Learning Speaker-specific Lip-to-Speech Generation Article Swipe
Munender Varshney
,
Ravindra Yadav
,
Vinay P. Namboodiri
,
Rajesh M. Hegde
·
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2206.02050
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2206.02050
Understanding the lip movement and inferring the speech from it is notoriously difficult for the common person. The task of accurate lip-reading gets help from various cues of the speaker and its contextual or environmental setting. Every speaker has a different accent and speaking style, which can be inferred from their visual and speech features. This work aims to understand the correlation/mapping between speech and the sequence of lip movement of individual speakers in an unconstrained and large vocabulary. We model the frame sequence as a prior to the transformer in an auto-encoder setting and learned a joint embedding that exploits temporal properties of both audio and video. We learn temporal synchronization using deep metric learning, which guides the decoder to generate speech in sync with input lip movements. The predictive posterior thus gives us the generated speech in speaker speaking style. We have trained our model on the Grid and Lip2Wav Chemistry lecture dataset to evaluate single speaker natural speech generation tasks from lip movement in an unconstrained natural setting. Extensive evaluation using various qualitative and quantitative metrics with human evaluation also shows that our method outperforms the Lip2Wav Chemistry dataset(large vocabulary in an unconstrained setting) by a good margin across almost all evaluation metrics and marginally outperforms the state-of-the-art on GRID dataset.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2206.02050
- https://arxiv.org/pdf/2206.02050
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4281723261
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4281723261Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2206.02050Digital Object Identifier
- Title
-
Learning Speaker-specific Lip-to-Speech GenerationWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2022Year of publication
- Publication date
-
2022-06-04Full publication date if available
- Authors
-
Munender Varshney, Ravindra Yadav, Vinay P. Namboodiri, Rajesh M. HegdeList of authors in order
- Landing page
-
https://arxiv.org/abs/2206.02050Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2206.02050Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2206.02050Direct OA link when available
- Concepts
-
Computer science, Speech recognition, Vocabulary, Hidden Markov model, Artificial intelligence, Chunking (psychology), Discriminative model, Margin (machine learning), Natural language processing, Machine learning, Linguistics, PhilosophyTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4281723261 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2206.02050 |
| ids.doi | https://doi.org/10.48550/arxiv.2206.02050 |
| ids.openalex | https://openalex.org/W4281723261 |
| fwci | |
| type | preprint |
| title | Learning Speaker-specific Lip-to-Speech Generation |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10860 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9994999766349792 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1711 |
| topics[0].subfield.display_name | Signal Processing |
| topics[0].display_name | Speech and Audio Processing |
| topics[1].id | https://openalex.org/T11448 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9700000286102295 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1707 |
| topics[1].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[1].display_name | Face recognition and analysis |
| topics[2].id | https://openalex.org/T13289 |
| topics[2].field.id | https://openalex.org/fields/36 |
| topics[2].field.display_name | Health Professions |
| topics[2].score | 0.9129999876022339 |
| topics[2].domain.id | https://openalex.org/domains/4 |
| topics[2].domain.display_name | Health Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/3611 |
| topics[2].subfield.display_name | Pharmacy |
| topics[2].display_name | Infant Health and Development |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.8115311861038208 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C28490314 |
| concepts[1].level | 1 |
| concepts[1].score | 0.7135622501373291 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q189436 |
