Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385696475> ?p ?o ?g. }
- W4385696475 endingPage "84513" @default.
- W4385696475 startingPage "84500" @default.
- W4385696475 abstract "Speaker recognition is an indispensable technology for biometrics. It distinguishes individuals based on their vocal patterns. In this paper, a joint confirmation method based on the Akaike Information Criterion (AIC) of reconstruction error (REE) and time complexity (AIC-Time joint confirmation method) is proposed to select the optimal decomposition rank of NMF. Furthermore, non-negative matrix factorization (NMF) is applied to the spectrogram to generate speaker features. The network for speaker recognition is based on Convolutional Neural Networks combining Squeeze Excitation (SE) modules with ResNeXt, and the best combination is explored experimentally. The SE module conducts a channel-level adaptive adjustment of the feature maps, reducing redundancy and noise interference while improving feature extraction efficiency and accuracy. The ResNeXt convolutional neural network concurrently executes multiple convolutional kernels, acquiring richer feature information. The experimental results demonstrate that compared to speaker recognition based on Gaussian mixture models (GMM), Visual Geometry Group Network (VGGNet), ResNet, and SE-ResNeXt using spectrograms, this method increases the accuracy by an average of 5.8% and 16.24% under the overlaid of babble and factory1 noise with different signal-to-noise ratios, respectively. In the short speech test, the test set is short speech of 1s and 2s, and the noise is superimposed. Compared with other methods, the recognition rate is increased by an average of 8.67% and 11.72%, respectively." @default.
- W4385696475 created "2023-08-10" @default.
- W4385696475 creator A5004035476 @default.
- W4385696475 creator A5016770120 @default.
- W4385696475 creator A5020271369 @default.
- W4385696475 creator A5034904172 @default.
- W4385696475 date "2023-01-01" @default.
- W4385696475 modified "2023-10-17" @default.
- W4385696475 title "A Method for Speaker Recognition Based on the ResNeXt Network Under Challenging Acoustic Conditions" @default.
- W4385696475 cites W1014281907 @default.
- W4385696475 cites W1143553410 @default.
- W4385696475 cites W1555814299 @default.
- W4385696475 cites W1996601463 @default.
- W4385696475 cites W2003780581 @default.
- W4385696475 cites W2046056978 @default.
- W4385696475 cites W2117539524 @default.
- W4385696475 cites W2183341477 @default.
- W4385696475 cites W2294255557 @default.
- W4385696475 cites W2412385789 @default.
- W4385696475 cites W2549139847 @default.
- W4385696475 cites W2607177476 @default.
- W4385696475 cites W2752782242 @default.
- W4385696475 cites W2793150943 @default.
- W4385696475 cites W2800776862 @default.
- W4385696475 cites W2810478609 @default.
- W4385696475 cites W2889093877 @default.
- W4385696475 cites W2890964092 @default.
- W4385696475 cites W2892929556 @default.
- W4385696475 cites W2902422112 @default.
- W4385696475 cites W2909324822 @default.
- W4385696475 cites W2927182142 @default.
- W4385696475 cites W2946508582 @default.
- W4385696475 cites W2954911682 @default.
- W4385696475 cites W2963242190 @default.
- W4385696475 cites W2963420686 @default.
- W4385696475 cites W3000659041 @default.
- W4385696475 cites W3005759882 @default.
- W4385696475 cites W3017925328 @default.
- W4385696475 cites W3025787433 @default.
- W4385696475 cites W3040156878 @default.
- W4385696475 cites W3048835987 @default.
- W4385696475 cites W3082314721 @default.
- W4385696475 cites W3100202987 @default.
- W4385696475 cites W3121150787 @default.
- W4385696475 cites W3135760902 @default.
- W4385696475 cites W3136208589 @default.
- W4385696475 cites W3140854437 @default.
- W4385696475 cites W3142516134 @default.
- W4385696475 cites W3156052130 @default.
- W4385696475 cites W3199481609 @default.
- W4385696475 cites W4230984366 @default.
- W4385696475 cites W4289781874 @default.
- W4385696475 cites W4293104133 @default.
- W4385696475 cites W4312214407 @default.
- W4385696475 doi "https://doi.org/10.1109/access.2023.3303485" @default.
- W4385696475 hasPublicationYear "2023" @default.
- W4385696475 type Work @default.
- W4385696475 citedByCount "0" @default.
- W4385696475 crossrefType "journal-article" @default.
- W4385696475 hasAuthorship W4385696475A5004035476 @default.
- W4385696475 hasAuthorship W4385696475A5016770120 @default.
- W4385696475 hasAuthorship W4385696475A5020271369 @default.
- W4385696475 hasAuthorship W4385696475A5034904172 @default.
- W4385696475 hasBestOaLocation W43856964751 @default.
- W4385696475 hasConcept C121332964 @default.
- W4385696475 hasConcept C133892786 @default.
- W4385696475 hasConcept C148483581 @default.
- W4385696475 hasConcept C152671427 @default.
- W4385696475 hasConcept C153180895 @default.
- W4385696475 hasConcept C154945302 @default.
- W4385696475 hasConcept C158693339 @default.
- W4385696475 hasConcept C28490314 @default.
- W4385696475 hasConcept C40969351 @default.
- W4385696475 hasConcept C41008148 @default.
- W4385696475 hasConcept C42355184 @default.
- W4385696475 hasConcept C45273575 @default.
- W4385696475 hasConcept C52622490 @default.
- W4385696475 hasConcept C62520636 @default.
- W4385696475 hasConcept C81363708 @default.
- W4385696475 hasConceptScore W4385696475C121332964 @default.
- W4385696475 hasConceptScore W4385696475C133892786 @default.
- W4385696475 hasConceptScore W4385696475C148483581 @default.
- W4385696475 hasConceptScore W4385696475C152671427 @default.
- W4385696475 hasConceptScore W4385696475C153180895 @default.
- W4385696475 hasConceptScore W4385696475C154945302 @default.
- W4385696475 hasConceptScore W4385696475C158693339 @default.
- W4385696475 hasConceptScore W4385696475C28490314 @default.
- W4385696475 hasConceptScore W4385696475C40969351 @default.
- W4385696475 hasConceptScore W4385696475C41008148 @default.
- W4385696475 hasConceptScore W4385696475C42355184 @default.
- W4385696475 hasConceptScore W4385696475C45273575 @default.
- W4385696475 hasConceptScore W4385696475C52622490 @default.
- W4385696475 hasConceptScore W4385696475C62520636 @default.
- W4385696475 hasConceptScore W4385696475C81363708 @default.
- W4385696475 hasFunder F4320321001 @default.
- W4385696475 hasLocation W43856964751 @default.
- W4385696475 hasOpenAccess W4385696475 @default.
- W4385696475 hasPrimaryLocation W43856964751 @default.