Fluent and Low-latency Simultaneous Speech-to-Speech Translation with Self-adaptive Training

Renjie Zheng, Mingbo Ma, Baigong Zheng, Kaibo Liu, Jiahong Yuan, Kenneth Church, Liang Huang


Abstract
Simultaneous speech-to-speech translation is an extremely challenging but widely useful scenario that aims to generate target-language speech only a few seconds behind the source-language speech. In addition, we have to continuously translate a speech of multiple sentences, but all recent solutions merely focus on the single-sentence scenario. As a result, current approaches will accumulate more and more latencies in later sentences when the speaker talks faster and introduce unnatural pauses into translated speech when the speaker talks slower. To overcome these issues, we propose Self-Adaptive Translation which flexibly adjusts the length of translations to accommodate different source speech rates. At similar levels of translation quality (as measured by BLEU), our method generates more fluent target speech latency than the baseline, in both Zh<->En directions.
Anthology ID:
2020.findings-emnlp.349
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2020
Month:
November
Year:
2020
Address:
Online
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3928–3937
Language:
URL:
https://aclanthology.org/2020.findings-emnlp.349
DOI:
10.18653/v1/2020.findings-emnlp.349
Bibkey:
Cite (ACL):
Renjie Zheng, Mingbo Ma, Baigong Zheng, Kaibo Liu, Jiahong Yuan, Kenneth Church, and Liang Huang. 2020. Fluent and Low-latency Simultaneous Speech-to-Speech Translation with Self-adaptive Training. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 3928–3937, Online. Association for Computational Linguistics.
Cite (Informal):
Fluent and Low-latency Simultaneous Speech-to-Speech Translation with Self-adaptive Training (Zheng et al., Findings 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2020.findings-emnlp.349.pdf