Efficient CTC Regularization via Coarse Labels for End-to-End Speech Translation

Biao Zhang, Barry Haddow, Rico Sennrich


Abstract
For end-to-end speech translation, regularizing the encoder with the Connectionist Temporal Classification (CTC) objective using the source transcript or target translation as labels can greatly improve quality. However, CTC demands an extra prediction layer over the vocabulary space, bringing in non-negligible model parameters and computational overheads, although this layer becomes useless at inference. In this paper, we re-examine the need for genuine vocabulary labels for CTC for regularization and explore strategies to reduce the CTC label space, targeting improved efficiency without quality degradation. We propose coarse labeling for CTC (CoLaCTC), which merges vocabulary labels via simple heuristic rules, such as using truncation, division or modulo (MOD) operations. Despite its simplicity, our experiments on 4 source and 8 target languages show that CoLaCTC with MOD particularly can compress the label space aggressively to 256 and even further, gaining training efficiency (1.18× ∼ 1.77× speedup depending on the original vocabulary size) yet still delivering comparable or better performance than the CTC baseline. We also show that CoLaCTC successfully generalizes to CTC regularization regardless of using transcript or translation for labeling.
Anthology ID:
2023.eacl-main.166
Volume:
Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
Month:
May
Year:
2023
Address:
Dubrovnik, Croatia
Editors:
Andreas Vlachos, Isabelle Augenstein
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2264–2276
Language:
URL:
https://aclanthology.org/2023.eacl-main.166
DOI:
10.18653/v1/2023.eacl-main.166
Bibkey:
Cite (ACL):
Biao Zhang, Barry Haddow, and Rico Sennrich. 2023. Efficient CTC Regularization via Coarse Labels for End-to-End Speech Translation. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 2264–2276, Dubrovnik, Croatia. Association for Computational Linguistics.
Cite (Informal):
Efficient CTC Regularization via Coarse Labels for End-to-End Speech Translation (Zhang et al., EACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.eacl-main.166.pdf
Video:
 https://aclanthology.org/2023.eacl-main.166.mp4