FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2914242616> ?p ?o ?g. }

• W2914242616 endingPage "374" @default.
• W2914242616 startingPage "364" @default.
• W2914242616 abstract "Deep neural networks (DNNs) have achieved significant success in the field of automatic speech recognition. One main advantage of DNNs is automatic feature extraction without human intervention. However, adaptation under limited available data remains a major challenge for DNN-based systems because of their enormous free parameters. In this paper, we propose a filterbank-incorporated DNN that incorporates a filterbank layer that presents the filter shape/center frequency and a DNN-based acoustic model. The filterbank layer and the following networks of the proposed model are trained jointly by exploiting the advantages of the hierarchical feature extraction, while most systems use pre-defined mel-scale filterbank features as input acoustic features to DNNs. Filters in the filterbank layer are parameterized to represent speaker characteristics while minimizing a number of parameters. The optimization of one type of parameters corresponds to the Vocal Tract Length Normalization (VTLN), and another type corresponds to feature-space Maximum Linear Likelihood Regression (fMLLR) and feature-space Discriminative Linear Regression (fDLR). Since the filterbank layer consists of just a few parameters, it is advantageous in adaptation under limited available data. In the experiment, filterbank-incorporated DNNs showed effectiveness in speaker/gender adaptations under limited adaptation data. Experimental results on CSJ task demonstrate that the adaptation of proposed model showed 5.8% word error reduction ratio with 10 utterances against the un-adapted model." @default.
• W2914242616 created "2019-02-21" @default.
• W2914242616 creator A5018428974 @default.
• W2914242616 creator A5032115994 @default.
• W2914242616 creator A5046874748 @default.
• W2914242616 creator A5077186384 @default.
• W2914242616 date "2019-02-01" @default.
• W2914242616 modified "2023-10-11" @default.
• W2914242616 title "Discriminative Learning of Filterbank Layer within Deep Neural Network Based Speech Recognition for Speaker Adaptation" @default.
• W2914242616 cites W1616590059 @default.
• W2914242616 cites W16408605 @default.
• W2914242616 cites W1770758908 @default.
• W2914242616 cites W1964815273 @default.
• W2914242616 cites W1969851134 @default.
• W2914242616 cites W1989549063 @default.
• W2914242616 cites W1995562189 @default.
• W2914242616 cites W2037740282 @default.
• W2914242616 cites W2057498692 @default.
• W2914242616 cites W2079623482 @default.
• W2914242616 cites W2112021726 @default.
• W2914242616 cites W2112739286 @default.
• W2914242616 cites W2124449749 @default.
• W2914242616 cites W2135894295 @default.
• W2914242616 cites W2160306971 @default.
• W2914242616 cites W2160815625 @default.
• W2914242616 cites W2163786726 @default.
• W2914242616 cites W2166661046 @default.
• W2914242616 cites W2239847623 @default.
• W2914242616 cites W2276408190 @default.
• W2914242616 cites W2295119550 @default.
• W2914242616 cites W2343348669 @default.
• W2914242616 cites W2394954022 @default.
• W2914242616 cites W2398826216 @default.
• W2914242616 cites W2404620314 @default.
• W2914242616 cites W2406171445 @default.
• W2914242616 cites W2508162385 @default.
• W2914242616 cites W2508627142 @default.
• W2914242616 cites W2593451766 @default.
• W2914242616 cites W2654517624 @default.
• W2914242616 cites W2658929981 @default.
• W2914242616 cites W2710239804 @default.
• W2914242616 cites W2735006420 @default.
• W2914242616 cites W2963669405 @default.
• W2914242616 cites W82936479 @default.
• W2914242616 doi "https://doi.org/10.1587/transinf.2018edp7252" @default.
• W2914242616 hasPublicationYear "2019" @default.
• W2914242616 type Work @default.
• W2914242616 sameAs 2914242616 @default.
• W2914242616 citedByCount "3" @default.
• W2914242616 countsByYear W29142426162022 @default.
• W2914242616 countsByYear W29142426162023 @default.
• W2914242616 crossrefType "journal-article" @default.
• W2914242616 hasAuthorship W2914242616A5018428974 @default.
• W2914242616 hasAuthorship W2914242616A5032115994 @default.
• W2914242616 hasAuthorship W2914242616A5046874748 @default.
• W2914242616 hasAuthorship W2914242616A5077186384 @default.
• W2914242616 hasBestOaLocation W29142426161 @default.
• W2914242616 hasConcept C100515483 @default.
• W2914242616 hasConcept C106131492 @default.
• W2914242616 hasConcept C133892786 @default.
• W2914242616 hasConcept C136886441 @default.
• W2914242616 hasConcept C144024400 @default.
• W2914242616 hasConcept C153180895 @default.
• W2914242616 hasConcept C154945302 @default.
• W2914242616 hasConcept C19165224 @default.
• W2914242616 hasConcept C28490314 @default.
• W2914242616 hasConcept C31972630 @default.
• W2914242616 hasConcept C41008148 @default.
• W2914242616 hasConcept C50644808 @default.
• W2914242616 hasConcept C52622490 @default.
• W2914242616 hasConcept C83665646 @default.
• W2914242616 hasConcept C97931131 @default.
• W2914242616 hasConceptScore W2914242616C100515483 @default.
• W2914242616 hasConceptScore W2914242616C106131492 @default.
• W2914242616 hasConceptScore W2914242616C133892786 @default.
• W2914242616 hasConceptScore W2914242616C136886441 @default.
• W2914242616 hasConceptScore W2914242616C144024400 @default.
• W2914242616 hasConceptScore W2914242616C153180895 @default.
• W2914242616 hasConceptScore W2914242616C154945302 @default.
• W2914242616 hasConceptScore W2914242616C19165224 @default.
• W2914242616 hasConceptScore W2914242616C28490314 @default.
• W2914242616 hasConceptScore W2914242616C31972630 @default.
• W2914242616 hasConceptScore W2914242616C41008148 @default.
• W2914242616 hasConceptScore W2914242616C50644808 @default.
• W2914242616 hasConceptScore W2914242616C52622490 @default.
• W2914242616 hasConceptScore W2914242616C83665646 @default.
• W2914242616 hasConceptScore W2914242616C97931131 @default.
• W2914242616 hasIssue "2" @default.
• W2914242616 hasLocation W29142426161 @default.
• W2914242616 hasOpenAccess W2914242616 @default.
• W2914242616 hasPrimaryLocation W29142426161 @default.
• W2914242616 hasRelatedWork W1617617605 @default.
• W2914242616 hasRelatedWork W2103897043 @default.
• W2914242616 hasRelatedWork W2153315159 @default.
• W2914242616 hasRelatedWork W259157601 @default.
• W2914242616 hasRelatedWork W2761785940 @default.
• W2914242616 hasRelatedWork W2965546495 @default.
• W2914242616 hasRelatedWork W3103844505 @default.

• next