Matches in SemOpenAlex for { <https://semopenalex.org/work/W2765381110> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W2765381110 abstract "Incorporating prosodic information with spectral information at the feature level is challenging. In this paper, a method for feature level fusion of spectral and prosodic information is proposed. A pitch contour is first extracted from the frame blocked segments of the speech signal. These speech segments obtained herein are labeled as high pitch and low pitch segments. Both spectral and prosodic features are extracted from each segment class. An integrated feature set is obtained by concatenating spectral and prosodic features from each of these classes. In the next stage of fusion, the high and low pitch labeled features are further combined using joint error optimization approach. This optimization approach assumes that the mean of the high pitch segments can be obtained by an affine transformation on the mean of the low pitch segments. The parameters of the affine transformation are obtained using the gradient descent approach. The final integrated feature set is obtained after normalization of both sets of features thus obtained. This integrated feature set is used in a Hidden Markov Modeling (HMM) framework along with a novel sliding syllable protocol for keyword spotting. Keyword spotting experiments are conducted on the Hindi language database developed for this purpose. Experiments on keyword recognition and keyword spotting are conducted to evaluate the performance of the proposed fusion method. Experimental results obtained in terms of WER and receiver operating characteristics indicate a reasonable improvements over the use of a single feature set like the MFCC." @default.
- W2765381110 created "2017-11-10" @default.
- W2765381110 creator A5027196655 @default.
- W2765381110 creator A5057075522 @default.
- W2765381110 creator A5085503354 @default.
- W2765381110 date "2017-03-01" @default.
- W2765381110 modified "2023-09-27" @default.
- W2765381110 title "Fusion of spectral and prosodic information using combined error optimization for keyword spotting" @default.
- W2765381110 cites W1538323930 @default.
- W2765381110 cites W1579838312 @default.
- W2765381110 cites W158901718 @default.
- W2765381110 cites W1983906381 @default.
- W2765381110 cites W2002342963 @default.
- W2765381110 cites W2041823554 @default.
- W2765381110 cites W2046932483 @default.
- W2765381110 cites W2101328377 @default.
- W2765381110 cites W2105594594 @default.
- W2765381110 cites W2125838338 @default.
- W2765381110 cites W2143827132 @default.
- W2765381110 cites W2155443942 @default.
- W2765381110 cites W3147254695 @default.
- W2765381110 doi "https://doi.org/10.1109/ncc.2017.8077071" @default.
- W2765381110 hasPublicationYear "2017" @default.
- W2765381110 type Work @default.
- W2765381110 sameAs 2765381110 @default.
- W2765381110 citedByCount "2" @default.
- W2765381110 countsByYear W27653811102018 @default.
- W2765381110 crossrefType "proceedings-article" @default.
- W2765381110 hasAuthorship W2765381110A5027196655 @default.
- W2765381110 hasAuthorship W2765381110A5057075522 @default.
- W2765381110 hasAuthorship W2765381110A5085503354 @default.
- W2765381110 hasConcept C136886441 @default.
- W2765381110 hasConcept C138885662 @default.
- W2765381110 hasConcept C144024400 @default.
- W2765381110 hasConcept C151989614 @default.
- W2765381110 hasConcept C153180895 @default.
- W2765381110 hasConcept C154945302 @default.
- W2765381110 hasConcept C19165224 @default.
- W2765381110 hasConcept C202444582 @default.
- W2765381110 hasConcept C23224414 @default.
- W2765381110 hasConcept C2776401178 @default.
- W2765381110 hasConcept C2779506182 @default.
- W2765381110 hasConcept C2781213101 @default.
- W2765381110 hasConcept C28490314 @default.
- W2765381110 hasConcept C33923547 @default.
- W2765381110 hasConcept C41008148 @default.
- W2765381110 hasConcept C41895202 @default.
- W2765381110 hasConcept C52622490 @default.
- W2765381110 hasConcept C92757383 @default.
- W2765381110 hasConceptScore W2765381110C136886441 @default.
- W2765381110 hasConceptScore W2765381110C138885662 @default.
- W2765381110 hasConceptScore W2765381110C144024400 @default.
- W2765381110 hasConceptScore W2765381110C151989614 @default.
- W2765381110 hasConceptScore W2765381110C153180895 @default.
- W2765381110 hasConceptScore W2765381110C154945302 @default.
- W2765381110 hasConceptScore W2765381110C19165224 @default.
- W2765381110 hasConceptScore W2765381110C202444582 @default.
- W2765381110 hasConceptScore W2765381110C23224414 @default.
- W2765381110 hasConceptScore W2765381110C2776401178 @default.
- W2765381110 hasConceptScore W2765381110C2779506182 @default.
- W2765381110 hasConceptScore W2765381110C2781213101 @default.
- W2765381110 hasConceptScore W2765381110C28490314 @default.
- W2765381110 hasConceptScore W2765381110C33923547 @default.
- W2765381110 hasConceptScore W2765381110C41008148 @default.
- W2765381110 hasConceptScore W2765381110C41895202 @default.
- W2765381110 hasConceptScore W2765381110C52622490 @default.
- W2765381110 hasConceptScore W2765381110C92757383 @default.
- W2765381110 hasLocation W27653811101 @default.
- W2765381110 hasOpenAccess W2765381110 @default.
- W2765381110 hasPrimaryLocation W27653811101 @default.
- W2765381110 hasRelatedWork W1516974462 @default.
- W2765381110 hasRelatedWork W1963740019 @default.
- W2765381110 hasRelatedWork W1971793356 @default.
- W2765381110 hasRelatedWork W2005330134 @default.
- W2765381110 hasRelatedWork W2043920657 @default.
- W2765381110 hasRelatedWork W2052282967 @default.
- W2765381110 hasRelatedWork W2066511540 @default.
- W2765381110 hasRelatedWork W2072229047 @default.
- W2765381110 hasRelatedWork W2081562600 @default.
- W2765381110 hasRelatedWork W2085326828 @default.
- W2765381110 hasRelatedWork W2106694981 @default.
- W2765381110 hasRelatedWork W2116842019 @default.
- W2765381110 hasRelatedWork W2267953971 @default.
- W2765381110 hasRelatedWork W2363702666 @default.
- W2765381110 hasRelatedWork W2507286840 @default.
- W2765381110 hasRelatedWork W2566781703 @default.
- W2765381110 hasRelatedWork W2572576546 @default.
- W2765381110 hasRelatedWork W2766545623 @default.
- W2765381110 hasRelatedWork W2901354910 @default.
- W2765381110 hasRelatedWork W6882942 @default.
- W2765381110 isParatext "false" @default.
- W2765381110 isRetracted "false" @default.
- W2765381110 magId "2765381110" @default.
- W2765381110 workType "article" @default.