{"id":{"repo_id":"east-anglia","oai_identifier":"oai:ueaeprints.uea.ac.uk:59384"},"canonical_url":"https://search.dev.ndltd.org/etd/east-anglia/oai:ueaeprints.uea.ac.uk:59384","repository":{"repo_id":"east-anglia","name":"University of East Anglia","base_url":"https://ueaeprints.uea.ac.uk/cgi/oai2"},"display":{"title":"Decoding visemes: improving machine lip-reading","abstract":"Abstract This thesis is about improving machine lip-reading, that is, the classi�cation of speech from only visual cues of a speaker. Machine lip-reading is a niche research problem in both areas of speech processing and computer vision. Current challenges for machine lip-reading fall into two groups: the content of the video, such as the rate at which a person is speaking or; the parameters of the video recording for example, the video resolution. We begin our work with a literature review to understand the restrictions current technology limits machine lip-reading recognition and conduct an experiment into resolution a�ects. We show that high de�nition video is not needed to successfully lip-read with a computer. The term \\viseme\" is used in machine lip-reading to represent a visual cue or gesture which corresponds to a subgroup of phonemes where the phonemes are indistinguishable in the visual speech signal. Whilst a viseme is yet to be formally de�ned, we use the common working de�nition `a viseme is a group of phonemes with identical appearance on the lips'. A phoneme is the smallest acoustic unit a human can utter. Because there are more phonemes per viseme, mapping between the units creates a many-to-one relationship. Many mappings have been presented, and we conduct an experiment to determine which mapping produces the most accurate classi�cation. Our results show Lee's [82] is best. Lee's classi�cation also outperforms machine lip-reading systems which use the popular Fisher [48] phonemeto- viseme map. Further to this, we propose three methods of deriving speaker-dependent phonemeto- viseme maps and compare our new approaches to Lee's. Our results show the ii iii sensitivity of phoneme clustering and we use our new knowledge for our �rst suggested augmentation to the conventional lip-reading system. Speaker independence in machine lip-reading classi�cation is another unsolved obstacle. It has been observed, in the visual domain, that classi�ers need training on the test subject to achieve the best classi�cation. Thus machine lip-reading is highly dependent upon the speaker. Speaker independence is the opposite of this, or in other words, is the classi�cation of a speaker not present in the classi�er's training data. We investigate the dependence of phoneme-to-viseme maps between speakers. Our results show there is not a high variability of visual cues, but there is high variability in trajectory between visual cues of an individual speaker with the same ground truth. This implies a dependency upon the number of visemes within each set for each individual. Finally, we investigate how many visemes is the optimum number within a set. We show the phoneme-to-viseme maps in literature rarely have enough visemes and the optimal number, which varies by speaker, ranges from 11 to 35. The last di�culty we address is decoding from visemes back to phonemes and into words. Traditionally this is completed using a language model. The language model unit is either: the same as the classi�er, e.g. visemes or phonemes; or the language model unit is words. In a novel approach we use these optimum range viseme sets within hierarchical training of phoneme labelled classi�ers. This new method of classi�er training demonstrates signi�cant increase in classi�cation with a word language network.","abstract_html":"Abstract This thesis is about improving machine lip-reading, that is, the classi�cation of speech from only visual cues of a speaker. Machine lip-reading is a niche research problem in both areas of speech processing and computer vision. Current challenges for machine lip-reading fall into two groups: the content of the video, such as the rate at which a person is speaking or; the parameters of the video recording for example, the video resolution. We begin our work with a literature review to understand the restrictions current technology limits machine lip-reading recognition and conduct an experiment into resolution a�ects. We show that high de�nition video is not needed to successfully lip-read with a computer. The term \\viseme" is used in machine lip-reading to represent a visual cue or gesture which corresponds to a subgroup of phonemes where the phonemes are indistinguishable in the visual speech signal. Whilst a viseme is yet to be formally de�ned, we use the common working de�nition `a viseme is a group of phonemes with identical appearance on the lips'. A phoneme is the smallest acoustic unit a human can utter. Because there are more phonemes per viseme, mapping between the units creates a many-to-one relationship. Many mappings have been presented, and we conduct an experiment to determine which mapping produces the most accurate classi�cation. Our results show Lee's [82] is best. Lee's classi�cation also outperforms machine lip-reading systems which use the popular Fisher [48] phonemeto- viseme map. Further to this, we propose