Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384080302> ?p ?o ?g. }
Showing items 1 to 58 of
58
with 100 items per page.
- W4384080302 endingPage "18" @default.
- W4384080302 startingPage "1" @default.
- W4384080302 abstract "Speech is a natural communication way between people and a good way for human-computer interaction. However, speech with audible voices often faces the following problems, e.g., being affected by surrounding noises, breaking the quiet environment, leaking privacy, etc. Therefore, silent speech was proposed, especially lip reading, which aims to recognize speech content based on lip movements. In this paper, we utilize inaudible acoustic signals generated from mobile device to sense and recognize lip movements for lip reading. Considering the lack of public dataset in acoustic-based lip reading, we propose and release a large-scale lip-reading dataset <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink><tex-math>${sf LIPCMD}$</tex-math></inline-formula> with 30000 acoustic-based recordings. To advance the further research in lip reading, we provide benchmark evaluation on <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink><tex-math>${sf LIPCMD}$</tex-math></inline-formula> , while using traditional machine learning solutions and recent deep learning approaches. To recognize weak acoustic signals as words for lip reading, we propose a self distillation based approach <italic xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>LipReader</i> , which distills the probability distribution and attention map in convolutional neural network itself for better classification. Finally, we implement <italic xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>LipReader</i> on smartphone and evaluate it on <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink><tex-math>${sf LIPCMD}$</tex-math></inline-formula> dataset as well as under complex scenarios. Experimental results show that <italic xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>LipReader</i> can achieve a good recognition accuracy for lip reading, i.e., 91.58%, while outperforming baseline solutions and existing work." @default.
- W4384080302 created "2023-07-13" @default.
- W4384080302 creator A5010955832 @default.
- W4384080302 creator A5043533769 @default.
- W4384080302 creator A5052267876 @default.
- W4384080302 creator A5078573016 @default.
- W4384080302 creator A5087888694 @default.
- W4384080302 date "2023-01-01" @default.
- W4384080302 modified "2023-09-26" @default.
- W4384080302 title "Acoustic-based Lip Reading for Mobile Devices: Dataset, Benchmark and A Self Distillation-based Approach" @default.
- W4384080302 doi "https://doi.org/10.1109/tmc.2023.3294416" @default.
- W4384080302 hasPublicationYear "2023" @default.
- W4384080302 type Work @default.
- W4384080302 citedByCount "0" @default.
- W4384080302 crossrefType "journal-article" @default.
- W4384080302 hasAuthorship W4384080302A5010955832 @default.
- W4384080302 hasAuthorship W4384080302A5043533769 @default.
- W4384080302 hasAuthorship W4384080302A5052267876 @default.
- W4384080302 hasAuthorship W4384080302A5078573016 @default.
- W4384080302 hasAuthorship W4384080302A5087888694 @default.
- W4384080302 hasConcept C13280743 @default.
- W4384080302 hasConcept C154945302 @default.
- W4384080302 hasConcept C17744445 @default.
- W4384080302 hasConcept C185798385 @default.
- W4384080302 hasConcept C199539241 @default.
- W4384080302 hasConcept C204321447 @default.
- W4384080302 hasConcept C205649164 @default.
- W4384080302 hasConcept C28490314 @default.
- W4384080302 hasConcept C41008148 @default.
- W4384080302 hasConcept C554936623 @default.
- W4384080302 hasConceptScore W4384080302C13280743 @default.
- W4384080302 hasConceptScore W4384080302C154945302 @default.
- W4384080302 hasConceptScore W4384080302C17744445 @default.
- W4384080302 hasConceptScore W4384080302C185798385 @default.
- W4384080302 hasConceptScore W4384080302C199539241 @default.
- W4384080302 hasConceptScore W4384080302C204321447 @default.
- W4384080302 hasConceptScore W4384080302C205649164 @default.
- W4384080302 hasConceptScore W4384080302C28490314 @default.
- W4384080302 hasConceptScore W4384080302C41008148 @default.
- W4384080302 hasConceptScore W4384080302C554936623 @default.
- W4384080302 hasLocation W43840803021 @default.
- W4384080302 hasOpenAccess W4384080302 @default.
- W4384080302 hasPrimaryLocation W43840803021 @default.
- W4384080302 hasRelatedWork W112744582 @default.
- W4384080302 hasRelatedWork W1485630101 @default.
- W4384080302 hasRelatedWork W1490303524 @default.
- W4384080302 hasRelatedWork W2030059621 @default.
- W4384080302 hasRelatedWork W2070338563 @default.
- W4384080302 hasRelatedWork W2368651715 @default.
- W4384080302 hasRelatedWork W2498017833 @default.
- W4384080302 hasRelatedWork W2611614995 @default.
- W4384080302 hasRelatedWork W3033750096 @default.
- W4384080302 hasRelatedWork W3081841992 @default.
- W4384080302 isParatext "false" @default.
- W4384080302 isRetracted "false" @default.
- W4384080302 workType "article" @default.