E-LIB Suche - Ergebnisse für: Deng, Keqi

1

Decoupled structure for improved adaptability of end-to-end..:

Deng, Keqi ; Woodland, Philip C.
Speech Communication. 163 (2024) - p. 103109 , 2024

2

Label-Synchronous Neural Transducer for Adaptable Online E2..:

Deng, Keqi ; Woodland, Philip C.
IEEE/ACM Transactions on Audio, Speech, and Language Processing. 32 (2024) - p. 3507-3516 , 2024

Link: https://doi.org/10.1109/..

3

FastInject: Injecting Unpaired Text Data into CTC-Based ASR..:

, In: ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP),

Deng, Keqi ; Woodland, Philip C. - p. 11836-11840 , 2024

Link: https://doi.org/10.1109/..

4

Direct 3D Bioprinting of Tough and Antifatigue Cell-Laden C..:

Liu, Qi ; Yang, Jingzhou ; Wang, Yingjie...
Biomacromolecules. 24 (2023) 6 - p. 2549-2562 , 2023

Link: https://doi.org/10.1021/..

5

Adaptable End-to-End ASR Models Using Replaceable Internal ..:

, In: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP),

Deng, Keqi ; Woodland, Philip C. - p. 1-5 , 2023

Link: https://doi.org/10.1109/..

6

Improving CTC-Based Speech Recognition Via Knowledge Transf..:

, In: ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP),

Deng, Keqi ; Cao, Songjun ; Zhang, Yike... - p. 8517-8521 , 2022

Link: https://doi.org/10.1109/..

7

Alleviating ASR Long-Tailed Problem by Decoupling the Learn..:

Deng, Keqi ; Cheng, Gaofeng ; Yang, Runyan.
IEEE/ACM Transactions on Audio, Speech, and Language Processing. 30 (2022) - p. 340-354 , 2022

Link: https://doi.org/10.1109/..

8

ETEH: Unified Attention-Based End-to-End ASR and KWS Archit..:

Cheng, Gaofeng ; Miao, Haoran ; Yang, Runyan..
IEEE/ACM Transactions on Audio, Speech, and Language Processing. 30 (2022) - p. 1360-1373 , 2022

Link: https://doi.org/10.1109/..

9

Improving Non-Autoregressive End-to-End Speech Recognition ..:

, In: ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP),

Deng, Keqi ; Yang, Zehui ; Watanabe, Shinji... - p. 8522-8526 , 2022

Link: https://doi.org/10.1109/..

10

Label-Synchronous Neural Transducer for Adaptable Online E2..:

Deng, Keqi ; Woodland, Philip C
http://arxiv.org/abs/2311.11353. , 2023

Link: http://arxiv.org/abs/231..

11

Decoupled Structure for Improved Adaptability of End-to-End..:

Deng, Keqi ; Woodland, Philip C
http://arxiv.org/abs/2308.13345. , 2023

Link: http://arxiv.org/abs/230..

12

FastInject: Injecting Unpaired Text Data into CTC-based ASR..:

Deng, Keqi ; Woodland, Philip C
http://arxiv.org/abs/2312.09100. , 2023

Link: http://arxiv.org/abs/231..

13

Label-Synchronous Neural Transducer for End-to-End ASR:

Deng, Keqi ; Woodland, Philip C
http://arxiv.org/abs/2307.03088. , 2023

Link: http://arxiv.org/abs/230..

14

Adaptable End-to-End ASR Models using Replaceable Internal ..:

Deng, Keqi ; Woodland, Philip C
http://arxiv.org/abs/2302.08579. , 2023

Link: http://arxiv.org/abs/230..

15

Improving non-autoregressive end-to-end speech recognition ..:

Deng, Keqi ; Yang, Zehui ; Watanabe, Shinji...
http://arxiv.org/abs/2201.10103. , 2022

Link: http://arxiv.org/abs/220..