FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2332932830> ?p ?o ?g. }

• W2332932830 abstract "Robust Speaker Recognition (SR) has been a focus of attention for researchers since long. The advancement in speech-aided technologies especially biometrics highlights the necessity of foolproof SR systems. However, the performance of a SR system critically depends on the quality of speech features used to represent the speaker-specific information. This research aims at extracting the speaker-specific information from Mel-frequency Cepstral Coefficients (MFCCs) using deep learning.Speech is a mixture of various information components that include linguistic, speaker-specific and speaker?s emotional state information. Feature extraction for each information component is inevitable in different speech-related tasks for robust performance. However, almost all forms of speech representation carry all the information as a whole, which is responsible for the compromised performances by SR systems. Motivated by the complex problem solving ability of deep architectures by learning high-level task-specific information in the data, we propose a novel Deep Neural Architecture (DNA) to extract speaker-specific information (SI) from MFCCs, a popular frequency domain speech signal representation. A two-stage learning strategy is adopted, which is based on unsupervised training for network initialisation followed by regularised contrastive learning.To train our network in the 2nd stage, we devise a contrastive loss function to discriminate the speakers on the basis of their intrinsic statistical patterns, distributed in the representations yielded by our deep network. This is achieved in the contrastive pair-wise comparison of these representations for similar or dissimilar speakers. To improve the generalisation and reduce the interference of environmental effects with the speaker-specific representation, we regulate the contrastive loss with the data reconstruction loss in a multi-objective optimisation.A detailed study has been done to analyse the parametric space in training the proposed deep architecture for optimum performance. Finally we compare the performance of our learned speaker-specific representations with several state-of-the-art techniques in speaker verification and speaker segmentation tasks. It is evident that the representations acquired through learned DNA are invariant and comparatively less sensitive to the text, language and environmental variability." @default.
• W2332932830 created "2016-06-24" @default.
• W2332932830 creator A5028240974 @default.
• W2332932830 date "2012-08-21" @default.
• W2332932830 modified "2023-09-23" @default.
• W2332932830 title "Learning Speaker-Specific Characteristics With Deep Neural Architecture" @default.
• W2332932830 hasPublicationYear "2012" @default.
• W2332932830 type Work @default.
• W2332932830 sameAs 2332932830 @default.
• W2332932830 citedByCount "1" @default.
• W2332932830 countsByYear W23329328302019 @default.
• W2332932830 crossrefType "journal-article" @default.
• W2332932830 hasAuthorship W2332932830A5028240974 @default.
• W2332932830 hasConcept C108583219 @default.
• W2332932830 hasConcept C120665830 @default.
• W2332932830 hasConcept C121332964 @default.
• W2332932830 hasConcept C133892786 @default.
• W2332932830 hasConcept C149838564 @default.
• W2332932830 hasConcept C154945302 @default.
• W2332932830 hasConcept C162324750 @default.
• W2332932830 hasConcept C168167062 @default.
• W2332932830 hasConcept C17744445 @default.
• W2332932830 hasConcept C187736073 @default.
• W2332932830 hasConcept C192209626 @default.
• W2332932830 hasConcept C199539241 @default.
• W2332932830 hasConcept C204321447 @default.
• W2332932830 hasConcept C2776359362 @default.
• W2332932830 hasConcept C2780451532 @default.
• W2332932830 hasConcept C28490314 @default.
• W2332932830 hasConcept C41008148 @default.
• W2332932830 hasConcept C50644808 @default.
• W2332932830 hasConcept C52622490 @default.
• W2332932830 hasConcept C59404180 @default.
• W2332932830 hasConcept C94625758 @default.
• W2332932830 hasConcept C97355855 @default.
• W2332932830 hasConceptScore W2332932830C108583219 @default.
• W2332932830 hasConceptScore W2332932830C120665830 @default.
• W2332932830 hasConceptScore W2332932830C121332964 @default.
• W2332932830 hasConceptScore W2332932830C133892786 @default.
• W2332932830 hasConceptScore W2332932830C149838564 @default.
• W2332932830 hasConceptScore W2332932830C154945302 @default.
• W2332932830 hasConceptScore W2332932830C162324750 @default.
• W2332932830 hasConceptScore W2332932830C168167062 @default.
• W2332932830 hasConceptScore W2332932830C17744445 @default.
• W2332932830 hasConceptScore W2332932830C187736073 @default.
• W2332932830 hasConceptScore W2332932830C192209626 @default.
• W2332932830 hasConceptScore W2332932830C199539241 @default.
• W2332932830 hasConceptScore W2332932830C204321447 @default.
• W2332932830 hasConceptScore W2332932830C2776359362 @default.
• W2332932830 hasConceptScore W2332932830C2780451532 @default.
• W2332932830 hasConceptScore W2332932830C28490314 @default.
• W2332932830 hasConceptScore W2332932830C41008148 @default.
• W2332932830 hasConceptScore W2332932830C50644808 @default.
• W2332932830 hasConceptScore W2332932830C52622490 @default.
• W2332932830 hasConceptScore W2332932830C59404180 @default.
• W2332932830 hasConceptScore W2332932830C94625758 @default.
• W2332932830 hasConceptScore W2332932830C97355855 @default.
• W2332932830 hasLocation W23329328301 @default.
• W2332932830 hasOpenAccess W2332932830 @default.
• W2332932830 hasPrimaryLocation W23329328301 @default.
• W2332932830 hasRelatedWork W1492587309 @default.
• W2332932830 hasRelatedWork W2099797668 @default.
• W2332932830 hasRelatedWork W2305940569 @default.
• W2332932830 hasRelatedWork W2489394779 @default.
• W2332932830 hasRelatedWork W2520176975 @default.
• W2332932830 hasRelatedWork W2563686518 @default.
• W2332932830 hasRelatedWork W2765233562 @default.
• W2332932830 hasRelatedWork W2767395757 @default.
• W2332932830 hasRelatedWork W2790216641 @default.
• W2332932830 hasRelatedWork W2889226978 @default.
• W2332932830 hasRelatedWork W2972943112 @default.
• W2332932830 hasRelatedWork W3005914302 @default.
• W2332932830 hasRelatedWork W3016048045 @default.
• W2332932830 hasRelatedWork W3046954891 @default.
• W2332932830 hasRelatedWork W3097938098 @default.
• W2332932830 hasRelatedWork W3120557855 @default.
• W2332932830 hasRelatedWork W3163929126 @default.
• W2332932830 hasRelatedWork W3198815374 @default.
• W2332932830 hasRelatedWork W3201363892 @default.
• W2332932830 hasRelatedWork W32689833 @default.
• W2332932830 isParatext "false" @default.
• W2332932830 isRetracted "false" @default.
• W2332932830 magId "2332932830" @default.
• W2332932830 workType "article" @default.