已选(0)清除
条数/页: 排序方式: |
| Improving End-to-End Contextual Speech Recognition with Fine-Grained Contextual Knowledge Selection 会议论文 , Singapore, Singapore, 2022.05 作者: Minglun Han; Linhao Dong; Zhenlin Liang; Meng Cai; Shiyu Zhou; Zejun Ma; Bo Xu Adobe PDF(463Kb)  |  收藏  |  浏览/下载:219/64  |  提交时间:2023/05/29 Automatic Speech Recognition Context Biasing Speech Recognition Customization Continuous Integrate-and-Fire Mechanism |
| CIF-Based Collaborative Decoding for End-to-End Contextual Speech Recognition 会议论文 , Toronto, Canada, 2021-06-06 作者: Minglun Han; Linhao Dong; Shiyu Zhou; Bo Xu Adobe PDF(469Kb)  |  收藏  |  浏览/下载:175/60  |  提交时间:2023/05/29 Contextual Speech Recognition Automatic Speech Recognition Context Biasing |
| Sequence-level Speaker Change Detection with Difference-based Continuous Integrate-and-fire 期刊论文 Signal Processing Letters, 2022, 页码: 1551-1554 作者: Fan ZY(范志赟); Dong LH(董林昊); Cai M(蔡猛); Ma ZJ(马泽君); Xu B(徐波) Adobe PDF(404Kb)  |  收藏  |  浏览/下载:203/46  |  提交时间:2022/09/17 |
| A Comparison of Modeling Units in Sequence-to-Sequence Speech Recognition with the Transformer on Mandarin Chinese 会议论文 ICONIP, Siem Reap, Cambodia, 2018 作者: Shiyu Zhou; Linhao Dong; Shuang Xu; Bo Xu 收藏  |  浏览/下载:103/0  |  提交时间:2020/10/27 Asr Multi-head Attention Modeling Units Sequence-to-sequence Transformer |
| Syllable-Based Sequence-to-Sequence Speech Recognition with the Transformer in Mandarin Chinese 会议论文 Interspeech, 印度的海德拉巴, 2018 作者: Shiyu Zhou; Linhao Dong; Shuang Xu; Bo Xu 收藏  |  浏览/下载:118/0  |  提交时间:2020/10/27 Asr Multi-head Attention Syllable Based Acoustic Modeling Sequence-to-sequence |
| Syllable-Based Acoustic Modeling with CTC for Multi-Scenarios Mandarin speech recognition 会议论文 , Rio de Janeiro, Brazil, 8-13, July, 2018 作者: Zhao YY(赵媛媛); Linhao Dong; Shuang Xu; Bo Xu; Yuanyuan Zhao 收藏  |  浏览/下载:103/0  |  提交时间:2020/10/27 Multi-scenarios Context-independent Syllable-based Modeling Mandarin Speech Recognition Layer Normalization |
| CIF: Continuous Integrate-and-Fire for End-to-End Speech Recognition 会议论文 , 在线会议, 2020-05 作者: Dong, Linhao; Xu, Bo 浏览  |  Adobe PDF(641Kb)  |  收藏  |  浏览/下载:370/85  |  提交时间:2020/06/13 continuous integrate-and-fire end-to-end model soft and monotonic alignment online speech recognition acoustic boundary positioning |
| Self-Attention Aligner: A Latency-Control End-to-End Model for ASR using Self-attention Network and Chunk-hopping 会议论文 , Brighton, United Kingdom, 2019-05 作者: Dong, Linhao; Wang, Feng; Xu, Bo 浏览  |  Adobe PDF(930Kb)  |  收藏  |  浏览/下载:273/51  |  提交时间:2020/06/13 speech recognition self-attention network encoder-decoder end-to-end latency-control |
| Extending Recurrent Neural Aligner for Streaming End-to-End Speech Recognition in Mandarin 会议论文 , Hyderabad, India, 2018-09 作者: Dong, Linhao; Zhou, Shiyu; Chen, Wei; Xu, Bo 浏览  |  Adobe PDF(321Kb)  |  收藏  |  浏览/下载:291/89  |  提交时间:2020/06/13 speech recognition recurrent neural aligner mandarin end-to-end |
| Speech-Transformer: A No-Recurrence Sequence-to-Sequence Model for Speech Recognition 会议论文 , Calgary, Canada, 2018-04 作者: Dong, Linhao; Xu, Shuang; Xu, Bo 浏览  |  Adobe PDF(640Kb)  |  收藏  |  浏览/下载:875/495  |  提交时间:2020/06/13 speech recognition sequence-to-sequence attention transformer |