Speaker alignment in synthesised, machine translation communication

Anne H. Schneider, Saturnino Luz


Abstract
The effect of mistranslations on the verbal behaviour of users of speech-to-speech translation is investigated through a question answering experiment in which users were presented with machine translated questions through synthesized speech. Results show that people are likely to align their verbal behaviour to the output of a system that combines machine translation, speech recognition and speech synthesis in an interactive dialogue context, even when the system produces erroneous output. The alignment phenomenon has been previously considered by dialogue system designers from the perspective of the benefits it might bring to the interaction (e.g. by making the user more likely to employ terms contained in the system’s vocabulary). In contrast, our results reveal that in speech-to-speech translation systems alignment can in fact be detrimental to the interaction (e.g. by priming the user to align with non-existing lexical items produced by mistranslation). The implications of these findings are discussed with respect to the design of such systems.
Anthology ID:
2011.iwslt-papers.9
Volume:
Proceedings of the 8th International Workshop on Spoken Language Translation: Papers
Month:
December 8-9
Year:
2011
Address:
San Francisco, California
Venue:
IWSLT
SIG:
Publisher:
Note:
Pages:
254–260
Language:
URL:
https://aclanthology.org/2011.iwslt-papers.9
DOI:
Bibkey:
Cite (ACL):
Anne H. Schneider and Saturnino Luz. 2011. Speaker alignment in synthesised, machine translation communication. In Proceedings of the 8th International Workshop on Spoken Language Translation: Papers, pages 254–260, San Francisco, California.
Cite (Informal):
Speaker alignment in synthesised, machine translation communication (Schneider & Luz, IWSLT 2011)
Copy Citation:
PDF:
https://preview.aclanthology.org/update-css-js/2011.iwslt-papers.9.pdf