{"id":3091,"identifier":"data/TMEDTX","persistentUrl":"https://doi.org/10.11588/data/TMEDTX","protocol":"doi","authority":"10.11588","publisher":"heiDATA","publicationDate":"2019-10-21","storageIdentifier":"file://10.11588/data/TMEDTX","datasetVersion":{"id":519,"datasetId":3091,"datasetPersistentId":"doi:10.11588/data/TMEDTX","storageIdentifier":"file://10.11588/data/TMEDTX","versionNumber":2,"versionMinorNumber":0,"versionState":"RELEASED","productionDate":"2019-10-17","lastUpdateTime":"2020-06-13T07:01:19Z","releaseTime":"2020-06-13T07:01:19Z","createTime":"2020-06-12T15:47:50Z","publicationDate":"2019-10-21","citationDate":"2019-10-21","termsOfUse":"Licensed under Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0) \r\n","fileAccessRequest":false,"metadataBlocks":{"citation":{"displayName":"Citation Metadata","name":"citation","fields":[{"typeName":"title","multiple":false,"typeClass":"primitive","value":"LibriVoxDeEn - A Corpus for German-to-English Speech Translation and Speech Recognition"},{"typeName":"author","multiple":true,"typeClass":"compound","value":[{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Beilharz, Benjamin"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"Department of Computational Linguistics, Heidelberg University, Heidelberg, Germany"}},{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Sun, Xin"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"Department of Computational Linguistics, Heidelberg University, Heidelberg, Germany"}}]},{"typeName":"datasetContact","multiple":true,"typeClass":"compound","value":[{"datasetContactName":{"typeName":"datasetContactName","multiple":false,"typeClass":"primitive","value":"Riezler, Stefan"},"datasetContactAffiliation":{"typeName":"datasetContactAffiliation","multiple":false,"typeClass":"primitive","value":"Department of Computational Linguistics, Heidelberg University, Heidelberg, Germany"},"datasetContactEmail":{"typeName":"datasetContactEmail","multiple":false,"typeClass":"primitive","value":"riezler@cl.uni-heidelberg.de"}}]},{"typeName":"dsDescription","multiple":true,"typeClass":"compound","value":[{"dsDescriptionValue":{"typeName":"dsDescriptionValue","multiple":false,"typeClass":"primitive","value":"This dataset is a corpus of sentence-aligned triples of German audio, German text, and English translation, based on German audio books. The corpus consists of over 100 hours of audio material and over 50k parallel sentences. The speech data are low in disfluencies because of the audio book setup. The quality of audio and sentence alignments has been checked by a manual evaluation, showing that that speech alignment is in general very high. The sentence alignment quality is comparable to well-used parallel translation data and can be adjusted by cutoffs on the automatic alignment score. To our knowledge, this corpus is to date the largest resource for end-to-end speech translation for German."},"dsDescriptionDate":{"typeName":"dsDescriptionDate","multiple":false,"typeClass":"primitive","value":"2019-10-17"}}]},{"typeName":"subject","multiple":true,"typeClass":"controlledVocabulary","value":["Computer and Information Science"]},{"typeName":"keyword","multiple":true,"typeClass":"compound","value":[{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"Speech Translation Corpus German-English"}}]},{"typeName":"topicClassification","multiple":true,"typeClass":"compound","value":[{"topicClassValue":{"typeName":"topicClassValue","multiple":false,"typeClass":"primitive","value":"Speech Translation"}}]},{"typeName":"publication","multiple":true,"typeClass":"compound","value":[{"publicationCitation":{"typeName":"publicationCitation","multiple":false,"typeClass":"primitive","value":"Beilharz et al. 2019, LibriVoxDeEn - A Corpus for German-to-English Speech Translation and Speech Recognition (arXiv preprint - arXiv:1910.07924)"},"publicationIDType":{"typeName":"publicationIDType","multiple":false,"typeClass":"controlledVocabulary","value":"arXiv"},"publicationIDNumber":{"typeName":"publicationIDNumber","multiple":false,"typeClass":"primitive","value":"1910.07924"},"publicationURL":{"typeName":"publicationURL","multiple":false,"typeClass":"primitive","value":"https://arxiv.org/abs/1910.07924"}}]},{"typeName":"language","multiple":true,"typeClass":"controlledVocabulary","value":["English","German"]},{"typeName":"producer","multiple":true,"typeClass":"compound","value":[{"producerName":{"typeName":"producerName","multiple":false,"typeClass":"primitive","value":"Statistical NLP Group, Department