Name
Abstract | ||
|---|---|---|
Attention-based methods and Connectionist Temporal Classification (CTC) network have been promising research directions for end-to-end (E2E) Automatic Speech Recognition (ASR). The joint CTC/Attention model has achieved great success by utilizing both architectures during multi-task training and joint decoding. In this article, we present a multi-stream framework based on joint CTC/Attention E2E A... |
Year | DOI | Venue |
|---|---|---|
2020 | 10.1109/TASLP.2019.2959721 | IEEE/ACM Transactions on Audio, Speech, and Language Processing |
Keywords | Field | DocType |
Decoding,Speech recognition,Acoustics,Computational modeling,Microphone arrays,Task analysis | Computer science,End-to-end principle,Word error rate,Speech recognition,Robustness (computer science),Encoder,Decoding methods,Microphone,Connectionism,Test set | Journal |
Volume | Issue | ISSN |
28 | 1 | 2329-9290 |
Citations | PageRank | References |
1 | 0.35 | 12 |
Authors | ||
6 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| ruizhi li | 1 | 51 | 12.01 |
| Xiaofei Wang | 2 | 13 | 4.99 |
| Sri Harish Reddy Mallidi | 3 | 48 | 7.94 |
| Shinji Watanabe | 4 | 1158 | 139.38 |
| Takaaki Hori | 5 | 408 | 45.58 |
| Hynek Hermansky | 6 | 3298 | 510.27 |