TC-STAR is an European integrated project focusing on Speech-to-Speech Translation (SST). To encourage significant advances in all SST technologies, annual competitive evaluations are organized. Automatic Speech Recognition (ASR), Spoken Language Translation (SLT) and Text-To-Speech (TTS) are evaluated independently and within an end-to-end system. The project targets a selection of unconstrained conversational speech domains—speeches and broadcast news—and three languages: European English, European Spanish, and Mandarin Chinese.
The first evaluation took place in March 2005 for ASR and SLT and September 2005 for TTS. TC-STAR welcomes outside participants in its 2nd evaluation of January-February 2006. This participation is free of charge.
The TC-STAR 2006 evaluation campaign will consider:
SLT in the following directions
a) Chinese-to-English (Broadcast News)
b) Spanish-to-English (European Parliament plenary speeches)
c) English-to-Spanish (European Parliament plenary speeches)
The SLT evaluation of European Parliament plenary speeches will cover three types of input:
1. ASR output (single best sentence, and more: N-best, word lattices)
2. verbatim transcription,
3. final text edition.
ASR in the following languages
TTS in Chinese, English, and Spanish under the following conditions:
a) English (European Parliament plenary speeches)
Spanish (European Parliament plenary speeches)
c) Mandarin Chinese (Broadcast News)
a) Complete system: participants use their own training data
b) Voice conversion intralingual and crosslingual, expressive speech: data provided by TC-STAR
For ASR and SLT, training data will be made available by the TC-STAR project for English and Spanish and can be purchased at LDC for Chinese. Development data will be provided by the TC-STAR project. Legal issues regarding the data will be detailed in the 2nd Call For Participation.
All participants will be given the opportunity to present and discuss their results in the TC-STAR evaluation workshop in Barcelona in June 2006.
Registration: October 2005 (early expression of interest is welcome)
ASR evaluation: from mid January to end of January 2006
SLT evaluation: from begin February to mid February 2006
TTS evaluation: from begin February to end of February 2006
Release: April 2006
Submission of papers: May 2006
Workshop: June 2006
Contact: Djamel Mostefa (ELDA)
tel. +33 1 43 13 33 33