FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3110588169> ?p ?o ?g. }

• W3110588169 endingPage "3028" @default.
• W3110588169 startingPage "3018" @default.
• W3110588169 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.
• W3110588169 created "2020-12-07" @default.
• W3110588169 creator A5018585368 @default.
• W3110588169 creator A5054217723 @default.
• W3110588169 creator A5084672392 @default.
• W3110588169 date "2020-01-01" @default.
• W3110588169 modified "2023-10-16" @default.
• W3110588169 title "Dataset Artefacts in Anti-Spoofing Systems: A Case Study on the ASVspoof 2017 Benchmark" @default.
• W3110588169 cites W1506806321 @default.
• W3110588169 cites W1550612414 @default.
• W3110588169 cites W1932198206 @default.
• W3110588169 cites W2031342017 @default.
• W3110588169 cites W2069883713 @default.
• W3110588169 cites W2074619556 @default.
• W3110588169 cites W2101234009 @default.
• W3110588169 cites W2133420453 @default.
• W3110588169 cites W2144620969 @default.
• W3110588169 cites W2150769028 @default.
• W3110588169 cites W2176804518 @default.
• W3110588169 cites W2178339699 @default.
• W3110588169 cites W2542381826 @default.
• W3110588169 cites W2566903824 @default.
• W3110588169 cites W2585365199 @default.
• W3110588169 cites W2590129515 @default.
• W3110588169 cites W2727650337 @default.
• W3110588169 cites W2736287575 @default.
• W3110588169 cites W2745896134 @default.
• W3110588169 cites W2747024632 @default.
• W3110588169 cites W2747182415 @default.
• W3110588169 cites W2747419477 @default.
• W3110588169 cites W2747872086 @default.
• W3110588169 cites W2750335806 @default.
• W3110588169 cites W2757251151 @default.
• W3110588169 cites W2802820526 @default.
• W3110588169 cites W2807325376 @default.
• W3110588169 cites W2888980597 @default.
• W3110588169 cites W2888989492 @default.
• W3110588169 cites W2889084898 @default.
• W3110588169 cites W2889138442 @default.
• W3110588169 cites W2889361425 @default.
• W3110588169 cites W2889469280 @default.
• W3110588169 cites W2890964092 @default.
• W3110588169 cites W2891042661 @default.
• W3110588169 cites W2913181996 @default.
• W3110588169 cites W2922143889 @default.
• W3110588169 cites W2922490899 @default.
• W3110588169 cites W2936654294 @default.
• W3110588169 cites W2949650786 @default.
• W3110588169 cites W2954930777 @default.
• W3110588169 cites W2963460857 @default.
• W3110588169 cites W2964002811 @default.
• W3110588169 cites W2964052309 @default.
• W3110588169 cites W2964075883 @default.
• W3110588169 cites W2967606780 @default.
• W3110588169 cites W2969462144 @default.
• W3110588169 cites W2972465261 @default.
• W3110588169 cites W2973143722 @default.
• W3110588169 cites W2973164265 @default.
• W3110588169 cites W2979544394 @default.
• W3110588169 cites W2999615834 @default.
• W3110588169 cites W3210835518 @default.
• W3110588169 cites W8362967 @default.
• W3110588169 doi "https://doi.org/10.1109/taslp.2020.3036777" @default.
• W3110588169 hasPublicationYear "2020" @default.
• W3110588169 type Work @default.
• W3110588169 sameAs 3110588169 @default.
• W3110588169 citedByCount "8" @default.
• W3110588169 countsByYear W31105881692021 @default.
• W3110588169 countsByYear W31105881692022 @default.
• W3110588169 countsByYear W31105881692023 @default.
• W3110588169 crossrefType "journal-article" @default.
• W3110588169 hasAuthorship W3110588169A5018585368 @default.
• W3110588169 hasAuthorship W3110588169A5054217723 @default.
• W3110588169 hasAuthorship W3110588169A5084672392 @default.
• W3110588169 hasBestOaLocation W31105881692 @default.
• W3110588169 hasConcept C119857082 @default.
• W3110588169 hasConcept C126042441 @default.
• W3110588169 hasConcept C13280743 @default.
• W3110588169 hasConcept C136197465 @default.
• W3110588169 hasConcept C154945302 @default.
• W3110588169 hasConcept C165696696 @default.
• W3110588169 hasConcept C167900197 @default.
• W3110588169 hasConcept C184297639 @default.
• W3110588169 hasConcept C185798385 @default.
• W3110588169 hasConcept C205649164 @default.
• W3110588169 hasConcept C2775852435 @default.
• W3110588169 hasConcept C2776214188 @default.
• W3110588169 hasConcept C28490314 @default.
• W3110588169 hasConcept C38652104 @default.
• W3110588169 hasConcept C41008148 @default.
• W3110588169 hasConcept C76155785 @default.
• W3110588169 hasConceptScore W3110588169C119857082 @default.
• W3110588169 hasConceptScore W3110588169C126042441 @default.
• W3110588169 hasConceptScore W3110588169C13280743 @default.
• W3110588169 hasConceptScore W3110588169C136197465 @default.
• W3110588169 hasConceptScore W3110588169C154945302 @default.
• W3110588169 hasConceptScore W3110588169C165696696 @default.
• W3110588169 hasConceptScore W3110588169C167900197 @default.

• next