Show simple item record

Depositordc.contributorYamagishi, Junichi
Funderdc.contributor.otherEuropean Commissionen_UK
Funderdc.contributor.otherAcademy of Finland
Funderdc.contributor.otherJapan Society for the Promotion of Science (JSPS)
Data Creatordc.creatorKinnunen, Tomi
Data Creatordc.creatorSahidullah, Md
Data Creatordc.creatorDelgado, Héctor
Data Creatordc.creatorTodisco, Massimiliano
Data Creatordc.creatorEvans, Nicholas
Data Creatordc.creatorYamagishi, Junichi
Data Creatordc.creatorLee, Kong Aik
Date Accessioneddc.date.accessioned2018-04-02T15:42:37Z
Date Availabledc.date.available2018-04-02T15:42:37Z
Citationdc.identifier.citationKinnunen, Tomi; Sahidullah, Md; Delgado, Héctor; Todisco, Massimiliano; Evans, Nicholas; Yamagishi, Junichi; Lee, Kong Aik. (2018). The 2nd Automatic Speaker Verification Spoofing and Countermeasures Challenge (ASVspoof 2017) Database, Version 2, [sound]. University of Edinburgh. The Centre for Speech Technology Research (CSTR). https://doi.org/10.7488/ds/2332.en
Persistent Identifierdc.identifier.urihttp://hdl.handle.net/10283/3055
Persistent Identifierdc.identifier.urihttps://doi.org/10.7488/ds/2332
Dataset Description (abstract)dc.description.abstractThis is a database used for the Second Automatic Speaker Verification Spoofing and Countermeasuers Challenge, for short, ASVspoof 2017 (http://www.asvspoof.org) organized by Tomi Kinnunen, Md Sahidullah, Héctor Delgado, Massimiliano Todisco, Nicholas Evans, Junichi Yamagishi, Kong Aik Lee in 2017. The ASVspoof challenge aims to encourage further progress through (i) the collection and distribution of a standard dataset with varying spoofing attacks implemented with multiple, diverse algorithms and (ii) a series of competitive evaluations for automatic speaker verification. The ASVspoof 2017 challenge follows on from two special sessions on spoofing and countermeasures for automatic speaker verification held during INTERSPEECH 2013 and 2015. While the first edition in 2013 was targeted mainly at increasing awareness of the spoofing problem, the 2015 edition included a first challenge on the topic, with commonly defined evaluation data, metrics and protocols. The task in ASVspoof 2015 was to discriminate genuine human speech from speech produced using text-to-speech (TTS) and voice conversion (VC) attacks. The challenge was drawn upon state-of-the-art TTS and VC attacks data prepared for the “SAS” corpus by TTS and VC researchers. The primary technical goal of ASVspoof 2017 is to assess spoofing attack detection accuracy with ‘out in the wild’ conditions, thereby advancing research towards generalized spoofing countermeasure, in particular to detect replay. In addition, ASVspoof 2017 attempts to better interlink the research efforts from spoofing and text-dependent ASV communities. To this end, ASVspoof 2017 makes an extensive use of the recent text-dependent RedDots corpus, as well as a replayed version of the same data. The ASVspoof 2017 database contains large amount of speech data collected from 179 replay sessions in 61 unique replay configurations. Number of speakers is 42. A replay configuration means a unique combination of room, replay device and recording device, while a session refers to a set of source files, which share the same replay configuration. This is version 2 of the ASVspoof 2017 database. Please see README and ChangeLog for more details.en_UK
Dataset Description (TOC)dc.description.tableofcontentsBelow are some details about the database: 1. Training and development data are included in 'ASVspoof2017_V2_train.zip’ ’ASVspoof2017_V2_dev.zip’. Training dataset contains audio files with known ground-truth which can be used to train systems which can distinguish between genuine and spoofed speech. The development dataset contains audio files with known ground-truth which can be used for the development of spoofing detection algorithms. 2. Evaluation data is available in 'ASVspoof2017_V2_eval.zip’. 3. Protocol and keys are available in 'protocol_V2.zip’. 4. Additional Instruction_V2.txt file is included in packages. There are originally used for the challenge participant to explain the database. 5. About how to compute the EERs, please refer the evaluation plan included in this repository. 6. To compare with the challenge results, please refer the summary paper of the challenge included in this repository. 7. The baseline results based on CQCC can be reproduced using publicly released Matlab-based implementation of a replay attack spoofing detector http://www.asvspoof.org/data2017/baseline_CM.zipen_UK
Languagedc.language.isoengen_UK
Publisherdc.publisherUniversity of Edinburgh. The Centre for Speech Technology Research (CSTR)en_UK
Relation (Is Version Of)dc.relation.isversionofhttps://doi.org/10.7488/ds/298en_UK
Relation (Is Referenced By)dc.relation.isreferencedbyhttps://doi.org/10.21437/Interspeech.2017-1111en_UK
Relation (Is Referenced By)dc.relation.isreferencedbyTodisco, M., Evans, N., Yamagishi, J., Lee, K.A. (2017) The ASVspoof 2017 Challenge: Assessing the Limits of Replay Spoofing Attack Detection. Proc. Interspeech 2017, 2-6, DOI: 10.21437/Interspeech.2017-1111.
Relation (Is Referenced By)dc.relation.isreferencedbyhttps://doi.org/10.21437/Odyssey.2018-42
Relation (Is Referenced By)dc.relation.isreferencedbyDelgado, H., Todisco, M., Sahidullah, M., Evans, N., Kinnunen, T., Lee, K.A., Yamagishi, J. (2018) ASVspoof 2017 Version 2.0: meta-data analysis and baseline enhancements . Proc. Odyssey 2018 The Speaker and Language Recognition Workshop, 296-303, DOI: 10.21437/Odyssey.2018-42.
Supersedesdc.relation.replaceshttps://doi.org/10.7488/ds/2313en_UK
Supersedesdc.relation.replaceshttps://doi.org/10.7488/ds/2301
Supersedesdc.relation.replaceshttps://doi.org/10.7488/ds/2105
Rightsdc.rightsYou are free to use this database under Creative Commons Attribution-NonCommercial License (CC-BY-NC). Regarding Creative Commons License: Attribution-NonCommercial 4.0 International (CC BY-NC 4.0), please see https://creativecommons.org/licenses/by-nc/4.0/en
Subjectdc.subjectspeechen_UK
Subjectdc.subjectspeaker verificationen_UK
Subjectdc.subjectanti-spoofingen_UK
Subjectdc.subjectpresentation attacken_UK
Subjectdc.subjectreplyen_UK
Subject Classificationdc.subject.classificationEngineeringen_UK
Titledc.titleThe 2nd Automatic Speaker Verification Spoofing and Countermeasures Challenge (ASVspoof 2017) Database, Version 2en_UK
Typedc.typesounden_UK

Download All
zip file MD5 Checksum: 112fc3ad0516fcd2b63d819a48c47af7

Files in this item

Thumbnail
Thumbnail
Thumbnail
Thumbnail
Thumbnail
Thumbnail
Thumbnail
Thumbnail
Thumbnail
Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record