Journal
2020 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING
Volume -, Issue -, Pages 6084-6088Publisher
IEEE
DOI: 10.1109/icassp40776.2020.9053165
Keywords
Transformer; end-to-end speech recognition; online speech recognition; CTC/attention speech recognition
Categories
Funding
- National Key Research and Development Program [2018YFC0823402, 2018YFC0823401, 2018YFC0823405, 2018YFC0823400]
- National Natural Science Foundation of China [11590774, 11590772, 11590770]
- Key Science and Technology Project of the Xinjiang Uygur Autonomous Region
Ask authors/readers for more resources
Recently, Transformer has gained success in automatic speech recognition (ASR) field. However, it is challenging to deploy a Transformer-based end-to-end (E2E) model for online speech recognition. In this paper, we propose the Transformer-based online CTC/attention E2E ASR architecture, which contains the chunk self-attention encoder (chunk-SAE) and the monotonic truncated attention (MTA) based self-attention decoder (SAD). Firstly, the chunk-SAE splits the speech into isolated chunks. To reduce the computational cost and improve the performance, we propose the state reuse chunk-SAE. Sencondly, the MTA based SAD truncates the speech features monotonically and performs attention on the truncated features. To support the online recognition, we integrate the state reuse chunk-SAE and the MTA based SAD into online CTC/attention architecture. We evaluate the proposed online models on the HKUST Mandarin ASR benchmark and achieve a 23:66% character error rate (CER) with a 320 ms latency. Our online model yields as little as 0:19% absolute CER degradation compared with the offline baseline, and achieves significant improvement over our prior work on Long Short-Term Memory (LSTM) based online E2E models.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available