|
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：265/76 | 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：185/42 | 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：90/36 | 提交时间：2022/06/14 |
| Spike-Triggered Non-Autoregressive Transformer for End-to-End Speech Recognition 会议论文
, Shanghai, China, October 25–29, 2020
作者: Zhengkun Tian; Jiangyan Yi; Jianhua Tao; Ye Bai; Shuai Zhang; Zhengqi Wen
Adobe PDF(629Kb) | 收藏 | 浏览/下载：150/49 | 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：168/39 | 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：57/8 | 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：143/49 | 提交时间：2021/06/25 |
| 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：79/20 | 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：115/30 | 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：179/50 | 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 |
