中文版 | English

在结果中检索

CASIA OpenIR
（本次检索基于用户作品认领结果）

浏览/检索结果: 共13条，第1-10条 帮助

限定条件        
已选(0)清除 条数/页：   排序方式：
FSR: Accelerating the Inference Process of Transducer-Based Models by Applying Fast-Skip Regularization 会议论文
, Brno, Czechia, 30 August – 3 September
作者:  Zhengkun Tian;  Jiangyan Yi;  Ye Bai;  Jianhua Tao;  Shuai Zhang;  Zhengqi Wen
Adobe PDF(839Kb)  |  收藏  |  浏览/下载：175/39  |  提交时间：2022/06/14
Learn Spelling from Teachers: Transferring Knowledge from Language Models to Sequence-to-Sequence Speech Recognition 会议论文
, Graz, 2019
作者:  Ye Bai;  Jiangyan Yi;  Jianhua Tao;  Zhengkun Tian;  Zhengqi Wen
Adobe PDF(779Kb)  |  收藏  |  浏览/下载：55/7  |  提交时间：2021/06/25
A Time Delay Neural Network with Shared Weight Self-Attention for Small-Footprint Keyword Spotting 会议论文
, graz, 2019
作者:  Ye Bai;  Jiangyan Yi;  Zhengqi Wen;  Zhengkun Tian;  Chenghao Zhao;  Cunhang Fan
Adobe PDF(290Kb)  |  收藏  |  浏览/下载：127/45  |  提交时间：2021/06/25
Fast End-to-End Speech Recognition via Non-Autoregressive Models and Cross-Modal Knowledge Transferring from BERT 期刊论文
IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2021, 期号: 29, 页码: 1897 - 1911
作者:  Ye Bai;  Jiangyan Yi;  Jianhua Tao;  Zhengkun Tian;  Zhengqi Wen;  Shuai Zhang
Adobe PDF(1163Kb)  |  收藏  |  浏览/下载：173/48  |  提交时间：2021/06/25
端到端语音识别、迁移学习、知识蒸馏、老师-学生学习、BERT、非自回归语音识别  
Amplitude spectrum based excitation model for HMM-based speech synthesis 会议论文
Annual Conference of the International Speech Communication Association (INTERSPEECH), 美国, 2012
作者:  Wen, Zhengqi;  Tao, Jianhua;  Zhengqi Wen
收藏  |  浏览/下载：19/0  |  提交时间：2020/10/27
Speech Synthesis  Hmm-based Speech Synthesis  Excitation Model  Amplitude Spectrum  
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
收藏  |  浏览/下载：127/0  |  提交时间：2020/10/27
Hierarchical Viterbi Algorithm  Unit Selection  Hidden Markov Models  Hybrid Tts  Cvs Region  
Pitch-Scaled Spectrum Based Excitation Model for HMM-based Speech Synthesis 期刊论文
JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY, 2014, 卷号: 74, 期号: 3, 页码: 423-435
作者:  Wen, Zhengqi;  Tao, Jianhua;  Pan, Shifeng;  Wang, Yang;  Zhengqi Wen
收藏  |  浏览/下载：15/0  |  提交时间：2020/10/27
Speech Synthesis  Hmm-based Speech Synthesis  Parametric Representation Of Speech  Excitation Model  Pitch-scaled Spectrum  
Adversarial Multilingual Training for Low-Resource Speech Recognition 会议论文
, Calgary, AB, Canada, 2018.04.15-2018.04.20
作者:  Jiangyan Yi;  Jianhua Tao;  Zhengqi Wen;  Ye Bai
浏览  |  Adobe PDF(1343Kb)  |  收藏  |  浏览/下载：31/14  |  提交时间：2020/10/22
CTC Regularized Model Adaptation for Improving LSTM RNN Based Multi-Accent Mandarin Speech Recognition 期刊论文
JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY, 2018, 卷号: 90, 期号: 7, 页码: 985-997
作者:  Jiangyan Yi;  Zhengqi Wen;  Jianhua Tao;  Hao Ni;  Bin Liu
浏览  |  Adobe PDF(1416Kb)  |  收藏  |  浏览/下载：124/50  |  提交时间：2020/10/22
multi-accent, Mandarin speech recognition,LSTM-RNN-CTC, model adaptation, CTC regularization  
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：213/80  |  提交时间：2020/06/27