Exploring Phoneme-Level Speech Representations for End-to-End Speech Translation

Elizabeth Salesky, Matthias Sperber, Alan W Black


Abstract
Previous work on end-to-end translation from speech has primarily used frame-level features as speech representations, which creates longer, sparser sequences than text. We show that a naive method to create compressed phoneme-like speech representations is far more effective and efficient for translation than traditional frame-level speech features. Specifically, we generate phoneme labels for speech frames and average consecutive frames with the same label to create shorter, higher-level source sequences for translation. We see improvements of up to 5 BLEU on both our high and low resource language pairs, with a reduction in training time of 60%. Our improvements hold across multiple data sizes and two language pairs.
Anthology ID:
P19-1179
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2019
Address:
Florence, Italy
Editors:
Anna Korhonen, David Traum, Lluís Màrquez
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1835–1841
Language:
URL:
https://aclanthology.org/P19-1179
DOI:
10.18653/v1/P19-1179
Bibkey:
Cite (ACL):
Elizabeth Salesky, Matthias Sperber, and Alan W Black. 2019. Exploring Phoneme-Level Speech Representations for End-to-End Speech Translation. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 1835–1841, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Exploring Phoneme-Level Speech Representations for End-to-End Speech Translation (Salesky et al., ACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/P19-1179.pdf
Video:
 https://aclanthology.org/P19-1179.mp4