| Paper ID | SPE-14.4 |
| Paper Title |
AN ASYNCHRONOUS WFST-BASED DECODER FOR AUTOMATIC SPEECH RECOGNITION |
| Authors |
Hang Lv, Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, China and Center of Language and Speech Processing, Johns Hopkins University, United States; Zhehuai Chen, Center of Language and Speech Processing at Johns Hopkins University, USA; SpeechLab, Departement of Computer Science and Engineering, Shanghai Jiao Tong University, China; Hainan Xu, Center for Language Speech Processing at Johns Hopkins University, United States; Daniel Povey, Xiaomi Corporation, United Kingdom; Lei Xie, Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, China; Sanjeev Khudanpur, Center for Language Speech Processing at Johns Hopkins University and Human Language Technology Center of Excellence at Johns Hopkins University, United States |
| Session | SPE-14: Speech Recognition 6: New Algorithms for Sparsity/Efficiency |
| Location | Gather.Town |
| Session Time: | Wednesday, 09 June, 13:00 - 13:45 |
| Presentation Time: | Wednesday, 09 June, 13:00 - 13:45 |
| Presentation |
Poster
|
| Topic |
Speech Processing: [SPE-GASR] General Topics in Speech Recognition |
| IEEE Xplore Open Preview |
Click here to view in IEEE Xplore |
| Virtual Presentation |
Click here to watch in the Virtual Conference |
| Abstract |
We introduce asynchronous dynamic decoder, which adopts an efficient A* algorithm to incorporate big language models in the one-pass decoding for large vocabulary continuous speech recognition. Unlike standard one-pass decoding with on-the-fly composition decoder which might induce a significant computation overhead, the asynchronous dynamic decoder has a novel design where it has two fronts, with one performing ''exploration'' and the other ''backfill''. The computation of the two fronts alternates in the decoding process, resulting in more effective pruning than the standard one-pass decoding with an on-the-fly composition decoder. Experiments show that the proposed decoder works notably faster than the standard one-pass decoding with on-the-fly composition decoder, while the acceleration will be more obvious with the increment of data complexity. |
