Matches in SemOpenAlex for { <https://semopenalex.org/work/W2070545637> ?p ?o ?g. }
Showing items 1 to 50 of
50
with 100 items per page.
- W2070545637 endingPage "232" @default.
- W2070545637 startingPage "223" @default.
- W2070545637 abstract "Abstract In this work we demonstrate that explicit modeling of correlations between spectral parameters in speech recognition improves speech models both in terms of their descriptive power (higher likelihoods) and classification accuracy. Most large-vocabulary speech recognition systems are based on some form of hidden Markov models (HMMs) modeling sub-word speech segments. Most of the time speech segments are represented using short term spectra. In this work we employ three-state left-to-right phone models and LPC cepstral parameters including their first and second order time differentials. We investigate the importance of modeling correlations between cepstral parameters for high accuracy phone recognition. Several different types of distributions for each HMM state are compared. The simplest uses a single multivariate Gaussian distribution with a full covariance matrix. The next uses a weighted mixture of multivariate Gaussian distributions with diagonal covariances. It uses implicit rather than explicit modeling of parameter correlations. The most elaborate model employs a mixture of Gaussian distributions, just like the previous model, but in addition it uses a parameter space rotation which is specific to a given state in an HMM. It thus explicitly models parameter correlations in exactly the same way as the simplest model which uses a single distribution per state. The highest phone accuracy on the DARPA Resource Management task Feb 89 test set is obtained using the most elaborate model, with mixtures and space rotation - 82·4% phone accuracy. The next best result was achieved using single distributions, which also explicitly model parameter correlations, with 80·8% phone accuracy. The worst result was obtained using distributions which only implicitly model parameter correlations, achieving 78·7% phone accuracy. These results clearly demonstrate the importance of explicitly modeling parameter correlations for improving speech recognition performance." @default.
- W2070545637 created "2016-06-24" @default.
- W2070545637 creator A5060308914 @default.
- W2070545637 date "1994-07-01" @default.
- W2070545637 modified "2023-09-24" @default.
- W2070545637 title "The importance of cepstral parameter correlations in speech recognition" @default.
- W2070545637 doi "https://doi.org/10.1006/csla.1994.1011" @default.
- W2070545637 hasPublicationYear "1994" @default.
- W2070545637 type Work @default.
- W2070545637 sameAs 2070545637 @default.
- W2070545637 citedByCount "33" @default.
- W2070545637 crossrefType "journal-article" @default.
- W2070545637 hasAuthorship W2070545637A5060308914 @default.
- W2070545637 hasConcept C151989614 @default.
- W2070545637 hasConcept C153180895 @default.
- W2070545637 hasConcept C154945302 @default.
- W2070545637 hasConcept C204321447 @default.
- W2070545637 hasConcept C28490314 @default.
- W2070545637 hasConcept C41008148 @default.
- W2070545637 hasConcept C52622490 @default.
- W2070545637 hasConcept C88485024 @default.
- W2070545637 hasConceptScore W2070545637C151989614 @default.
- W2070545637 hasConceptScore W2070545637C153180895 @default.
- W2070545637 hasConceptScore W2070545637C154945302 @default.
- W2070545637 hasConceptScore W2070545637C204321447 @default.
- W2070545637 hasConceptScore W2070545637C28490314 @default.
- W2070545637 hasConceptScore W2070545637C41008148 @default.
- W2070545637 hasConceptScore W2070545637C52622490 @default.
- W2070545637 hasConceptScore W2070545637C88485024 @default.
- W2070545637 hasIssue "3" @default.
- W2070545637 hasLocation W20705456371 @default.
- W2070545637 hasOpenAccess W2070545637 @default.
- W2070545637 hasPrimaryLocation W20705456371 @default.
- W2070545637 hasRelatedWork W1670591028 @default.
- W2070545637 hasRelatedWork W1847576989 @default.
- W2070545637 hasRelatedWork W1996938627 @default.
- W2070545637 hasRelatedWork W2069796675 @default.
- W2070545637 hasRelatedWork W2380536744 @default.
- W2070545637 hasRelatedWork W3107474891 @default.
- W2070545637 hasRelatedWork W3186851455 @default.
- W2070545637 hasRelatedWork W40124310 @default.
- W2070545637 hasRelatedWork W879529032 @default.
- W2070545637 hasRelatedWork W2276856808 @default.
- W2070545637 hasVolume "8" @default.
- W2070545637 isParatext "false" @default.
- W2070545637 isRetracted "false" @default.
- W2070545637 magId "2070545637" @default.
- W2070545637 workType "article" @default.