Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387544554> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W4387544554 endingPage "386" @default.
- W4387544554 startingPage "375" @default.
- W4387544554 abstract "Lip-reading is a method that focuses on the observation and interpretation of lip movements to understand spoken language. Previous studies have exclusively concentrated on a single variation of residual networks (ResNets). This study primarily aimed to conduct a comparative analysis of several types of ResNets. This study additionally calculates metrics for several word structures included in the GRID dataset, encompassing verbs, colors, prepositions, letters, and numerals. This component has not been previously investigated in other studies. The proposed approach encompasses several stages, namely pre-processing, which involves face detection and mouth location, feature extraction, and classification. The architecture for feature extraction comprises a 3-dimensional convolutional neural network (3D-CNN) integrated with ResNets. The management of temporal sequences during the classification phase is accomplished through the utilization of the bidirectional gated recurrent units (Bi-GRU) model. The experimental results demonstrated a character error rate (CER) of 14.09% and a word error rate (WER) of 28.51%. The combination of 3D-CNN ResNet-34 and Bi-GRU yielded superior outcomes in comparison to ResNet-18 and ResNet-50. The correlation between increased network depth and enhanced performance in lip-reading models was not consistently observed. Nevertheless, the incorporation of additional trained parameters offers certain benefits. Moreover, it has demonstrated superior levels of precision in comparison to human professionals in the task of distinguishing diverse word structures. Doi: 10.28991/HIJ-2023-04-02-010 Full Text: PDF" @default.
- W4387544554 created "2023-10-12" @default.
- W4387544554 creator A5016609672 @default.
- W4387544554 creator A5076770416 @default.
- W4387544554 date "2023-06-01" @default.
- W4387544554 modified "2023-10-12" @default.
- W4387544554 title "Lip-Reading with Visual Form Classification using Residual Networks and Bidirectional Gated Recurrent Units" @default.
- W4387544554 doi "https://doi.org/10.28991/hij-2023-04-02-010" @default.
- W4387544554 hasPublicationYear "2023" @default.
- W4387544554 type Work @default.
- W4387544554 citedByCount "0" @default.
- W4387544554 crossrefType "journal-article" @default.
- W4387544554 hasAuthorship W4387544554A5016609672 @default.
- W4387544554 hasAuthorship W4387544554A5076770416 @default.
- W4387544554 hasBestOaLocation W43875445541 @default.
- W4387544554 hasConcept C11413529 @default.
- W4387544554 hasConcept C121332964 @default.
- W4387544554 hasConcept C138885662 @default.
- W4387544554 hasConcept C153180895 @default.
- W4387544554 hasConcept C154945302 @default.
- W4387544554 hasConcept C155512373 @default.
- W4387544554 hasConcept C162324750 @default.
- W4387544554 hasConcept C17744445 @default.
- W4387544554 hasConcept C187736073 @default.
- W4387544554 hasConcept C199539241 @default.
- W4387544554 hasConcept C204160518 @default.
- W4387544554 hasConcept C204321447 @default.
- W4387544554 hasConcept C2524010 @default.
- W4387544554 hasConcept C2776401178 @default.
- W4387544554 hasConcept C2778334786 @default.
- W4387544554 hasConcept C2780451532 @default.
- W4387544554 hasConcept C28490314 @default.
- W4387544554 hasConcept C2944601119 @default.
- W4387544554 hasConcept C33923547 @default.
- W4387544554 hasConcept C40969351 @default.
- W4387544554 hasConcept C41008148 @default.
- W4387544554 hasConcept C41895202 @default.
- W4387544554 hasConcept C44870925 @default.
- W4387544554 hasConcept C554936623 @default.
- W4387544554 hasConcept C81363708 @default.
- W4387544554 hasConcept C90805587 @default.
- W4387544554 hasConceptScore W4387544554C11413529 @default.
- W4387544554 hasConceptScore W4387544554C121332964 @default.
- W4387544554 hasConceptScore W4387544554C138885662 @default.
- W4387544554 hasConceptScore W4387544554C153180895 @default.
- W4387544554 hasConceptScore W4387544554C154945302 @default.
- W4387544554 hasConceptScore W4387544554C155512373 @default.
- W4387544554 hasConceptScore W4387544554C162324750 @default.
- W4387544554 hasConceptScore W4387544554C17744445 @default.
- W4387544554 hasConceptScore W4387544554C187736073 @default.
- W4387544554 hasConceptScore W4387544554C199539241 @default.
- W4387544554 hasConceptScore W4387544554C204160518 @default.
- W4387544554 hasConceptScore W4387544554C204321447 @default.
- W4387544554 hasConceptScore W4387544554C2524010 @default.
- W4387544554 hasConceptScore W4387544554C2776401178 @default.
- W4387544554 hasConceptScore W4387544554C2778334786 @default.
- W4387544554 hasConceptScore W4387544554C2780451532 @default.
- W4387544554 hasConceptScore W4387544554C28490314 @default.
- W4387544554 hasConceptScore W4387544554C2944601119 @default.
- W4387544554 hasConceptScore W4387544554C33923547 @default.
- W4387544554 hasConceptScore W4387544554C40969351 @default.
- W4387544554 hasConceptScore W4387544554C41008148 @default.
- W4387544554 hasConceptScore W4387544554C41895202 @default.
- W4387544554 hasConceptScore W4387544554C44870925 @default.
- W4387544554 hasConceptScore W4387544554C554936623 @default.
- W4387544554 hasConceptScore W4387544554C81363708 @default.
- W4387544554 hasConceptScore W4387544554C90805587 @default.
- W4387544554 hasIssue "2" @default.
- W4387544554 hasLocation W43875445541 @default.
- W4387544554 hasOpenAccess W4387544554 @default.
- W4387544554 hasPrimaryLocation W43875445541 @default.
- W4387544554 hasRelatedWork W2161593895 @default.
- W4387544554 hasRelatedWork W2274287116 @default.
- W4387544554 hasRelatedWork W2964350391 @default.
- W4387544554 hasRelatedWork W2967403871 @default.
- W4387544554 hasRelatedWork W2983358626 @default.
- W4387544554 hasRelatedWork W2984708981 @default.
- W4387544554 hasRelatedWork W3087144180 @default.
- W4387544554 hasRelatedWork W3160076723 @default.
- W4387544554 hasRelatedWork W3196952692 @default.
- W4387544554 hasRelatedWork W4300939921 @default.
- W4387544554 hasVolume "4" @default.
- W4387544554 isParatext "false" @default.
- W4387544554 isRetracted "false" @default.
- W4387544554 workType "article" @default.