This paper reports on the evaluation activities conducted in the first year of the TC-STAR project. The TC-STAR project, financed by the European Commission within the Sixth Framework Program, is envisaged as a long-term effort to advance research in the core technologies of Speech-to-Speech Translation (SST). SST technology is a combination of Automatic Speech Recognition (ASR), Spoken Language Translation (SLT) and Text To Speech (TTS). The project targets a selection of unconstrained conversational speech domain (speeches and broadcast news) and three languages: European English, European Spanish, andMandarin Chinese. To assess the advances in SST technologies, annual competitive evaluations are organized. The aim of the first evaluation campaign was to measure the progress made during the first year of the project in ASR and SLT.
[1]
Khalid Choukri,et al.
TC-STAR: New language resources for ASR and SLT purposes
,
2006,
LREC.
[2]
Salim Roukos,et al.
Bleu: a Method for Automatic Evaluation of Machine Translation
,
2002,
ACL.
[3]
Jonathan G. Fiscus,et al.
A post-processing system to yield reduced word error rates: Recognizer Output Voting Error Reduction (ROVER)
,
1997,
1997 IEEE Workshop on Automatic Speech Recognition and Understanding Proceedings.
[4]
Bogdan Babych,et al.
Modelling Legitimate Translation Variation for Automatic Evaluation of MT Quality
,
2004,
LREC.