Speech-translation

From domain-limited to domain-unlimited translation tasks

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Speech translation research started more than 15 years ago. Early projects and demonstrations, like Verbmobil and work done by the C-Star consortium where restricted to domain-limited applications, esp. travel domain. We see continued interest in this kind of projects, and also a strong tendency to commercialize speech translation technology. In recent years the goals have become more challenging: domain-unlimited speech translation. Projects like TC-Star in Europe and GALE in the United States aim at translating parliamentary speeches, broadcast news and even broadcast conversations. Ongoing research focuses on questions like tighter coupling between speech recognition and translation, segmenting speech recognition output into sentence-like units, and how this affects translation quality, detecting and removing disfluencies, and end-to-end optimization. In this paper we will review some of recent work done in both domain-limite d and domain-unlimited speech translation. We will show where progress has been made and highlight areas, where initial expectations have not been met so far.

Original languageEnglish
Title of host publication2007 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2007, Proceedings
Publication statusPublished - 1 Dec 2007
Externally publishedYes
Event2007 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2007 - Kyoto, Japan
Duration: 9 Dec 200713 Dec 2007

Other

Other2007 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2007
CountryJapan
CityKyoto
Period9/12/0713/12/07

Fingerprint

Speech recognition
Stars
Demonstrations

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Software
  • Artificial Intelligence

Cite this

Vogel, S. (2007). Speech-translation: From domain-limited to domain-unlimited translation tasks. In 2007 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2007, Proceedings [4430141]

Speech-translation : From domain-limited to domain-unlimited translation tasks. / Vogel, Stephan.

2007 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2007, Proceedings. 2007. 4430141.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Vogel, S 2007, Speech-translation: From domain-limited to domain-unlimited translation tasks. in 2007 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2007, Proceedings., 4430141, 2007 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2007, Kyoto, Japan, 9/12/07.
Vogel S. Speech-translation: From domain-limited to domain-unlimited translation tasks. In 2007 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2007, Proceedings. 2007. 4430141
Vogel, Stephan. / Speech-translation : From domain-limited to domain-unlimited translation tasks. 2007 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2007, Proceedings. 2007.
@inproceedings{13afe8cd103b4a17b0da45bc52cc9e6d,
title = "Speech-translation: From domain-limited to domain-unlimited translation tasks",
abstract = "Speech translation research started more than 15 years ago. Early projects and demonstrations, like Verbmobil and work done by the C-Star consortium where restricted to domain-limited applications, esp. travel domain. We see continued interest in this kind of projects, and also a strong tendency to commercialize speech translation technology. In recent years the goals have become more challenging: domain-unlimited speech translation. Projects like TC-Star in Europe and GALE in the United States aim at translating parliamentary speeches, broadcast news and even broadcast conversations. Ongoing research focuses on questions like tighter coupling between speech recognition and translation, segmenting speech recognition output into sentence-like units, and how this affects translation quality, detecting and removing disfluencies, and end-to-end optimization. In this paper we will review some of recent work done in both domain-limite d and domain-unlimited speech translation. We will show where progress has been made and highlight areas, where initial expectations have not been met so far.",
author = "Stephan Vogel",
year = "2007",
month = "12",
day = "1",
language = "English",
booktitle = "2007 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2007, Proceedings",

}

TY - GEN

T1 - Speech-translation

T2 - From domain-limited to domain-unlimited translation tasks

AU - Vogel, Stephan

PY - 2007/12/1

Y1 - 2007/12/1

N2 - Speech translation research started more than 15 years ago. Early projects and demonstrations, like Verbmobil and work done by the C-Star consortium where restricted to domain-limited applications, esp. travel domain. We see continued interest in this kind of projects, and also a strong tendency to commercialize speech translation technology. In recent years the goals have become more challenging: domain-unlimited speech translation. Projects like TC-Star in Europe and GALE in the United States aim at translating parliamentary speeches, broadcast news and even broadcast conversations. Ongoing research focuses on questions like tighter coupling between speech recognition and translation, segmenting speech recognition output into sentence-like units, and how this affects translation quality, detecting and removing disfluencies, and end-to-end optimization. In this paper we will review some of recent work done in both domain-limite d and domain-unlimited speech translation. We will show where progress has been made and highlight areas, where initial expectations have not been met so far.

AB - Speech translation research started more than 15 years ago. Early projects and demonstrations, like Verbmobil and work done by the C-Star consortium where restricted to domain-limited applications, esp. travel domain. We see continued interest in this kind of projects, and also a strong tendency to commercialize speech translation technology. In recent years the goals have become more challenging: domain-unlimited speech translation. Projects like TC-Star in Europe and GALE in the United States aim at translating parliamentary speeches, broadcast news and even broadcast conversations. Ongoing research focuses on questions like tighter coupling between speech recognition and translation, segmenting speech recognition output into sentence-like units, and how this affects translation quality, detecting and removing disfluencies, and end-to-end optimization. In this paper we will review some of recent work done in both domain-limite d and domain-unlimited speech translation. We will show where progress has been made and highlight areas, where initial expectations have not been met so far.

UR - http://www.scopus.com/inward/record.url?scp=44849124550&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=44849124550&partnerID=8YFLogxK

M3 - Conference contribution

BT - 2007 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2007, Proceedings

ER -