This paper describes an application of a speech translation system to another task/domain in the real-world by using developmental data collected from real-world interactions. The total cost for this task-alteration was calculated to be 9 Person-Month. The newly applied system was also evaluated by using speech data collected from real-world interactions. For real-world speech having a machine-friendly speaking style, the newly applied system could recognize typical sentences with a word accuracy of 90% or better. We also found that, concerning the overall speech translation performance, the system could translate about 80% of the input Japanese speech into acceptable English sentences.
Atsushi NAKAMURA
Masaki NAITO
Hajime TSUKADA
Rainer GRUHN
Eiichiro SUMITA
Hideki KASHIOKA
Hideharu NAKAJIMA
Tohru SHIMIZU
Yoshinori SAGISAKA
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Atsushi NAKAMURA, Masaki NAITO, Hajime TSUKADA, Rainer GRUHN, Eiichiro SUMITA, Hideki KASHIOKA, Hideharu NAKAJIMA, Tohru SHIMIZU, Yoshinori SAGISAKA, "A Speech Translation System Applied to a Real-World Task/Domain and Its Evaluation Using Real-World Speech Data" in IEICE TRANSACTIONS on Information,
vol. E84-D, no. 1, pp. 142-154, January 2001, doi: .
Abstract: This paper describes an application of a speech translation system to another task/domain in the real-world by using developmental data collected from real-world interactions. The total cost for this task-alteration was calculated to be 9 Person-Month. The newly applied system was also evaluated by using speech data collected from real-world interactions. For real-world speech having a machine-friendly speaking style, the newly applied system could recognize typical sentences with a word accuracy of 90% or better. We also found that, concerning the overall speech translation performance, the system could translate about 80% of the input Japanese speech into acceptable English sentences.
URL: https://global.ieice.org/en_transactions/information/10.1587/e84-d_1_142/_p
Copy
@ARTICLE{e84-d_1_142,
author={Atsushi NAKAMURA, Masaki NAITO, Hajime TSUKADA, Rainer GRUHN, Eiichiro SUMITA, Hideki KASHIOKA, Hideharu NAKAJIMA, Tohru SHIMIZU, Yoshinori SAGISAKA, },
journal={IEICE TRANSACTIONS on Information},
title={A Speech Translation System Applied to a Real-World Task/Domain and Its Evaluation Using Real-World Speech Data},
year={2001},
volume={E84-D},
number={1},
pages={142-154},
abstract={This paper describes an application of a speech translation system to another task/domain in the real-world by using developmental data collected from real-world interactions. The total cost for this task-alteration was calculated to be 9 Person-Month. The newly applied system was also evaluated by using speech data collected from real-world interactions. For real-world speech having a machine-friendly speaking style, the newly applied system could recognize typical sentences with a word accuracy of 90% or better. We also found that, concerning the overall speech translation performance, the system could translate about 80% of the input Japanese speech into acceptable English sentences.},
keywords={},
doi={},
ISSN={},
month={January},}
Copy
TY - JOUR
TI - A Speech Translation System Applied to a Real-World Task/Domain and Its Evaluation Using Real-World Speech Data
T2 - IEICE TRANSACTIONS on Information
SP - 142
EP - 154
AU - Atsushi NAKAMURA
AU - Masaki NAITO
AU - Hajime TSUKADA
AU - Rainer GRUHN
AU - Eiichiro SUMITA
AU - Hideki KASHIOKA
AU - Hideharu NAKAJIMA
AU - Tohru SHIMIZU
AU - Yoshinori SAGISAKA
PY - 2001
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E84-D
IS - 1
JA - IEICE TRANSACTIONS on Information
Y1 - January 2001
AB - This paper describes an application of a speech translation system to another task/domain in the real-world by using developmental data collected from real-world interactions. The total cost for this task-alteration was calculated to be 9 Person-Month. The newly applied system was also evaluated by using speech data collected from real-world interactions. For real-world speech having a machine-friendly speaking style, the newly applied system could recognize typical sentences with a word accuracy of 90% or better. We also found that, concerning the overall speech translation performance, the system could translate about 80% of the input Japanese speech into acceptable English sentences.
ER -