Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386014758> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W4386014758 endingPage "558" @default.
- W4386014758 startingPage "549" @default.
- W4386014758 abstract "Deep learning models are now regarded as state of the art in several fields of pattern recognition, including image identification and speech recognition. This paper implements a three-dimensional convolutional neural network-based model to identify a speaker with short audio signals from the available set of speakers enrolled during the model training. In order to improve the overall operation and performance of recognition, the proposed technique uses Log-Mel spectrograms and Mel-frequency cepstral coefficients (MFCCs) with their first and second differential features as input for the 3D CNN model. Furthermore, this work comprises both the design and implementation of the CNN model and employs the same prosody elements for a Gaussian mixture model (GMM) architecture. Before being retrieved for the final speaker recognition task, the audio features are pre-processed using a pre-emphasis filter for the spectral shape compensation. As compared to the relatively complex standard GMM designs, this is a significant finding in understanding how deep learning models can be applied to the problem of speaker recognition. The CNN model is trained and tested against a freely available and comprehensive VoxCeleb1 dataset." @default.
- W4386014758 created "2023-08-21" @default.
- W4386014758 creator A5001053064 @default.
- W4386014758 creator A5001270801 @default.
- W4386014758 creator A5017313847 @default.
- W4386014758 creator A5054506776 @default.
- W4386014758 creator A5081858877 @default.
- W4386014758 creator A5087943086 @default.
- W4386014758 date "2023-01-01" @default.
- W4386014758 modified "2023-10-02" @default.
- W4386014758 title "Speaker Recognition Using 3D Convolutional Neural Network and GMM" @default.
- W4386014758 cites W1480629789 @default.
- W4386014758 cites W1991769082 @default.
- W4386014758 cites W2045556006 @default.
- W4386014758 cites W2046056978 @default.
- W4386014758 cites W2064364374 @default.
- W4386014758 cites W2111805153 @default.
- W4386014758 cites W2129244720 @default.
- W4386014758 cites W2156017586 @default.
- W4386014758 cites W2191779130 @default.
- W4386014758 cites W2402626018 @default.
- W4386014758 cites W2533523908 @default.
- W4386014758 cites W2726515241 @default.
- W4386014758 cites W2746762848 @default.
- W4386014758 cites W2770454110 @default.
- W4386014758 cites W2936774411 @default.
- W4386014758 cites W2955291451 @default.
- W4386014758 cites W2963723765 @default.
- W4386014758 cites W3015611708 @default.
- W4386014758 cites W3154715947 @default.
- W4386014758 doi "https://doi.org/10.1007/978-981-99-3691-5_47" @default.
- W4386014758 hasPublicationYear "2023" @default.
- W4386014758 type Work @default.
- W4386014758 citedByCount "0" @default.
- W4386014758 crossrefType "book-chapter" @default.
- W4386014758 hasAuthorship W4386014758A5001053064 @default.
- W4386014758 hasAuthorship W4386014758A5001270801 @default.
- W4386014758 hasAuthorship W4386014758A5017313847 @default.
- W4386014758 hasAuthorship W4386014758A5054506776 @default.
- W4386014758 hasAuthorship W4386014758A5081858877 @default.
- W4386014758 hasAuthorship W4386014758A5087943086 @default.
- W4386014758 hasConcept C108583219 @default.
- W4386014758 hasConcept C133892786 @default.
- W4386014758 hasConcept C151989614 @default.
- W4386014758 hasConcept C153180895 @default.
- W4386014758 hasConcept C154945302 @default.
- W4386014758 hasConcept C177264268 @default.
- W4386014758 hasConcept C199360897 @default.
- W4386014758 hasConcept C28490314 @default.
- W4386014758 hasConcept C41008148 @default.
- W4386014758 hasConcept C45273575 @default.
- W4386014758 hasConcept C52622490 @default.
- W4386014758 hasConcept C61224824 @default.
- W4386014758 hasConcept C81363708 @default.
- W4386014758 hasConceptScore W4386014758C108583219 @default.
- W4386014758 hasConceptScore W4386014758C133892786 @default.
- W4386014758 hasConceptScore W4386014758C151989614 @default.
- W4386014758 hasConceptScore W4386014758C153180895 @default.
- W4386014758 hasConceptScore W4386014758C154945302 @default.
- W4386014758 hasConceptScore W4386014758C177264268 @default.
- W4386014758 hasConceptScore W4386014758C199360897 @default.
- W4386014758 hasConceptScore W4386014758C28490314 @default.
- W4386014758 hasConceptScore W4386014758C41008148 @default.
- W4386014758 hasConceptScore W4386014758C45273575 @default.
- W4386014758 hasConceptScore W4386014758C52622490 @default.
- W4386014758 hasConceptScore W4386014758C61224824 @default.
- W4386014758 hasConceptScore W4386014758C81363708 @default.
- W4386014758 hasLocation W43860147581 @default.
- W4386014758 hasOpenAccess W4386014758 @default.
- W4386014758 hasPrimaryLocation W43860147581 @default.
- W4386014758 hasRelatedWork W2131673591 @default.
- W4386014758 hasRelatedWork W2189089965 @default.
- W4386014758 hasRelatedWork W2254811285 @default.
- W4386014758 hasRelatedWork W2279398222 @default.
- W4386014758 hasRelatedWork W2798765714 @default.
- W4386014758 hasRelatedWork W3085775777 @default.
- W4386014758 hasRelatedWork W3091785813 @default.
- W4386014758 hasRelatedWork W3119288895 @default.
- W4386014758 hasRelatedWork W4299822940 @default.
- W4386014758 hasRelatedWork W2367530725 @default.
- W4386014758 isParatext "false" @default.
- W4386014758 isRetracted "false" @default.
- W4386014758 workType "book-chapter" @default.