| concepts[1].display_name | Speech recognition |
| concepts[2].id | https://openalex.org/C2777601683 |
| concepts[2].level | 2 |
| concepts[2].score | 0.520641028881073 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q6499736 |
| concepts[2].display_name | Vocabulary |
| concepts[3].id | https://openalex.org/C23224414 |
| concepts[3].level | 2 |
| concepts[3].score | 0.5153509974479675 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q176769 |
| concepts[3].display_name | Hidden Markov model |
| concepts[4].id | https://openalex.org/C154945302 |
| concepts[4].level | 1 |
| concepts[4].score | 0.46791011095046997 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[4].display_name | Artificial intelligence |
| concepts[5].id | https://openalex.org/C203357204 |
| concepts[5].level | 2 |
| concepts[5].score | 0.4672197103500366 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q1089605 |
| concepts[5].display_name | Chunking (psychology) |
| concepts[6].id | https://openalex.org/C97931131 |
| concepts[6].level | 2 |
| concepts[6].score | 0.4615843892097473 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q5282087 |
| concepts[6].display_name | Discriminative model |
| concepts[7].id | https://openalex.org/C774472 |
| concepts[7].level | 2 |
| concepts[7].score | 0.4523240029811859 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q6760393 |
| concepts[7].display_name | Margin (machine learning) |
| concepts[8].id | https://openalex.org/C204321447 |
| concepts[8].level | 1 |
| concepts[8].score | 0.34478959441185 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q30642 |
| concepts[8].display_name | Natural language processing |
| concepts[9].id | https://openalex.org/C119857082 |
| concepts[9].level | 1 |
| concepts[9].score | 0.1962626576423645 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[9].display_name | Machine learning |
| concepts[10].id | https://openalex.org/C41895202 |
| concepts[10].level | 1 |
| concepts[10].score | 0.0 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q8162 |
| concepts[10].display_name | Linguistics |
| concepts[11].id | https://openalex.org/C138885662 |
| concepts[11].level | 0 |
| concepts[11].score | 0.0 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q5891 |
| concepts[11].display_name | Philosophy |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.8115311861038208 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/speech-recognition |
| keywords[1].score | 0.7135622501373291 |
| keywords[1].display_name | Speech recognition |
| keywords[2].id | https://openalex.org/keywords/vocabulary |
| keywords[2].score | 0.520641028881073 |
| keywords[2].display_name | Vocabulary |
| keywords[3].id | https://openalex.org/keywords/hidden-markov-model |
| keywords[3].score | 0.5153509974479675 |
| keywords[3].display_name | Hidden Markov model |
| keywords[4].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[4].score | 0.46791011095046997 |
| keywords[4].display_name | Artificial intelligence |
| keywords[5].id | https://openalex.org/keywords/chunking |
| keywords[5].score | 0.4672197103500366 |
| keywords[5].display_name | Chunking (psychology) |
| keywords[6].id | https://openalex.org/keywords/discriminative-model |
| keywords[6].score | 0.4615843892097473 |
| keywords[6].display_name | Discriminative model |
| keywords[7].id | https://openalex.org/keywords/margin |
| keywords[7].score | 0.4523240029811859 |
| keywords[7].display_name | Margin (machine learning) |
| keywords[8].id | https://openalex.org/keywords/natural-language-processing |
| keywords[8].score | 0.34478959441185 |
| keywords[8].display_name | Natural language processing |
| keywords[9].id | https://openalex.org/keywords/machine-learning |
| keywords[9].score | 0.1962626576423645 |
| keywords[9].display_name | Machine learning |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2206.02050 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400194 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | arXiv (Cornell University) |
| locations[0].source.host_organization | https://openalex.org/I205783295 |
| locations[0].source.host_organization_name | Cornell University |
| locations[0].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[0].license | cc-by |
| locations[0].pdf_url | https://arxiv.org/pdf/2206.02050 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| locations[0].license_id | https://openalex.org/licenses/cc-by |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2206.02050 |
