|
Selected(0)Clear
Items/Page: Sort: |
| 基于自注意力机制的流式端到端语音识别方法研究 学位论文
, 中国 北京: 中国科学院自动化研究所, 2022
Authors: 田正坤
 Adobe PDF(8871Kb) |  Favorite | View/Download：122/13 | Submit date：2022/06/13
请输入关键词 |
| Hybrid Autoregressive and Non-Autoregressive Transformer Models for Speech Recognition 期刊论文
IEEE SIGNAL PROCESSING LETTERS, 2022, 页码: 762-766
Authors: Zhengkun Tian; Jiangyan Yi; Jianhua Tao; Shuai Zhang; Zhengqi Wen
 Adobe PDF(934Kb) | Favorite | View/Download：79/11 | Submit date：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
Authors: Zhengkun Tian; Jiangyan Yi; Ye Bai; Jianhua Tao; Shuai Zhang; Zhengqi Wen
Adobe PDF(563Kb) | Favorite | View/Download：56/7 | Submit date：2022/06/14 |
| Continual Learning for Fake Audio Detection 会议论文
, 线上（捷克）, 2021-9
Authors: Ma Haoxin; Yi Jiangyan; Tao Jianhua; Bai Ye; Tian Zhengkun; Wang Chenglong
Adobe PDF(2113Kb) | Favorite | View/Download：81/18 | Submit date：2022/06/20
fake audio detection continual learning detecting fake without forgetting |
| A Large-Scale Chinese Multimodal NER Dataset with Speech Clues 会议论文
, Online, 2021-8
Authors: Sui DB(隋典伯); Zhengkun Tian; Yubo Chen; Kang Liu; Jun Zhao
Adobe PDF(749Kb) | Favorite | View/Download：56/5 | Submit date：2022/06/28 |
| FSR: Accelerating the Inference Process of Transducer-Based Models by Applying Fast-Skip Regularization 会议论文
, Brno, Czechia, 30 August – 3 September
Authors: Zhengkun Tian; Jiangyan Yi; Ye Bai; Jianhua Tao; Shuai Zhang; Zhengqi Wen
Adobe PDF(839Kb) | Favorite | View/Download：53/4 | Submit date：2022/06/14 |
| Integrating Knowledge Into End-to-End Speech Recognition From External Text-Only Data 期刊论文
IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2021, 卷号: 29, 页码: 1340-1351
Authors: Bai, Ye; Yi, Jiangyan; Tao, Jianhua; Wen, Zhengqi; Tian, Zhengkun; Zhang, Shuai
Favorite | View/Download：54/0 | Submit date：2021/06/07
End-to-End language modeling speech recognition teacher-student learning transfer learning |
| 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
Authors: Ye Bai; Jiangyan Yi; Jianhua Tao; Zhengkun Tian; Zhengqi Wen; Shuai Zhang
Adobe PDF(1163Kb) | Favorite | View/Download：81/11 | Submit date：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
Authors: Fan, Cunhang; Yi, Jiangyan; Tao, Jianhua; Tian, Zhengkun; Liu, Bin; Wen, Zhengqi
Adobe PDF(2534Kb) | Favorite | View/Download：137/12 | Submit date：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 |
| Spike-Triggered Non-Autoregressive Transformer for End-to-End Speech Recognition 会议论文
, Shanghai, China, October 25–29, 2020
Authors: Zhengkun Tian; Jiangyan Yi; Jianhua Tao; Ye Bai; Shuai Zhang; Zhengqi Wen
Adobe PDF(629Kb) | Favorite | View/Download：46/4 | Submit date：2022/06/14 |
