OLAC Record oai:catalogue.elra.info:ELRA-E0031

Metadata
Title:		TC-STAR 2006 Evaluation Package – End-to-End
Access Rights:		Rights available for: evaluationUse
Date Available (W3CDTF):		2007-10-09
Date Issued (W3CDTF):		2007-10-09
Date Modified (W3CDTF):		2007-10-09
Description:		TC-STAR is a European integrated project focusing on Speech-to-Speech Translation (SST). To encourage significant breakthrough in all SST technologies, annual open competitive evaluations are organized. Automatic Speech Recognition (ASR), Spoken Language Translation (SLT) Text-To-Speech (TTS) are evaluated independently and within an end-to-end system (E2E).The second TC-STAR evaluation campaign took place in March 2006. Three core technologies were evaluated during the campaign:• Automatic Speech Recognition (ASR),• Spoken Language Translation (SLT),• Text to Speech (TTS).For the 2006 campaign, an end-to-end evaluation was also carried out.Each evaluation package includes resources, protocols, scoring tools, results of the official campaign, etc., that were used or produced during the second evaluation campaign. The aim of these evaluation packages is to enable external players to evaluate their own system and compare their results with those obtained during the campaign itself.The speech databases made within the TC-STAR project were validated by SPEX, in the Netherlands, to assess their compliance with the TC-STAR format and content specifications.This package includes the material used for the TC-STAR 2006 E2E evaluation campaign for English-to-Spanish translation.To be able to chain the components, ASR, SLT and TTS evaluation tasks were designed to use common sets of raw data and conditions. Three evaluation tasks, common to ASR, SLT and TTS, were selected: EPPS (European Parliament Plenary Sessions) task, CORTES (Spanish Parliament Sessions) task and VOA (Voice of America) task. The CORTES data were used in addition to the EPPS data to evaluate ASR in Spanish and SLT from Spanish into English.For the E2E task, ASR, SLT and TTS output was used to evaluate TC-STAR system. This package consists of 20 input audio files (2-3 minutes each), with corresponding transcription from the ASR system, corresponding translation from the SLT system, as well as corresponding synthesis from the TTS system. The output audio files, consisting of interpreters’ recordings, are provided. The package also contains the questionnaires used for the comprehension and fluency evaluation of TC-STAR system and interpreters’ files, together with the answers given by judges.
Identifier:		ELRA-E0031
		ISLRN: 096-175-302-473-2
Identifier (URI):		https://catalog.elra.info/en-us/repository/browse/ELRA-E0031/
Language:		English
		Spanish; Castilian
Language (ISO639):		eng
		spa
Medium:		Not specified
Publisher:		ELRA (European Language Resources Association)
Type (DCMI):		Sound
Type (OLAC):		primary_text
OLAC Info
Archive:		ELRA Catalogue of Language Resources
Description:		http://www.language-archives.org/archive/catalogue.elra.info
GetRecord:		OAI-PMH request for OLAC format
GetRecord:		Pre-generated XML file
OAI Info
OaiIdentifier:		oai:catalogue.elra.info:ELRA-E0031
DateStamp:		2007-10-09
GetRecord:		OAI-PMH request for simple DC format
Search Info
Citation:		n.a. 2007. ELRA (European Language Resources Association).
Terms:		area_Europe country_ES country_GB dcmi_Sound iso639_eng iso639_spa olac_primary_text