Matches in SemOpenAlex for { <https://semopenalex.org/work/W2737701198> ?p ?o ?g. }
Showing items 1 to 66 of
66
with 100 items per page.
- W2737701198 abstract "Introducing features that better represent the visual information of speakers during the speech production is still an open issue that highly affects the quality of the lip-reading and Audio Visual Speech Recognition (AVSR) tasks. In this paper, three different types of visual features from both the image-based and model-based ones are investigated inside a professional lip reading task. The simple raw gray level information of the lips Region of Interest (ROI), the geometric representation of lips shape and the Deep Bottle-neck Features (DBNFs) extracted from a 6-layer Deep Auto-encoder Neural Network (DANN) are three valuable feature sets compared while employed for the lip reading purpose. Two different recognition systems, including the conventional GMM-HMM and the state-of-the-art DNN-HMM hybrid, are utilized to perform an isolated and connected digit recognition task. The results indicate that the high level information extracted from deep layers of the lips ROI can represent the visual modality with advantage of “high amount of information in a low dimension feature vector”. Moreover, the DBNFs showed a relative improvement with an average of 15.4% in comparison to the shape features and the shape features showed a relative improvement with an average of 20.4% in comparison to the ROI features over the test data." @default.
- W2737701198 created "2017-07-31" @default.
- W2737701198 creator A5000812812 @default.
- W2737701198 creator A5006262011 @default.
- W2737701198 date "2017-04-01" @default.
- W2737701198 modified "2023-09-23" @default.
- W2737701198 title "Lip-reading via a DNN-HMM hybrid system using combination of the image-based and model-based features" @default.
- W2737701198 cites W1545354932 @default.
- W2737701198 cites W1895481600 @default.
- W2737701198 cites W1929733467 @default.
- W2737701198 cites W2038952578 @default.
- W2737701198 cites W2098923380 @default.
- W2737701198 cites W2122538988 @default.
- W2737701198 cites W2156332321 @default.
- W2737701198 cites W329631617 @default.
- W2737701198 doi "https://doi.org/10.1109/pria.2017.7983045" @default.
- W2737701198 hasPublicationYear "2017" @default.
- W2737701198 type Work @default.
- W2737701198 sameAs 2737701198 @default.
- W2737701198 citedByCount "20" @default.
- W2737701198 countsByYear W27377011982017 @default.
- W2737701198 countsByYear W27377011982018 @default.
- W2737701198 countsByYear W27377011982019 @default.
- W2737701198 countsByYear W27377011982020 @default.
- W2737701198 countsByYear W27377011982021 @default.
- W2737701198 countsByYear W27377011982022 @default.
- W2737701198 crossrefType "proceedings-article" @default.
- W2737701198 hasAuthorship W2737701198A5000812812 @default.
- W2737701198 hasAuthorship W2737701198A5006262011 @default.
- W2737701198 hasConcept C138885662 @default.
- W2737701198 hasConcept C153180895 @default.
- W2737701198 hasConcept C154945302 @default.
- W2737701198 hasConcept C23224414 @default.
- W2737701198 hasConcept C2776401178 @default.
- W2737701198 hasConcept C28490314 @default.
- W2737701198 hasConcept C41008148 @default.
- W2737701198 hasConcept C41895202 @default.
- W2737701198 hasConcept C50644808 @default.
- W2737701198 hasConcept C52622490 @default.
- W2737701198 hasConceptScore W2737701198C138885662 @default.
- W2737701198 hasConceptScore W2737701198C153180895 @default.
- W2737701198 hasConceptScore W2737701198C154945302 @default.
- W2737701198 hasConceptScore W2737701198C23224414 @default.
- W2737701198 hasConceptScore W2737701198C2776401178 @default.
- W2737701198 hasConceptScore W2737701198C28490314 @default.
- W2737701198 hasConceptScore W2737701198C41008148 @default.
- W2737701198 hasConceptScore W2737701198C41895202 @default.
- W2737701198 hasConceptScore W2737701198C50644808 @default.
- W2737701198 hasConceptScore W2737701198C52622490 @default.
- W2737701198 hasLocation W27377011981 @default.
- W2737701198 hasOpenAccess W2737701198 @default.
- W2737701198 hasPrimaryLocation W27377011981 @default.
- W2737701198 hasRelatedWork W2016461833 @default.
- W2737701198 hasRelatedWork W2144059113 @default.
- W2737701198 hasRelatedWork W2146076056 @default.
- W2737701198 hasRelatedWork W2167236583 @default.
- W2737701198 hasRelatedWork W2375321655 @default.
- W2737701198 hasRelatedWork W2382607599 @default.
- W2737701198 hasRelatedWork W2546942002 @default.
- W2737701198 hasRelatedWork W2811390910 @default.
- W2737701198 hasRelatedWork W3003836766 @default.
- W2737701198 hasRelatedWork W3197541072 @default.
- W2737701198 isParatext "false" @default.
- W2737701198 isRetracted "false" @default.
- W2737701198 magId "2737701198" @default.
- W2737701198 workType "article" @default.