Show simple item record

Depositordc.contributorYamagishi, Junichi
Funderdc.contributor.otherThe Japan Society for the Promotion of Science (JSPS)en_UK
Data Creatordc.creatorLorenzo-Trueba, Jaime
Data Creatordc.creatorYamagishi, Junichi
Data Creatordc.creatorToda, Tomoki
Data Creatordc.creatorSaito, Daisuke
Data Creatordc.creatorVillavicencio, Fernando
Data Creatordc.creatorKinnunen, Tomi
Data Creatordc.creatorLing, Zhenhua
Date Accessioneddc.date.accessioned2018-04-10T09:56:33Z
Date Availabledc.date.available2018-04-10T09:56:33Z
Citationdc.identifier.citationLorenzo-Trueba, Jaime; Yamagishi, Junichi; Toda, Tomoki; Saito, Daisuke; Villavicencio, Fernando; Kinnunen, Tomi; Ling, Zhenhua. (2018). The Voice Conversion Challenge 2018: database and results, [sound]. The Centre for Speech Technology Research, The University of Edinburgh, UK. https://doi.org/10.7488/ds/2337.en
Persistent Identifierdc.identifier.urihttp://hdl.handle.net/10283/3061
Persistent Identifierdc.identifier.urihttps://doi.org/10.7488/ds/2337
Dataset Description (abstract)dc.description.abstractVoice conversion (VC) is a technique to transform a speaker identity included in a source speech waveform into a different one while preserving linguistic information of the source speech waveform. In 2016, we have launched the Voice Conversion Challenge (VCC) 2016 at Interspeech 2016. The objective of the 2016 challenge was to better understand different VC techniques built on a freely-available common dataset to look at a common goal, and to share views about unsolved problems and challenges faced by the current VC techniques. The VCC 2016 focused on the most basic VC task, that is, the construction of VC models that automatically transform the voice identity of a source speaker into that of a target speaker using a parallel clean training database where source and target speakers read out the same set of utterances in a professional recording studio. 17 research groups had participated in the 2016 challenge. The challenge was successful and it established new standard evaluation methodology and protocols for bench-marking the performance of VC systems. In 2018, we launched the second edition of VCC, the VCC 2018. In this second edition, we have revised three aspects of the challenge. First, we have reduced the amount of speech data used for the construction of participant's VC systems to half. This is based on feedback from participants in the previous challenge and this is also essential for practical applications. Second, we introduced a more challenging task refereed to a Spoke task in addition to a similar task to the 1st edition, which we call a Hub task. In the Spoke task, participants need to build their VC systems using a non-parallel database in which source and target speakers read out different sets of utterances. We then evaluate both parallel and non-parallel voice conversion systems via the same large-scale crowdsourcing listening test. Third, we also attempted to bridge the gap between the ASV and VC communities. Since new VC systems developed for the VCC 2018 may be strong candidates for enhancing the ASVspoof 2015 database, we also asses spoofing performance of the VC systems based on anti-spoofing scores. This repository contains the training and evaluation data released to participants, submissions from participants, and the listening test results for the 2018 Voice Conversion Challenge.en_UK
Dataset Description (TOC)dc.description.tableofcontentsData structure: Training and evaluation data vcc2018_database_training: training data for building parallel and non-parallel VC systems released to participants during the challenge vcc2018_database_evaluation: evaluation data (source speaker's data) released to participants during the challenge vcc2018_database_reference: evaluation data (target speaker's data) used as reference in listening tests vcc2018_database_evaluation_transcriptions: transcriptions of evaluation data. This was NOT released to participants during the challenge submissions from participants vcc2018_submitted_systems_converted_speech: converted speech of submitted systems vcc2018_submitted_systems_system_descriptions: descriptions of submitted systems provided by participants listening test results vcc2018_evaluation_results: listening test results vcc2018_evaluation_listening_test_raw_results: raw results of listening tests vcc2018_evaluation_listeners_information: information of listeners who participated in the listening testsen_UK
Languagedc.language.isoengen_UK
Publisherdc.publisherThe Centre for Speech Technology Research, The University of Edinburgh, UKen_UK
Relation (Is Version Of)dc.relation.isversionofhttps://doi.org/10.7488/ds/1575en_UK
Relation (Is Referenced By)dc.relation.isreferencedbyhttps://arxiv.org/abs/1804.04262en_UK
Relation (Is Referenced By)dc.relation.isreferencedbyJaime Lorenzo-Trueba, Junichi Yamagishi, Tomoki Toda, Daisuke Saito, Fernando Villavicencio, Tomi Kinnunen, Zhenhua Ling, "The Voice Conversion Challenge 2018: Promoting Development of Parallel and Nonparallel Methods", Proc Speaker Odyssey 2018, June 2018. https://doi.org/10.21437/Odyssey.2018-28
Relation (Is Referenced By)dc.relation.isreferencedbyhttps://doi.org/10.21437/Odyssey.2018-28
Rightsdc.rightsCreative Commons Attribution 4.0 International Public Licenseen
Sourcedc.sourceGautham J. Mysore, DAPS (Device and Produced Speech) Dataset - A dataset of professional production quality speech and corresponding aligned speech recorded on common consumer device, https://archive.org/details/daps_dataseten_UK
Subjectdc.subjectvoice conversionen_UK
Subjectdc.subjectspeaker conversionen_UK
Subjectdc.subjectVoice Conversion Challengeen_UK
Subject Classificationdc.subject.classificationMathematical and Computer Sciences::Speech and Natural Language Processingen_UK
Titledc.titleThe Voice Conversion Challenge 2018: database and resultsen_UK
Typedc.typesounden_UK

Download All
zip file MD5 Checksum: 5747680cc3c864b7bcbeff8ba1a2bc0c

Files in this item

Thumbnail
Thumbnail
Thumbnail
Thumbnail
Thumbnail
Thumbnail
Thumbnail
Thumbnail
Thumbnail
Thumbnail
Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record