Matches in SemOpenAlex for { <https://semopenalex.org/work/W3201604899> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W3201604899 abstract "State-of-the-art spoofing speech detection methods highly depend on hand-crafted features like LFCC, MFCC, CQCC, FFT spectrum, etc. But almost for all the features, during extracting procedure, some information will be lost permanently, which may be of vital importance to spoofing detection task. Most speeches on the web, are often accompanied by music or noise. Using monaural speech separation to get human voice and then doing spoofing detection later may be a natural idea, but it has two shortcomings: two models must be trained, and during first separation step, some voice will be filtered out while noise will be kept. In this paper, we propose an end-to-end anti-spoofing model which fully consists of one-dimensional convolutional neural networks for spoofing detection under noisy conditions. The proposed system achieved an EER of 1.50% on the ASVspoof2019 logical access evaluation set. Under noisy conditions, we proposed a novel approach based on knowledge distillation, and our proposed method achieved great performance improvements compared to multi-condition training method." @default.
- W3201604899 created "2021-09-27" @default.
- W3201604899 creator A5022934107 @default.
- W3201604899 creator A5054835275 @default.
- W3201604899 creator A5076182052 @default.
- W3201604899 date "2021-07-18" @default.
- W3201604899 modified "2023-09-24" @default.
- W3201604899 title "End-to-end spoofing speech detection and knowledge distillation under noisy conditions" @default.
- W3201604899 cites W1034159276 @default.
- W3201604899 cites W1600744878 @default.
- W3201604899 cites W1903029394 @default.
- W3201604899 cites W1979482308 @default.
- W3201604899 cites W2062164080 @default.
- W3201604899 cites W2064675550 @default.
- W3201604899 cites W2079735306 @default.
- W3201604899 cites W2129379984 @default.
- W3201604899 cites W2148154194 @default.
- W3201604899 cites W2191779130 @default.
- W3201604899 cites W2297648422 @default.
- W3201604899 cites W2303197844 @default.
- W3201604899 cites W2503204202 @default.
- W3201604899 cites W2512302098 @default.
- W3201604899 cites W2565961899 @default.
- W3201604899 cites W2588445447 @default.
- W3201604899 cites W2590129515 @default.
- W3201604899 cites W2592641653 @default.
- W3201604899 cites W2620998106 @default.
- W3201604899 cites W2651834199 @default.
- W3201604899 cites W2739879705 @default.
- W3201604899 cites W2740489634 @default.
- W3201604899 cites W2810350850 @default.
- W3201604899 cites W2889023442 @default.
- W3201604899 cites W2962734576 @default.
- W3201604899 cites W2963154580 @default.
- W3201604899 cites W2963351448 @default.
- W3201604899 cites W2963508548 @default.
- W3201604899 cites W2967606780 @default.
- W3201604899 cites W2972811785 @default.
- W3201604899 cites W3096333737 @default.
- W3201604899 doi "https://doi.org/10.1109/ijcnn52387.2021.9534312" @default.
- W3201604899 hasPublicationYear "2021" @default.
- W3201604899 type Work @default.
- W3201604899 sameAs 3201604899 @default.
- W3201604899 citedByCount "1" @default.
- W3201604899 countsByYear W32016048992023 @default.
- W3201604899 crossrefType "proceedings-article" @default.
- W3201604899 hasAuthorship W3201604899A5022934107 @default.
- W3201604899 hasAuthorship W3201604899A5054835275 @default.
- W3201604899 hasAuthorship W3201604899A5076182052 @default.
- W3201604899 hasConcept C102894143 @default.
- W3201604899 hasConcept C115961682 @default.
- W3201604899 hasConcept C151989614 @default.
- W3201604899 hasConcept C153180895 @default.
- W3201604899 hasConcept C154945302 @default.
- W3201604899 hasConcept C167900197 @default.
- W3201604899 hasConcept C177264268 @default.
- W3201604899 hasConcept C199360897 @default.
- W3201604899 hasConcept C28490314 @default.
- W3201604899 hasConcept C31258907 @default.
- W3201604899 hasConcept C41008148 @default.
- W3201604899 hasConcept C52622490 @default.
- W3201604899 hasConcept C81363708 @default.
- W3201604899 hasConcept C99498987 @default.
- W3201604899 hasConceptScore W3201604899C102894143 @default.
- W3201604899 hasConceptScore W3201604899C115961682 @default.
- W3201604899 hasConceptScore W3201604899C151989614 @default.
- W3201604899 hasConceptScore W3201604899C153180895 @default.
- W3201604899 hasConceptScore W3201604899C154945302 @default.
- W3201604899 hasConceptScore W3201604899C167900197 @default.
- W3201604899 hasConceptScore W3201604899C177264268 @default.
- W3201604899 hasConceptScore W3201604899C199360897 @default.
- W3201604899 hasConceptScore W3201604899C28490314 @default.
- W3201604899 hasConceptScore W3201604899C31258907 @default.
- W3201604899 hasConceptScore W3201604899C41008148 @default.
- W3201604899 hasConceptScore W3201604899C52622490 @default.
- W3201604899 hasConceptScore W3201604899C81363708 @default.
- W3201604899 hasConceptScore W3201604899C99498987 @default.
- W3201604899 hasLocation W32016048991 @default.
- W3201604899 hasOpenAccess W3201604899 @default.
- W3201604899 hasPrimaryLocation W32016048991 @default.
- W3201604899 hasRelatedWork W2059299633 @default.
- W3201604899 hasRelatedWork W2518599539 @default.
- W3201604899 hasRelatedWork W2732542196 @default.
- W3201604899 hasRelatedWork W2940977206 @default.
- W3201604899 hasRelatedWork W2969680539 @default.
- W3201604899 hasRelatedWork W2977314777 @default.
- W3201604899 hasRelatedWork W2988724699 @default.
- W3201604899 hasRelatedWork W2995914718 @default.
- W3201604899 hasRelatedWork W3004378172 @default.
- W3201604899 hasRelatedWork W4307883119 @default.
- W3201604899 isParatext "false" @default.
- W3201604899 isRetracted "false" @default.
- W3201604899 magId "3201604899" @default.
- W3201604899 workType "article" @default.