of Computational Linguistics"},"producerAffiliation":{"typeName":"producerAffiliation","multiple":false,"typeClass":"primitive","value":"Heidelberg University"},"producerAbbreviation":{"typeName":"producerAbbreviation","multiple":false,"typeClass":"primitive","value":"statNLPgroup"},"producerURL":{"typeName":"producerURL","multiple":false,"typeClass":"primitive","value":"https://www.cl.uni-heidelberg.de/statnlpgroup/"},"producerLogoURL":{"typeName":"producerLogoURL","multiple":false,"typeClass":"primitive","value":"https://www.cl.uni-heidelberg.de/statnlpgroup/images/statnlp_logo.png"}}]},{"typeName":"productionDate","multiple":false,"typeClass":"primitive","value":"2019-10-17"},{"typeName":"productionPlace","multiple":true,"typeClass":"primitive","value":["Heidelberg"]},{"typeName":"contributor","multiple":true,"typeClass":"compound","value":[{"contributorType":{"typeName":"contributorType","multiple":false,"typeClass":"controlledVocabulary","value":"Research Group"},"contributorName":{"typeName":"contributorName","multiple":false,"typeClass":"primitive","value":"Statistical NLP Group, Department of Computational Linguistics"}}]},{"typeName":"grantNumber","multiple":true,"typeClass":"compound","value":[{"grantNumberAgency":{"typeName":"grantNumberAgency","multiple":false,"typeClass":"primitive","value":"German research foundation (DFG)"},"grantNumberValue":{"typeName":"grantNumberValue","multiple":false,"typeClass":"primitive","value":"RI2221/4-1"}}]},{"typeName":"distributor","multiple":true,"typeClass":"compound","value":[{"distributorName":{"typeName":"distributorName","multiple":false,"typeClass":"primitive","value":"Statistical NLP Group, Department of Computational Linguistics"},"distributorAffiliation":{"typeName":"distributorAffiliation","multiple":false,"typeClass":"primitive","value":"Heidelberg University"},"distributorAbbreviation":{"typeName":"distributorAbbreviation","multiple":false,"typeClass":"primitive","value":"statNLPgroup"},"distributorURL":{"typeName":"distributorURL","multiple":false,"typeClass":"primitive","value":"https://www.cl.uni-heidelberg.de/statnlpgroup/"},"distributorLogoURL":{"typeName":"distributorLogoURL","multiple":false,"typeClass":"primitive","value":"https://www.cl.uni-heidelberg.de/statnlpgroup/images/statnlp_logo.png"}}]}]}},"files":[{"label":"librivoxdeen-1.01_part1.tar.gz","restricted":false,"version":1,"datasetVersionId":519,"categories":["Data"],"dataFile":{"id":3531,"persistentId":"doi:10.11588/data/TMEDTX/4UFDYA","pidURL":"https://doi.org/10.11588/data/TMEDTX/4UFDYA","filename":"librivoxdeen-1.01_part1.tar.gz","contentType":"application/gzip","friendlyType":"Gzip Archive","filesize":21837360314,"categories":["Data"],"storageIdentifier":"file://172a936e486-92abd0362d76","rootDataFileId":-1,"md5":"9fb23ee878584f4cab717e348cdeeaaf","checksum":{"type":"MD5","value":"9fb23ee878584f4cab717e348cdeeaaf"},"tabularData":false,"creationDate":"2020-06-12","publicationDate":"2020-06-13","fileAccessRequest":false}},{"label":"librivoxdeen-1.01_part2.tar.gz","restricted":false,"version":1,"datasetVersionId":519,"categories":["Data"],"dataFile":{"id":3532,"persistentId":"doi:10.11588/data/TMEDTX/3ATXPT","pidURL":"https://doi.org/10.11588/data/TMEDTX/3ATXPT","filename":"librivoxdeen-1.01_part2.tar.gz","contentType":"application/gzip","friendlyType":"Gzip Archive","filesize":18433481150,"categories":["Data"],"storageIdentifier":"file://172a936e2f5-8fb111235541","rootDataFileId":-1,"md5":"daf33d0f1242bad5a623b061fbaa426d","checksum":{"type":"MD5","value":"daf33d0f1242bad5a623b061fbaa426d"},"tabularData":false,"creationDate":"2020-06-12","publicationDate":"2020-06-13","fileAccessRequest":false}},{"label":"README.md","restricted":false,"version":1,"datasetVersionId":519,"categories":["Documentation"],"dataFile":{"id":3093,"persistentId":"doi:10.11588/data/TMEDTX/SJOCW8","pidURL":"https://doi.org/10.11588/data/TMEDTX/SJOCW8","filename":"README.md","contentType":"text/markdown","friendlyType":"Markdown Text","filesize":4421,"categories":["Documentation"],"storageIdentifier":"file://16ded08d2bf-1c3042e01609","rootDataFileId":-1,"md5":"971f62ef7dc31254dfc0e25f14347bc1","checksum":{"type":"MD5","value":"971f62ef7dc31254dfc0e25f14347bc1"},"tabularData":false,"creationDate":"2019-10-21","publicationDate":"2019-10-21","fileAccessRequest":false}}],"citation":"Beilharz, Benjamin; Sun, Xin, 2019, \"LibriVoxDeEn - A Corpus for German-to-English Speech Translation and Speech Recognition\", https://doi.org/10.11588/data/TMEDTX, heiDATA, V2"}}