E-LIB Suche - Ergebnisse für: McDermott, Erik

1

Neural Transducer Training: Reduced Memory Consumption with..:

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

Braun, Stefan ; McDermott, Erik ; Hsiao, Roger - p. 1-5 , 2023

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

2

Variable Attention Masking for Configurable Transformer Tra..:

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

Swietojanski, Pawel ; Braun, Stefan ; Can, Dogan... - p. 1-5 , 2023

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

3

Transformer Transducer: A Streamable Speech Recognition Mod..:

, In: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP),

Zhang, Qian ; Lu, Han ; Sak, Hasim... - p. 7829-7833 , 2020

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

4

A Density Ratio Approach to Language Model Fusion in End-to..:

, In: 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU),

McDermott, Erik ; Sak, Hasim ; Variani, Ehsan - p. 434-441 , 2019

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

5

Inverting mappings from smooth paths through Rn to paths th..:

Hogden, John ; Rubin, Philip ; McDermott, Erik..
Speech Communication. 49 (2007) 5 - p. 361-383 , 2007

Link: https://doi.org/10.1016/..

6

Discriminative training via minimization of risk estimates ..:

McDermott, Erik ; Katagiri, Shigeru
Applied Intelligence. 25 (2006) 1 - p. 37-57 , 2006

Link: https://doi.org/10.1007/..

7

A derivation of minimum classification error from the theor..:

McDermott, Erik ; Katagiri, Shigeru
Computer Speech & Language. 18 (2004) 2 - p. 107-122 , 2004

Link: https://doi.org/10.1016/..

8

Prototype-based minimum error training for speech recogniti..:

McDermott, Erik ; Katagiri, Shigeru
Applied Intelligence. 4 (1994) 3 - p. 245-256 , 1994

Link: https://doi.org/10.1007/..

9

Prototype-based minimum classification error/generalized pr..:

McDermott, Erik ; Katagiri, Shigeru
Computer Speech & Language. 8 (1994) 4 - p. 351-368 , 1994

Link: https://doi.org/10.1006/..

10

Re-evaluation of LVQ-HMM hybrid algorithm:

Iwamida, Hitoshi ; Katagiri, Shigeru ; McDermott, Erik
Journal of the Acoustical Society of Japan (E). 14 (1993) 4 - p. 267-274 , 1993

Link: https://doi.org/10.1250/..

11

A hybrid speech recognition system using HMMs with an LVQ-t..:

Iwamida, Hitoshi ; Katagiri, Shigeru ; McDermott, Erik.
Journal of the Acoustical Society of Japan (E). 11 (1990) 5 - p. 277-286 , 1990

Link: https://doi.org/10.1250/..

12

Optimizing Bilingual Neural Transducer with Synthetic Code-..:

Nguyen, Thien ; Tran, Nathalie ; Deng, Liuhui...
http://arxiv.org/abs/2210.12214. , 2022

Link: http://arxiv.org/abs/221..

13

Variable Attention Masking for Configurable Transformer Tra..:

Swietojanski, Pawel ; Braun, Stefan ; Can, Dogan...
http://arxiv.org/abs/2211.01438. , 2022

Link: http://arxiv.org/abs/221..

14

Neural Transducer Training: Reduced Memory Consumption with..:

Braun, Stefan ; McDermott, Erik ; Hsiao, Roger
http://arxiv.org/abs/2211.16270. , 2022

Link: http://arxiv.org/abs/221..

15

A Density Ratio Approach to Language Model Fusion in End-To..:

McDermott, Erik ; Sak, Hasim ; Variani, Ehsan
http://arxiv.org/abs/2002.11268. , 2020

Link: http://arxiv.org/abs/200..