/27