Show simple item record

Depositordc.contributorYamagishi, Junichi
Funderdc.contributor.otherMEXT KAKENHI
Funderdc.contributor.otherNational Institute of Informatics (NII) (JAPAN)
Data Creatordc.creatorSarfjoo, Seyyed Saeed
Data Creatordc.creatorYamagishi, Junichi
Date Accessioneddc.date.accessioned2017-11-24T16:50:30Z
Date Availabledc.date.available2018-01-28T05:15:26Z
Citationdc.identifier.citationSarfjoo, SS; Yamagishi, J. (2017). Device Recorded VCTK (Small subset version), [sound]. https://doi.org/10.7488/ds/2259en
Persistent Identifierdc.identifier.urihttps://hdl.handle.net/10283/2959
Persistent Identifierdc.identifier.urihttps://doi.org/10.7488/ds/2259
Dataset Description (abstract)dc.description.abstract## This item has been replaced by the one which can be found at https://doi.org/10.7488/ds/2316 ## This dataset is a new variant of the voice cloning toolkit (VCTK) dataset: device-recorded VCTK (DR-VCTK), where the high-quality speech signals recorded in a semi-anechoic chamber using professional audio devices are played back and re-recorded in office environments using relatively inexpensive consumer devices.en_UK
Dataset Description (TOC)dc.description.tableofcontentsThis dataset is a new variant of the voice cloning toolkit (VCTK) dataset: device-recorded VCTK (DR-VCTK), where the high-quality speech signals recorded in a semi-anechoic chamber using professional audio devices are played back and re-recorded in office environments using relatively inexpensive consumer devices. Using the parallel database of the original VCTK and DR-VCTK, we can consider data-driven mapping between device-recorded and high-quality audio. This package has a small preprocessed version of DR-VCTK used for our recent experiment submitted to ICASSP 2018. For more details, please see README.txten_UK
Languagedc.language.isoengen_UK
Publisherdc.publisherUniversity of Edinburgh. School of Informatics. The Centre for Speech Technology Research (CSTR)en_UK
Relation (Is Version Of)dc.relation.isversionofhttps://doi.org/10.7488/ds/1994en_UK
Superseded Bydc.relation.isreplacedbyhttps://doi.org/10.7488/ds/2316
Rightsdc.rightsCreative Commons Attribution 4.0 International Public Licenseen
Subjectdc.subjectSpeechen_UK
Subjectdc.subjectSpeech enhancementen_UK
Subjectdc.subjectSpeech synthesisen_UK
Subject Classificationdc.subject.classificationEngineeringen_UK
Titledc.titleSUPERSEDED - Device Recorded VCTK (Small subset version)en_UK
Typedc.typesounden_UK

Download All
zip file MD5 Checksum: bee244ed0c6e72d675b4817002bf9eb8

Files in this item

Thumbnail
Thumbnail
Thumbnail
Thumbnail

This item appears in the following Collection(s)

  • VCTK
    Voice Cloning Toolkit

Show simple item record