| locations[1].id | doi:10.48550/arxiv.2206.02050 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306400194 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | True |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | arXiv (Cornell University) |
| locations[1].source.host_organization | https://openalex.org/I205783295 |
| locations[1].source.host_organization_name | Cornell University |
| locations[1].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[1].license | cc-by |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | https://openalex.org/licenses/cc-by |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://doi.org/10.48550/arxiv.2206.02050 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5036559623 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-3061-5757 |
| authorships[0].author.display_name | Munender Varshney |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Varshney, Munender |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5010648323 |
| authorships[1].author.orcid | https://orcid.org/0000-0003-4628-0688 |
| authorships[1].author.display_name | Ravindra Yadav |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Yadav, Ravindra |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5007109424 |
| authorships[2].author.orcid | https://orcid.org/0000-0001-5262-9722 |
| authorships[2].author.display_name | Vinay P. Namboodiri |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Namboodiri, Vinay P. |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5085503354 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-6142-7724 |
| authorships[3].author.display_name | Rajesh M. Hegde |
| authorships[3].author_position | last |
| authorships[3].raw_author_name | Hegde, Rajesh M |
| authorships[3].is_corresponding | False |
| has_content.pdf | True |
| has_content.grobid_xml | True |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2206.02050 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Learning Speaker-specific Lip-to-Speech Generation |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10860 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9994999766349792 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1711 |
| primary_topic.subfield.display_name | Signal Processing |
| primary_topic.display_name | Speech and Audio Processing |
| related_works | https://openalex.org/W2384729545, https://openalex.org/W2198395236, https://openalex.org/W2800417007, https://openalex.org/W147604216, https://openalex.org/W4389116644, https://openalex.org/W2153315159, https://openalex.org/W3103844505, https://openalex.org/W2161080928, https://openalex.org/W259157601, https://openalex.org/W2167155152 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2206.02050 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306400194 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | arXiv (Cornell University) |
| best_oa_location.source.host_organization | https://openalex.org/I205783295 |
| best_oa_location.source.host_organization_name | Cornell University |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| best_oa_location.license | cc-by |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2206.02050 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | text |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | http://arxiv.org/abs/2206.02050 |
| primary_location.id | pmh:oai:arXiv.org:2206.02050 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400194 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | arXiv (Cornell University) |
| primary_location.source.host_organization | https://openalex.org/I205783295 |
| primary_location.source.host_organization_name | Cornell University |
| primary_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| primary_location.license | cc-by |
| primary_location.pdf_url | https://arxiv.org/pdf/2206.02050 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| primary_location.license_id | https://openalex.org/licenses/cc-by |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2206.02050 |
| publication_date | 2022-06-04 |
| publication_year | 2022 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 39, 85, 96, 198 |
| abstract_inverted_index.We | 79, 108, 142 |
| abstract_inverted_index.an | 74, 91, 167, 194 |
| abstract_inverted_index.as | 84 |
| abstract_inverted_index.be | 47 |
| abstract_inverted_index.by | 197 |
