Thumbnail
Access Restriction
Open

Author Zhang, Ruiqiang ♦ Kikui, Genichiro ♦ Yamamoto, Hirofumi ♦ Lo, Wai-Kit
Source CiteSeerX
Content type Text
File Format PDF
Language English
Subject Domain (in DDC) Computer science, information & general works ♦ Data processing & computer science
Subject Keyword Decoding Algorithm ♦ Speech Recognition Word Lattice ♦ Japanese-to-english Speech Trans-lation Task ♦ Word Lattice Translation ♦ Speech Recognition Confidence Measure ♦ Speech Translation ♦ Speech Translation Quality ♦ Misrecognized Single-best Hypothe-ses ♦ Experimental Result ♦ Im-proved Speech Translation Performance ♦ Posterior Probability
Description We propose a novel statistical machine translation de-coding algorithm for speech translation to improve speech translation quality. The algorithm can translate the speech recognition word lattice, where more hypotheses are uti-lized to bypass the misrecognized single-best hypothe-ses. We also show that a speech recognition confidence measure, implemented by posterior probability, is effec-tive to improve speech translation. The proposed tech-niques were tested in a Japanese-to-English speech trans-lation task. The experimental results demonstrate the im-proved speech translation performance by the proposed techniques. 1.
Educational Role Student ♦ Teacher
Age Range above 22 year
Educational Use Research
Education Level UG and PG ♦ Career/Technical Study
Learning Resource Type Article
Publisher Date 2005-01-01
Publisher Institution In Proceedings of the 2005 International Workshop on Spoken Language Translation