three methods of deriving speaker-dependent phonemeto- viseme maps and compare our new approaches to Lee's. Our results show the ii iii sensitivity of phoneme clustering and we use our new knowledge for our �rst suggested augmentation to the conventional lip-reading system. Speaker independence in machine lip-reading classi�cation is another unsolved obstacle. It has been observed, in the visual domain, that classi�ers need training on the test subject to achieve the best classi�cation. Thus machine lip-reading is highly dependent upon the speaker. Speaker independence is the opposite of this, or in other words, is the classi�cation of a speaker not present in the classi�er's training data. We investigate the dependence of phoneme-to-viseme maps between speakers. Our results show there is not a high variability of visual cues, but there is high variability in trajectory between visual cues of an individual speaker with the same ground truth. This implies a dependency upon the number of visemes within each set for each individual. Finally, we investigate how many visemes is the optimum number within a set. We show the phoneme-to-viseme maps in literature rarely have enough visemes and the optimal number, which varies by speaker, ranges from 11 to 35. The last di�culty we address is decoding from visemes back to phonemes and into words. Traditionally this is completed using a language model. The language model unit is either: the same as the classi�er, e.g. visemes or phonemes; or the language model unit is words. In a novel approach we use these optimum range viseme sets within hierarchical training of phoneme labelled classi�ers. This new method of classi�er training demonstrates signi�cant increase in classi�cation with a word language network.","abstract_has_math":false,"creators":["Bear, Helen L."],"institution":"University of East Anglia","degree_name":"phd","degree_level":"doctoral","degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2016,"date_issued":"2016-06","date_published":"2016-06","updated_at":"2026-07-24T02:12:16Z","subjects":[],"languages":["en"],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":null,"outbound_label":null,"outbound_source":null},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["Bear, Helen L."]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2016-06"]},{"key":"dc:date.issued","label":"Date","values":["2016-06"]},{"key":"dc:publisher.department","label":"Dc Publisher Department","values":["School of Computing Sciences"]},{"key":"dc:publisher.institution","label":"Dc Publisher Institution","values":["University of East Anglia"]},{"key":"dc:relation.isreferencedby","label":"Dc Relation Isreferencedby","values":["https://ueaeprints.uea.ac.uk/id/eprint/59384/"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"dc:type.qualificationlevel","label":"Dc Type Qualificationlevel","values":["doctoral"]},{"key":"dc:type.qualificationname","label":"Dc Type Qualificationname","values":["phd"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://ueaeprints.uea.ac.uk/id/eprint/59384/1/phdThesis_bear.pdf"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Abstract This thesis is about improving machine lip-reading, that is, the classi�cation of speech from only visual cues of a speaker. Machine lip-reading is a niche research problem in both areas of speech processing and computer vision. Current challenges for machine lip-reading fall into two groups: the content of the video, such as the rate at which a person is speaking or; the parameters of the video recording for example, the video resolution. We begin our work with a literature review to understand the restrictions current technology limits machine lip-reading recognition and conduct an experiment into resolution a�ects. We show that high de�nition video is not needed to successfully lip-read with a computer. The term \\viseme\" is used in machine lip-reading to represent a visual cue or gesture which corresponds to a subgroup of phonemes where the phonemes are indistinguishable in the visual speech signal. Whilst a viseme is yet to be formally de�ned, we use the common working de�nition `a viseme is a group of phonemes with identical appearance on the lips'. A phoneme is the smallest acoustic unit a human can utter. Because there are more phonemes per viseme, mapping between the units creates a many-to-one relationship. Many mappings have been presented, and we conduct an experiment to determine which mapping produces the most accurate classi�cation. Our results show Lee's [82] is best. Lee's classi�cation also outperforms machine lip-reading systems which use the popular Fisher [48] phonemeto- viseme map. Further to this, we propose three methods of deriving speaker-dependent phonemeto- viseme maps and compare our new approaches to Lee's. Our results show the ii iii sensitivity of phoneme clustering and we use our new knowledge for our �rst suggested augmentation to the conventional lip-reading system. Speaker independence in machine lip-reading classi�cation is another unsolved obstacle. It has been observed, in the visual domain, that classi�ers need training on the test subject to achieve the best classi�cation. Thus machine lip-reading is highly dependent upon the speaker. Speaker independence is the opposite