Temporal constraints on human and artificial muliti-sensory speech recognition

Simple item page
dc.contributor.authorPerlette, Christopher S.
dc.contributor.authorUniversity of Lethbridge. Faculty of Arts and Science
dc.contributor.supervisorTata, Matthew S.
dc.contributor.supervisorZhang, John Z.
dc.date.accessioned2023-04-18T19:37:57Z
dc.date.available2023-04-18T19:37:57Z
dc.date.issued2023
dc.degree.levelMastersen_US
dc.description.abstractAudio Visual Speech Recognition (AVSR) is the process of perceiving and understanding speech using audio and visual information. Combining visual information with auditory stimuli has been shown to improve AVSR performance when compared to purely auditory speech recognition when the task is performed in adverse conditions with large amounts of distracting noise. This work examines the relationship of auditory and visual speech information and the effect audio-visual temporary desynchronization has on AVSR performance. Using a whole report task, we show that (1) consistent with prior similar work, performance declines asymmetrically depending on the direction and quantity of a temporal lag, and (2) a common, modern architecture for computational AVSR does not show this asymmetry indicating a fundamental difference in biological and computational AVSR methods.en_US
dc.description.sponsorshipMitacs ASI NSERCen_US
dc.identifier.urihttps://hdl.handle.net/10133/6465
dc.language.isoen
dc.proquest.subject0984en_US
dc.proquest.subject0317en_US
dc.proquest.subject0384en_US
dc.proquestyesYesen_US
dc.publisherLethbridge, Alta. : University of Lethbridge, Dept. of Neuroscience
dc.publisher.departmentDepartment of Neuroscienceen_US
dc.publisher.facultyArts and Scienceen_US
dc.relation.ispartofseriesThesis (University of Lethbridge. Faculty of Arts and Science)
dc.subjectmachine learning
dc.subjectspeech recognition
dc.subjectbehavioural
dc.subjectneuroscience
dc.subjectSpeech processing systems--Research
dc.subjectSpeech perception--Research
dc.subjectVisual perception--Research
dc.subjectLipreading
dc.subjectLipreading--Computer simulation
dc.subjectMachine learning
dc.subjectNeurosciences
dc.subjectDissertations, Academic
dc.titleTemporal constraints on human and artificial muliti-sensory speech recognitionen_US
dc.typeThesisen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
PERLETTE_CHRISTOPHER_MSC_2023.pdf
Size:
775.61 KB
Format:
Adobe Portable Document Format
Description:
Main Article
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
3.25 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Arts and Science, Faculty of
University of Lethbridge Theses