"Can you give me another word for hyperbaric?": Improving speech translation using targeted clarification questions
Lists
Only you see this
Abstract
We present a novel approach for improving communication success between users of speech-to-speech translation systems by automatically detecting errors in the output of automatic speech recognition (ASR) and statistical machine translation (SMT) systems. Our approach initiates system-driven targeted clarification about errorful regions in user input and repairs them given user responses. Our system has been evaluated by unbiased subjects in live mode, and results show improved success of communication between users of the system.
BibTeX
@inproceedings{ayan2013can,
author = {Necip Fazil Ayan and Arindam Mandal and Michael W. Frandsen and Jing Zheng and Peter Blasco and Andreas Kathol and Frédéric Béchet and Benoît Favre and Alex Marin and Tom Kwiatkowski and Mari Ostendorf and Luke S. Zettlemoyer and Philipp Salletmayr and Julia Hirschberg and Svetlana Stoyanchev},
title = {{"Can you give me another word for hyperbaric?": Improving speech translation using targeted clarification questions}},
booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
year = {2013},
url = {https://openreview.net/forum?id=4J1CBJnNBqn},
}Loading related content...