E-LIB Suche - Ergebnisse für: Kashiwagi, Yosuke

1

Phoneme-Aware Encoding for Prefix-Tree-Based Contextual ASR:

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

Futami, Hayato ; Tsunoo, Emiru ; Kashiwagi, Yosuke... - p. 10641-10645 , 2024

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

2

Streaming Joint Speech Recognition and Disfluency Detection:

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

Futami, Hayato ; Tsunoo, Emiru ; Shibata, Kentaro... - p. 1-5 , 2023

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

3

E-Branchformer-Based E2E SLU Toward Stop on-Device Challeng:

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

Kashiwagi, Yosuke ; Arora, Siddhant ; Futami, Hayato... - p. 1-2 , 2023

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

4

The Pipeline System of ASR and NLU with MLM-based data Augm..:

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

Futami, Hayato ; Huynh, Jessica ; Arora, Siddhant... - p. 1-2 , 2023

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

5

A Study on the Integration of Pipeline and E2E SLU Systems ..:

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

Arora, Siddhant ; Futami, Hayato ; Wu, Shih-Lun... - p. 1-2 , 2023

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

6

Run-and-Back Stitch Search: Novel Block Synchronous Decodin..:

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

Tsunoo, Emiru ; Narisetty, Chaitanya ; Hentschel, Michael.. - p. 8287-8291 , 2022

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

7

Joint Speech Recognition and Audio Captioning:

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

Narisetty, Chaitanya ; Tsunoo, Emiru ; Chang, Xuankai... - p. 7892-7896 , 2022

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

8

Improving Character Error Rate is Not Equal to Having Clean..:

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

Sawata, Ryosuke ; Kashiwagi, Yosuke ; Takahashi, Shusuke - p. 991-995 , 2022

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

9

Gaussian Kernelized Self-Attention for Long Sequence Data a..:

, In: ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP),

Kashiwagi, Yosuke ; Tsunoo, Emiru ; Watanabe, Shinji - p. 6214-6218 , 2021

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

10

Transformer ASR with Contextual Block Processing:

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

Tsunoo, Emiru ; Kashiwagi, Yosuke ; Kumakura, Toshiyuki. - p. 427-433 , 2019

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

11

Tensor decomposition for minimization of E2E SLU model towa..:

Kashiwagi, Yosuke ; Arora, Siddhant ; Futami, Hayato...
http://arxiv.org/abs/2306.01247. , 2023

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

12

Integration of Frame- and Label-synchronous Beam Search for..:

Tsunoo, Emiru ; Futami, Hayato ; Kashiwagi, Yosuke..
http://arxiv.org/abs/2307.12767. , 2023

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

13

Integrating Pretrained ASR and LM to Perform Sequence Gener..:

Arora, Siddhant ; Futami, Hayato ; Kashiwagi, Yosuke...
http://arxiv.org/abs/2307.11005. , 2023

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

14

The Pipeline System of ASR and NLU with MLM-based Data Augm..:

Futami, Hayato ; Huynh, Jessica ; Arora, Siddhant...
http://arxiv.org/abs/2305.01194. , 2023

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

15

Phoneme-aware Encoding for Prefix-tree-based Contextual ASR:

Futami, Hayato ; Tsunoo, Emiru ; Kashiwagi, Yosuke...
http://arxiv.org/abs/2312.09582. , 2023

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