Matches in SemOpenAlex for { <https://semopenalex.org/work/W3092742905> ?p ?o ?g. }
- W3092742905 abstract "The Automatic Speaker Verification Spoofing and Countermeasures Challenges motivate research in protecting speech biometric systems against a variety of different access attacks. The 2017 edition focused on replay spoofing attacks, and involved participants building and training systems on a provided dataset (ASVspoof 2017). More than 60 research papers have so far been published with this dataset, but none have sought to answer why countermeasures appear successful in detecting spoofing attacks. This article shows how artefacts inherent to the dataset may be contributing to the apparent success of published systems. We first inspect the ASVspoof 2017 dataset and summarize various artefacts present in the dataset. Second, we demonstrate how countermeasure models can exploit these artefacts to appear successful in this dataset. Third, for reliable and robust performance estimates on this dataset we propose discarding nonspeech segments and silence before and after the speech utterance during training and inference. We create speech start and endpoint annotations in the dataset and demonstrate how using them helps countermeasure models become less vulnerable from being manipulated using artefacts found in the dataset. Finally, we provide several new benchmark results for both frame-level and utterance-level models that can serve as new baselines on this dataset." @default.
- W3092742905 created "2020-10-22" @default.
- W3092742905 creator A5018585368 @default.
- W3092742905 creator A5054217723 @default.
- W3092742905 creator A5084672392 @default.
- W3092742905 date "2020-10-15" @default.
- W3092742905 modified "2023-10-16" @default.
- W3092742905 title "Dataset artefacts in anti-spoofing systems: a case study on the ASVspoof 2017 benchmark" @default.
- W3092742905 cites W1506806321 @default.
- W3092742905 cites W1550612414 @default.
- W3092742905 cites W1660353176 @default.
- W3092742905 cites W1673923490 @default.
- W3092742905 cites W1932198206 @default.
- W3092742905 cites W1980581462 @default.
- W3092742905 cites W2031342017 @default.
- W3092742905 cites W2044879407 @default.
- W3092742905 cites W2069883713 @default.
- W3092742905 cites W2074619556 @default.
- W3092742905 cites W2101234009 @default.
- W3092742905 cites W2133420453 @default.
- W3092742905 cites W2144620969 @default.
- W3092742905 cites W2176804518 @default.
- W3092742905 cites W2414346124 @default.
- W3092742905 cites W2542381826 @default.
- W3092742905 cites W2562863628 @default.
- W3092742905 cites W2566903824 @default.
- W3092742905 cites W2585365199 @default.
- W3092742905 cites W2590129515 @default.
- W3092742905 cites W2727650337 @default.
- W3092742905 cites W2745896134 @default.
- W3092742905 cites W2747024632 @default.
- W3092742905 cites W2747182415 @default.
- W3092742905 cites W2747419477 @default.
- W3092742905 cites W2747872086 @default.
- W3092742905 cites W2750335806 @default.
- W3092742905 cites W2802820526 @default.
- W3092742905 cites W2807325376 @default.
- W3092742905 cites W2888980597 @default.
- W3092742905 cites W2888989492 @default.
- W3092742905 cites W2889084898 @default.
- W3092742905 cites W2889138442 @default.
- W3092742905 cites W2889361425 @default.
- W3092742905 cites W2889469280 @default.
- W3092742905 cites W2890964092 @default.
- W3092742905 cites W2891042661 @default.
- W3092742905 cites W2913181996 @default.
- W3092742905 cites W2922143889 @default.
- W3092742905 cites W2922490899 @default.
- W3092742905 cites W2936654294 @default.
- W3092742905 cites W2949650786 @default.
- W3092742905 cites W2954930777 @default.
- W3092742905 cites W2964002811 @default.
- W3092742905 cites W2964052309 @default.
- W3092742905 cites W2967606780 @default.
- W3092742905 cites W2969462144 @default.
- W3092742905 cites W2972465261 @default.
- W3092742905 cites W2973143722 @default.
- W3092742905 cites W2973164265 @default.
- W3092742905 cites W2979544394 @default.
- W3092742905 cites W2999615834 @default.
- W3092742905 cites W3102568015 @default.
- W3092742905 cites W3210835518 @default.
- W3092742905 cites W3215160418 @default.
- W3092742905 cites W8362967 @default.
- W3092742905 hasPublicationYear "2020" @default.
- W3092742905 type Work @default.
- W3092742905 sameAs 3092742905 @default.
- W3092742905 citedByCount "0" @default.
- W3092742905 crossrefType "posted-content" @default.
- W3092742905 hasAuthorship W3092742905A5018585368 @default.
- W3092742905 hasAuthorship W3092742905A5054217723 @default.
- W3092742905 hasAuthorship W3092742905A5084672392 @default.
- W3092742905 hasConcept C119857082 @default.
- W3092742905 hasConcept C126042441 @default.
- W3092742905 hasConcept C13280743 @default.
- W3092742905 hasConcept C136197465 @default.
- W3092742905 hasConcept C154945302 @default.
- W3092742905 hasConcept C165696696 @default.
- W3092742905 hasConcept C167900197 @default.
- W3092742905 hasConcept C184297639 @default.
- W3092742905 hasConcept C185798385 @default.
- W3092742905 hasConcept C205649164 @default.
- W3092742905 hasConcept C2775852435 @default.
- W3092742905 hasConcept C2776214188 @default.
- W3092742905 hasConcept C28490314 @default.
- W3092742905 hasConcept C38652104 @default.
- W3092742905 hasConcept C41008148 @default.
- W3092742905 hasConcept C76155785 @default.
- W3092742905 hasConceptScore W3092742905C119857082 @default.
- W3092742905 hasConceptScore W3092742905C126042441 @default.
- W3092742905 hasConceptScore W3092742905C13280743 @default.
- W3092742905 hasConceptScore W3092742905C136197465 @default.
- W3092742905 hasConceptScore W3092742905C154945302 @default.
- W3092742905 hasConceptScore W3092742905C165696696 @default.
- W3092742905 hasConceptScore W3092742905C167900197 @default.
- W3092742905 hasConceptScore W3092742905C184297639 @default.
- W3092742905 hasConceptScore W3092742905C185798385 @default.
- W3092742905 hasConceptScore W3092742905C205649164 @default.
- W3092742905 hasConceptScore W3092742905C2775852435 @default.
- W3092742905 hasConceptScore W3092742905C2776214188 @default.