Matches in SemOpenAlex for { <https://semopenalex.org/work/W4240342853> ?p ?o ?g. }
Showing items 1 to 70 of
70
with 100 items per page.
- W4240342853 endingPage "82" @default.
- W4240342853 startingPage "74" @default.
- W4240342853 abstract "The authors proposed for acoustic models based on the hidden Markov model a method that involves applying constraints to the model structure and tying the model's parameters in order to improve the training efficiency. Conventionally, the tied structure of an acoustic model is, mostly, defined by tying several adjacent parameters and expressing them with a single representative parameter. This method can be regarded as a tying method based on the parameters' values, under the assumption that adjacent parameters, usually, exhibit similar behavior. As opposed to this concept, the current study proposes a tied structure with consideration of transfer (movement) of parameters. A large volume of training data was used to measure transfer of each parameter during training, and tying relationships regarding the transfer vectors were organized between parameters performing statistically similar movements. In particular, in the current study, the authors concentrated on mean vectors of fundamental distributions and followed movements of these mean vectors during training of initial models (speaker-independent models) by acoustic data from different speakers. The structure was defined by identifying the mean vectors characterized by strong correlation of movements during training, and tying their corresponding transfer vectors. Speaker adaptation tests confirmed high training efficiency of the model obtained as a result of this tying. © 2000 Scripta Technica, Syst Comp Jpn, 31(14): 74–82, 2000" @default.
- W4240342853 created "2022-05-12" @default.
- W4240342853 creator A5003450550 @default.
- W4240342853 creator A5052125683 @default.
- W4240342853 date "2000-12-01" @default.
- W4240342853 modified "2023-09-26" @default.
- W4240342853 title "Speaker adaptation of acoustic models using correlations of training transfer vectors" @default.
- W4240342853 doi "https://doi.org/10.1002/1520-684x(200012)31:14<74::aid-scj9>3.3.co;2-e" @default.
- W4240342853 hasPublicationYear "2000" @default.
- W4240342853 type Work @default.
- W4240342853 citedByCount "0" @default.
- W4240342853 crossrefType "journal-article" @default.
- W4240342853 hasAuthorship W4240342853A5003450550 @default.
- W4240342853 hasAuthorship W4240342853A5052125683 @default.
- W4240342853 hasConcept C111919701 @default.
- W4240342853 hasConcept C119599485 @default.
- W4240342853 hasConcept C120665830 @default.
- W4240342853 hasConcept C121332964 @default.
- W4240342853 hasConcept C124101348 @default.
- W4240342853 hasConcept C127413603 @default.
- W4240342853 hasConcept C139807058 @default.
- W4240342853 hasConcept C148043351 @default.
- W4240342853 hasConcept C150899416 @default.
- W4240342853 hasConcept C153180895 @default.
- W4240342853 hasConcept C154945302 @default.
- W4240342853 hasConcept C173608175 @default.
- W4240342853 hasConcept C23224414 @default.
- W4240342853 hasConcept C2776175482 @default.
- W4240342853 hasConcept C2780009758 @default.
- W4240342853 hasConcept C2780938662 @default.
- W4240342853 hasConcept C28490314 @default.
- W4240342853 hasConcept C41008148 @default.
- W4240342853 hasConceptScore W4240342853C111919701 @default.
- W4240342853 hasConceptScore W4240342853C119599485 @default.
- W4240342853 hasConceptScore W4240342853C120665830 @default.
- W4240342853 hasConceptScore W4240342853C121332964 @default.
- W4240342853 hasConceptScore W4240342853C124101348 @default.
- W4240342853 hasConceptScore W4240342853C127413603 @default.
- W4240342853 hasConceptScore W4240342853C139807058 @default.
- W4240342853 hasConceptScore W4240342853C148043351 @default.
- W4240342853 hasConceptScore W4240342853C150899416 @default.
- W4240342853 hasConceptScore W4240342853C153180895 @default.
- W4240342853 hasConceptScore W4240342853C154945302 @default.
- W4240342853 hasConceptScore W4240342853C173608175 @default.
- W4240342853 hasConceptScore W4240342853C23224414 @default.
- W4240342853 hasConceptScore W4240342853C2776175482 @default.
- W4240342853 hasConceptScore W4240342853C2780009758 @default.
- W4240342853 hasConceptScore W4240342853C2780938662 @default.
- W4240342853 hasConceptScore W4240342853C28490314 @default.
- W4240342853 hasConceptScore W4240342853C41008148 @default.
- W4240342853 hasIssue "14" @default.
- W4240342853 hasLocation W42403428531 @default.
- W4240342853 hasOpenAccess W4240342853 @default.
- W4240342853 hasPrimaryLocation W42403428531 @default.
- W4240342853 hasRelatedWork W143197085 @default.
- W4240342853 hasRelatedWork W1485203548 @default.
- W4240342853 hasRelatedWork W2107259696 @default.
- W4240342853 hasRelatedWork W2108538578 @default.
- W4240342853 hasRelatedWork W2141827612 @default.
- W4240342853 hasRelatedWork W2155033763 @default.
- W4240342853 hasRelatedWork W2170807154 @default.
- W4240342853 hasRelatedWork W2293910151 @default.
- W4240342853 hasRelatedWork W2793122029 @default.
- W4240342853 hasRelatedWork W3128571556 @default.
- W4240342853 hasVolume "31" @default.
- W4240342853 isParatext "false" @default.
- W4240342853 isRetracted "false" @default.
- W4240342853 workType "article" @default.