Matches in SemOpenAlex for { <https://semopenalex.org/work/W2094048151> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W2094048151 abstract "Template-matching and discriminative techniques, like support vector machines (SVMs), have been widely used for automatic speech recognition. Both methods require that varying length sequences are mapped to vectors of fixed lengths: in template-matching, the problem is solved by means of dynamic time warping (DTW), while in SVM with dynamic kernels. The supervector and i-vector paradigms seem to represent a valid solution to such a problem when SVM are employed for classification. In this work, Gaussian mean supervectors (GMS), Gaussian posterior probability supervectors (GPPS) and i-vectors are evaluated as features both for template-matching and for SVM-based speech recognition in a comparative fashion. All these features are based on Power Normalized Cepstral Coefficients (PNCCs) directly extracted from speech utterances. The different methods are assessed in small vocabulary speech recognition tasks using two distinct corpora, and they have been compared to DTW, dynamic time alignment kernel (DTAK), outerproduct of trajectory matrix, and PocketSphinx as further recognition techniques to be evaluated. Experimental results showed the appropriateness of the supervector and i-vector based solutions with respect to the other state-of-the art techniques here addressed." @default.
- W2094048151 created "2016-06-24" @default.
- W2094048151 creator A5004758092 @default.
- W2094048151 creator A5004777557 @default.
- W2094048151 creator A5034253968 @default.
- W2094048151 date "2014-07-01" @default.
- W2094048151 modified "2023-10-16" @default.
- W2094048151 title "Power Normalized Cepstral Coefficients based supervectors and i-vectors for small vocabulary speech recognition" @default.
- W2094048151 cites W1603327663 @default.
- W2094048151 cites W1976524151 @default.
- W2094048151 cites W1986263748 @default.
- W2094048151 cites W1990938546 @default.
- W2094048151 cites W2015631279 @default.
- W2094048151 cites W2025715933 @default.
- W2094048151 cites W2050091530 @default.
- W2094048151 cites W2069620976 @default.
- W2094048151 cites W2096727529 @default.
- W2094048151 cites W2107638917 @default.
- W2094048151 cites W2114719288 @default.
- W2094048151 cites W2117633163 @default.
- W2094048151 cites W2121415728 @default.
- W2094048151 cites W2121973264 @default.
- W2094048151 cites W2124958607 @default.
- W2094048151 cites W2128653836 @default.
- W2094048151 cites W2150769028 @default.
- W2094048151 cites W2152131029 @default.
- W2094048151 cites W2153529069 @default.
- W2094048151 cites W2153635508 @default.
- W2094048151 cites W2156885227 @default.
- W2094048151 cites W2283504545 @default.
- W2094048151 cites W2407501792 @default.
- W2094048151 cites W2543956298 @default.
- W2094048151 cites W3145713857 @default.
- W2094048151 cites W4212863985 @default.
- W2094048151 cites W4239510810 @default.
- W2094048151 cites W82438768 @default.
- W2094048151 doi "https://doi.org/10.1109/ijcnn.2014.6889552" @default.
- W2094048151 hasPublicationYear "2014" @default.
- W2094048151 type Work @default.
- W2094048151 sameAs 2094048151 @default.
- W2094048151 citedByCount "7" @default.
- W2094048151 countsByYear W20940481512015 @default.
- W2094048151 countsByYear W20940481512017 @default.
- W2094048151 countsByYear W20940481512018 @default.
- W2094048151 countsByYear W20940481512020 @default.
- W2094048151 crossrefType "proceedings-article" @default.
- W2094048151 hasAuthorship W2094048151A5004758092 @default.
- W2094048151 hasAuthorship W2094048151A5004777557 @default.
- W2094048151 hasAuthorship W2094048151A5034253968 @default.
- W2094048151 hasConcept C105795698 @default.
- W2094048151 hasConcept C114614502 @default.
- W2094048151 hasConcept C121332964 @default.
- W2094048151 hasConcept C12267149 @default.
- W2094048151 hasConcept C151989614 @default.
- W2094048151 hasConcept C153180895 @default.
- W2094048151 hasConcept C154945302 @default.
- W2094048151 hasConcept C163716315 @default.
- W2094048151 hasConcept C165064840 @default.
- W2094048151 hasConcept C28490314 @default.
- W2094048151 hasConcept C33923547 @default.
- W2094048151 hasConcept C41008148 @default.
- W2094048151 hasConcept C52622490 @default.
- W2094048151 hasConcept C62520636 @default.
- W2094048151 hasConcept C74193536 @default.
- W2094048151 hasConcept C88516994 @default.
- W2094048151 hasConcept C97931131 @default.
- W2094048151 hasConceptScore W2094048151C105795698 @default.
- W2094048151 hasConceptScore W2094048151C114614502 @default.
- W2094048151 hasConceptScore W2094048151C121332964 @default.
- W2094048151 hasConceptScore W2094048151C12267149 @default.
- W2094048151 hasConceptScore W2094048151C151989614 @default.
- W2094048151 hasConceptScore W2094048151C153180895 @default.
- W2094048151 hasConceptScore W2094048151C154945302 @default.
- W2094048151 hasConceptScore W2094048151C163716315 @default.
- W2094048151 hasConceptScore W2094048151C165064840 @default.
- W2094048151 hasConceptScore W2094048151C28490314 @default.
- W2094048151 hasConceptScore W2094048151C33923547 @default.
- W2094048151 hasConceptScore W2094048151C41008148 @default.
- W2094048151 hasConceptScore W2094048151C52622490 @default.
- W2094048151 hasConceptScore W2094048151C62520636 @default.
- W2094048151 hasConceptScore W2094048151C74193536 @default.
- W2094048151 hasConceptScore W2094048151C88516994 @default.
- W2094048151 hasConceptScore W2094048151C97931131 @default.
- W2094048151 hasLocation W20940481511 @default.
- W2094048151 hasOpenAccess W2094048151 @default.
- W2094048151 hasPrimaryLocation W20940481511 @default.
- W2094048151 hasRelatedWork W2126100045 @default.
- W2094048151 hasRelatedWork W2141705618 @default.
- W2094048151 hasRelatedWork W2285052147 @default.
- W2094048151 hasRelatedWork W2336974148 @default.
- W2094048151 hasRelatedWork W2586441539 @default.
- W2094048151 hasRelatedWork W2743258233 @default.
- W2094048151 hasRelatedWork W2786925407 @default.
- W2094048151 hasRelatedWork W2806866760 @default.
- W2094048151 hasRelatedWork W2187500075 @default.
- W2094048151 hasRelatedWork W2345184372 @default.
- W2094048151 isParatext "false" @default.
- W2094048151 isRetracted "false" @default.
- W2094048151 magId "2094048151" @default.
- W2094048151 workType "article" @default.