Mutually-Constrained Monotonic Multihead Attention for Online Asr

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 49
  • Download : 0
Despite the feature of real-time decoding, Monotonic Multihead Attention (MMA) shows comparable performance to the state-of-the-art offline methods in machine translation and automatic speech recognition (ASR) tasks. However, the latency of MMAis still a major issue in ASR and should be combined with a technique that can reduce the test latency at inference time, such as head-synchronous beam search decoding, which forces all non-activated heads to activate after a small fixed delay from the first head activation. In this paper, we remove the discrepancy between training and test phases by considering, in the training of MMA, the interactions across multiple heads that will occur in the test time. Specifically, we derive the expected alignments from monotonic attention by considering the boundaries of other heads and reflect them in the learning process.We validate our proposed method on the two standard benchmark datasets for ASR and show that our approach, MMA with the mutually-constrained heads from the training stage, provides better performance than baselines. ©2021 IEEE.
Publisher
Institute of Electrical and Electronics Engineers Inc.
Issue Date
2021-06
Language
English
Citation

2021 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2021, pp.6508 - 6512

ISSN
1520-6149
DOI
10.1109/ICASSP39728.2021.9413862
URI
http://hdl.handle.net/10203/288789
Appears in Collection
RIMS Conference Papers
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0