Matches in SemOpenAlex for { <https://semopenalex.org/work/W4224256913> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W4224256913 abstract "This paper describes our best system and methodology for ADD 2022: The First Audio Deep Synthesis Detection Challenge[1]. The very same system was used for both two rounds of evaluation in Track 3.2 with similar training methodology. The first round of Track 3.2 data is generated from Text-to-Speech(TTS) or voice conversion (VC) algorithms, while the second round of data consists of generated fake audio from other participants in Track 3.1, aming to spoof our systems. Our systems uses a standard 34-layer ResNet [2], with multi-head attention pooling [3] to learn the discriminative embedding for fake audio and spoof detection. We further utilize neural stitching to boost the model’s generalization capability in order to perform equally well in different tasks, and more details will be explained in the following sessions. The experiments show that our proposed method outperforms all other systems with 10.1% equal error rate(EER) in Track 3.2." @default.
- W4224256913 created "2022-04-26" @default.
- W4224256913 creator A5037905363 @default.
- W4224256913 creator A5038813097 @default.
- W4224256913 creator A5059915555 @default.
- W4224256913 creator A5081173423 @default.
- W4224256913 creator A5082924224 @default.
- W4224256913 creator A5090814066 @default.
- W4224256913 date "2022-05-23" @default.
- W4224256913 modified "2023-10-14" @default.
- W4224256913 title "Audio Deepfake Detection System with Neural Stitching for ADD 2022" @default.
- W4224256913 cites W1912570122 @default.
- W4224256913 cites W2088399049 @default.
- W4224256913 cites W2295634712 @default.
- W4224256913 cites W2794506738 @default.
- W4224256913 cites W2807627734 @default.
- W4224256913 cites W2936774411 @default.
- W4224256913 cites W2963077989 @default.
- W4224256913 cites W2963351448 @default.
- W4224256913 cites W2964350391 @default.
- W4224256913 cites W2967606780 @default.
- W4224256913 cites W2972369255 @default.
- W4224256913 cites W2998508940 @default.
- W4224256913 cites W3015197287 @default.
- W4224256913 cites W3024920698 @default.
- W4224256913 cites W3162427973 @default.
- W4224256913 cites W3198129070 @default.
- W4224256913 cites W4221138880 @default.
- W4224256913 doi "https://doi.org/10.1109/icassp43922.2022.9746820" @default.
- W4224256913 hasPublicationYear "2022" @default.
- W4224256913 type Work @default.
- W4224256913 citedByCount "2" @default.
- W4224256913 countsByYear W42242569132022 @default.
- W4224256913 crossrefType "proceedings-article" @default.
- W4224256913 hasAuthorship W4224256913A5037905363 @default.
- W4224256913 hasAuthorship W4224256913A5038813097 @default.
- W4224256913 hasAuthorship W4224256913A5059915555 @default.
- W4224256913 hasAuthorship W4224256913A5081173423 @default.
- W4224256913 hasAuthorship W4224256913A5082924224 @default.
- W4224256913 hasAuthorship W4224256913A5090814066 @default.
- W4224256913 hasBestOaLocation W42242569132 @default.
- W4224256913 hasConcept C111919701 @default.
- W4224256913 hasConcept C134306372 @default.
- W4224256913 hasConcept C153180895 @default.
- W4224256913 hasConcept C154945302 @default.
- W4224256913 hasConcept C177148314 @default.
- W4224256913 hasConcept C28490314 @default.
- W4224256913 hasConcept C29081049 @default.
- W4224256913 hasConcept C33923547 @default.
- W4224256913 hasConcept C40969351 @default.
- W4224256913 hasConcept C41008148 @default.
- W4224256913 hasConcept C41608201 @default.
- W4224256913 hasConcept C70437156 @default.
- W4224256913 hasConcept C89992363 @default.
- W4224256913 hasConcept C97931131 @default.
- W4224256913 hasConceptScore W4224256913C111919701 @default.
- W4224256913 hasConceptScore W4224256913C134306372 @default.
- W4224256913 hasConceptScore W4224256913C153180895 @default.
- W4224256913 hasConceptScore W4224256913C154945302 @default.
- W4224256913 hasConceptScore W4224256913C177148314 @default.
- W4224256913 hasConceptScore W4224256913C28490314 @default.
- W4224256913 hasConceptScore W4224256913C29081049 @default.
- W4224256913 hasConceptScore W4224256913C33923547 @default.
- W4224256913 hasConceptScore W4224256913C40969351 @default.
- W4224256913 hasConceptScore W4224256913C41008148 @default.
- W4224256913 hasConceptScore W4224256913C41608201 @default.
- W4224256913 hasConceptScore W4224256913C70437156 @default.
- W4224256913 hasConceptScore W4224256913C89992363 @default.
- W4224256913 hasConceptScore W4224256913C97931131 @default.
- W4224256913 hasLocation W42242569131 @default.
- W4224256913 hasLocation W42242569132 @default.
- W4224256913 hasOpenAccess W4224256913 @default.
- W4224256913 hasPrimaryLocation W42242569131 @default.
- W4224256913 hasRelatedWork W1652783584 @default.
- W4224256913 hasRelatedWork W1990254706 @default.
- W4224256913 hasRelatedWork W2024160000 @default.
- W4224256913 hasRelatedWork W2404514746 @default.
- W4224256913 hasRelatedWork W2729514902 @default.
- W4224256913 hasRelatedWork W2911599258 @default.
- W4224256913 hasRelatedWork W2973523586 @default.
- W4224256913 hasRelatedWork W2982817420 @default.
- W4224256913 hasRelatedWork W4288029399 @default.
- W4224256913 hasRelatedWork W4313591539 @default.
- W4224256913 isParatext "false" @default.
- W4224256913 isRetracted "false" @default.
- W4224256913 workType "article" @default.