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：
Hybrid Autoregressive and Non-Autoregressive Transformer Models for Speech Recognition 期刊论文
IEEE SIGNAL PROCESSING LETTERS, 2022, 页码: 762-766
作者:  Zhengkun Tian;  Jiangyan Yi;  Jianhua Tao;  Shuai Zhang;  Zhengqi Wen
Adobe PDF(934Kb)  |  收藏  |  浏览/下载：273/76  |  提交时间：2022/06/14
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：192/44  |  提交时间：2022/06/14
Self-Attention Transducers for End-to-End Speech Recognition 会议论文
, Graz, Austria, September 15–19, 2019
作者:  Zhengkun Tian;  Jiangyan Yi;  Jianhua Tao;  Ye Bai;  Zhengqi Wen
Adobe PDF(278Kb)  |  收藏  |  浏览/下载：99/38  |  提交时间：2022/06/14
One In A Hundred: Selecting the Best Predicted Sequence from Numerous Candidates for Speech Recognition 会议论文
, Tokyo, Japan, 14-17 December 2021
作者:  Zhengkun Tian;  Jiangyan Yi;  Ye Bai;  Jianhua Tao;  Shuai Zhang;  Zhengqi Wen
Adobe PDF(563Kb)  |  收藏  |  浏览/下载：174/40  |  提交时间：2022/06/14
CLMAD: A Chinese Language Model Adaptation Dataset 会议论文
, 台北, 2018
作者:  Ye Bai;  Jianhua Tao;  Jiangyan Yi;  Zhengqi Wen;  Cunhang Fan
Adobe PDF(157Kb)  |  收藏  |  浏览/下载：88/24  |  提交时间：2021/06/25
Listen Attentively, and Spell Once: Whole Sentence Generation via a Non-Autoregressive Architecture for Low-Latency Speech Recognition 会议论文
, shanghai, 2020
作者:  Ye Bai;  Jiangyan Yi;  Jianhua Tao;  Zhengkun Tian;  Zhengqi Wen;  Shuai Zhang
Adobe PDF(801Kb)  |  收藏  |  浏览/下载：123/31  |  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：189/56  |  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  
Gated Recurrent Fusion With Joint Training Framework for Robust End-to-End Speech Recognition 期刊论文
IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2021, 期号: 29, 页码: 198-209
作者:  Fan, Cunhang;  Yi, Jiangyan;  Tao, Jianhua;  Tian, Zhengkun;  Liu, Bin;  Wen, Zhengqi
Adobe PDF(2534Kb)  |  收藏  |  浏览/下载：396/50  |  提交时间：2021/03/08
Speech enhancement  Speech recognition  Training  Noise measurement  Logic gates  Acoustic distortion  Task analysis  Gated recurrent fusion  robust end-to-end speech recognition  speech distortion  speech enhancement  speech transformer  
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：144/56  |  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：240/90  |  提交时间：2020/06/27