Direct Segmentation Models for Streaming Speech Translation

Javier Iranzo-Sánchez, Adrià Giménez Pastor, Joan Albert Silvestre-Cerdà, Pau Baquero-Arnal, Jorge Civera Saiz, Alfons Juan


Abstract
The cascade approach to Speech Translation (ST) is based on a pipeline that concatenates an Automatic Speech Recognition (ASR) system followed by a Machine Translation (MT) system. These systems are usually connected by a segmenter that splits the ASR output into hopefully, semantically self-contained chunks to be fed into the MT system. This is specially challenging in the case of streaming ST, where latency requirements must also be taken into account. This work proposes novel segmentation models for streaming ST that incorporate not only textual, but also acoustic information to decide when the ASR output is split into a chunk. An extensive and throughly experimental setup is carried out on the Europarl-ST dataset to prove the contribution of acoustic information to the performance of the segmentation model in terms of BLEU score in a streaming ST scenario. Finally, comparative results with previous work also show the superiority of the segmentation models proposed in this work.
Anthology ID:
2020.emnlp-main.206
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2599–2611
Language:
URL:
https://www.aclweb.org/anthology/2020.emnlp-main.206
DOI:
10.18653/v1/2020.emnlp-main.206
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/2020.emnlp-main.206.pdf
Optional supplementary material:
 2020.emnlp-main.206.OptionalSupplementaryMaterial.zip