of this, or in other words, is the classi�cation of a speaker not present in the classi�er's training data. We investigate the dependence of phoneme-to-viseme maps between speakers. Our results show there is not a high variability of visual cues, but there is high variability in trajectory between visual cues of an individual speaker with the same ground truth. This implies a dependency upon the number of visemes within each set for each individual. Finally, we investigate how many visemes is the optimum number within a set. We show the phoneme-to-viseme maps in literature rarely have enough visemes and the optimal number, which varies by speaker, ranges from 11 to 35. The last di�culty we address is decoding from visemes back to phonemes and into words. Traditionally this is completed using a language model. The language model unit is either: the same as the classi�er, e.g. visemes or phonemes; or the language model unit is words. In a novel approach we use these optimum range viseme sets within hierarchical training of phoneme labelled classi�ers. This new method of classi�er training demonstrates signi�cant increase in classi�cation with a word language network."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Decoding visemes: improving machine lip-reading"]}]}],"canonical_facts":{"dc:creator":["Bear, Helen L."],"dc:date":["2016-06"],"dc:date.issued":["2016-06"],"dc:description.abstract":["Abstract This thesis is about improving machine lip-reading, that is, the classi�cation of speech from only visual cues of a speaker. Machine lip-reading is a niche research problem in both areas of speech processing and computer vision. Current challenges for machine lip-reading fall into two groups: the content of the video, such as the rate at which a person is speaking or; the parameters of the video recording for example, the video resolution. We begin our work with a literature review to understand the restrictions current technology limits machine lip-reading recognition and conduct an experiment into resolution a�ects. We show that high de�nition video is not needed to successfully lip-read with a computer. The term \\viseme\" is used in machine lip-reading to represent a visual cue or gesture which corresponds to a subgroup of phonemes where the phonemes are indistinguishable in the visual speech signal. Whilst a viseme is yet to be formally de�ned, we use the common working de�nition `a viseme is a group of phonemes with identical appearance on the lips'. A phoneme is the smallest acoustic unit a human can utter. Because there are more phonemes per viseme, mapping between the units creates a many-to-one relationship. Many mappings have been presented, and we conduct an experiment to determine which mapping produces the most accurate classi�cation. Our results show Lee's [82] is best. Lee's classi�cation also outperforms machine lip-reading systems which use the popular Fisher [48] phonemeto- viseme map. Further to this, we propose three methods of deriving speaker-dependent phonemeto- viseme maps and compare our new approaches to Lee's. Our results show the ii iii sensitivity of phoneme clustering and we use our new knowledge for our �rst suggested augmentation to the conventional lip-reading system. Speaker independence in machine lip-reading classi�cation is another unsolved obstacle. It has been observed, in the visual domain, that classi�ers need training on the test subject to achieve the best classi�cation. Thus machine lip-reading is highly dependent upon the speaker. Speaker independence is the opposite of this, or in other words, is the classi�cation of a speaker not present in the classi�er's training data. We investigate the dependence of phoneme-to-viseme maps between speakers. Our results show there is not a high variability of visual cues, but there is high variability in trajectory between visual cues of an individual speaker with the same ground truth. This implies a dependency upon the number of visemes within each set for each individual. Finally, we investigate how many visemes is the optimum number within a set. We show the phoneme-to-viseme maps in literature rarely have enough visemes and the optimal number, which varies by speaker, ranges from 11 to 35. The last di�culty we address is decoding from visemes back to phonemes and into words. Traditionally this is completed using a language model. The language model unit is either: the same as the classi�er, e.g. visemes or phonemes; or the language model unit is words. In a novel approach we use these optimum range viseme sets within hierarchical training of phoneme labelled classi�ers. This new method of classi�er training demonstrates signi�cant increase in classi�cation with a word language network."],"dc:format":["application/pdf"],"dc:identifier.uri":["https://ueaeprints.uea.ac.uk/id/eprint/59384/1/phdThesis_bear.pdf"],"dc:language":["en"],"dc:publisher.department":["School of Computing Sciences"],"dc:publisher.institution":["University of East Anglia"],"dc:relation.isreferencedby":["https://ueaeprints.uea.ac.uk/id/eprint/59384/"],"dc:title":["Decoding visemes: improving machine lip-reading"],"dc:type":["Thesis"],"dc:type.qualificationlevel":["doctoral"],"dc:type.qualificationname":["phd"]},"updated_at":"2026-07-24T02:12:16Z"}