| abstract_inverted_index.in | 73, 90, 123, 138, 166, 193 |
| abstract_inverted_index.is | 10 |
| abstract_inverted_index.it | 9 |
| abstract_inverted_index.of | 19, 27, 67, 70, 103 |
| abstract_inverted_index.on | 147, 211 |
| abstract_inverted_index.or | 33 |
| abstract_inverted_index.to | 58, 87, 120, 155 |
| abstract_inverted_index.us | 134 |
| abstract_inverted_index.The | 17, 129 |
| abstract_inverted_index.all | 203 |
| abstract_inverted_index.and | 4, 30, 42, 52, 64, 76, 94, 106, 150, 176, 206 |
| abstract_inverted_index.can | 46 |
| abstract_inverted_index.for | 13 |
| abstract_inverted_index.has | 38 |
| abstract_inverted_index.its | 31 |
| abstract_inverted_index.lip | 2, 68, 127, 164 |
| abstract_inverted_index.our | 145, 185 |
| abstract_inverted_index.the | 1, 6, 14, 28, 60, 65, 81, 88, 118, 135, 148, 188, 209 |
| abstract_inverted_index.GRID | 212 |
| abstract_inverted_index.Grid | 149 |
| abstract_inverted_index.This | 55 |
| abstract_inverted_index.aims | 57 |
| abstract_inverted_index.also | 182 |
| abstract_inverted_index.both | 104 |
| abstract_inverted_index.cues | 26 |
| abstract_inverted_index.deep | 113 |
| abstract_inverted_index.from | 8, 24, 49, 163 |
| abstract_inverted_index.gets | 22 |
| abstract_inverted_index.good | 199 |
| abstract_inverted_index.have | 143 |
| abstract_inverted_index.help | 23 |
| abstract_inverted_index.sync | 124 |
| abstract_inverted_index.task | 18 |
| abstract_inverted_index.that | 99, 184 |
| abstract_inverted_index.thus | 132 |
| abstract_inverted_index.with | 125, 179 |
| abstract_inverted_index.work | 56 |
| abstract_inverted_index.Every | 36 |
| abstract_inverted_index.audio | 105 |
| abstract_inverted_index.frame | 82 |
| abstract_inverted_index.gives | 133 |
| abstract_inverted_index.human | 180 |
| abstract_inverted_index.input | 126 |
| abstract_inverted_index.joint | 97 |
| abstract_inverted_index.large | 77 |
| abstract_inverted_index.learn | 109 |
| abstract_inverted_index.model | 80, 146 |
| abstract_inverted_index.prior | 86 |
| abstract_inverted_index.shows | 183 |
| abstract_inverted_index.tasks | 162 |
| abstract_inverted_index.their | 50 |
| abstract_inverted_index.using | 112, 173 |
| abstract_inverted_index.which | 45, 116 |
| abstract_inverted_index.accent | 41 |
| abstract_inverted_index.across | 201 |
| abstract_inverted_index.almost | 202 |
| abstract_inverted_index.common | 15 |
| abstract_inverted_index.guides | 117 |
| abstract_inverted_index.margin | 200 |
| abstract_inverted_index.method | 186 |
| abstract_inverted_index.metric | 114 |
| abstract_inverted_index.single | 157 |
| abstract_inverted_index.speech | 7, 53, 63, 122, 137, 160 |
| abstract_inverted_index.style, | 44 |
| abstract_inverted_index.style. | 141 |
| abstract_inverted_index.video. | 107 |
| abstract_inverted_index.visual | 51 |
| abstract_inverted_index.Lip2Wav | 151, 189 |
| abstract_inverted_index.between | 62 |
| abstract_inverted_index.dataset | 154 |
| abstract_inverted_index.decoder | 119 |
| abstract_inverted_index.learned | 95 |
| abstract_inverted_index.lecture | 153 |
| abstract_inverted_index.metrics | 178, 205 |
| abstract_inverted_index.natural | 159, 169 |
| abstract_inverted_index.person. | 16 |
| abstract_inverted_index.setting | 93 |
| abstract_inverted_index.speaker | 29, 37, 139, 158 |
| abstract_inverted_index.trained | 144 |
| abstract_inverted_index.various | 25, 174 |
| abstract_inverted_index.accurate | 20 |
| abstract_inverted_index.dataset. | 213 |
| abstract_inverted_index.evaluate | 156 |
| abstract_inverted_index.exploits | 100 |
| abstract_inverted_index.generate | 121 |
| abstract_inverted_index.inferred | 48 |
| abstract_inverted_index.movement | 3, 69, 165 |
| abstract_inverted_index.sequence | 66, 83 |
| abstract_inverted_index.setting) | 196 |
| abstract_inverted_index.setting. | 35, 170 |
| abstract_inverted_index.speakers | 72 |
| abstract_inverted_index.speaking | 43, 140 |
| abstract_inverted_index.temporal | 101, 110 |
| abstract_inverted_index.Chemistry | 152, 190 |
| abstract_inverted_index.Extensive | 171 |
| abstract_inverted_index.different | 40 |
| abstract_inverted_index.difficult | 12 |
| abstract_inverted_index.embedding | 98 |
| abstract_inverted_index.features. | 54 |
| abstract_inverted_index.generated | 136 |
| abstract_inverted_index.inferring | 5 |
| abstract_inverted_index.learning, | 115 |
| abstract_inverted_index.posterior | 131 |
| abstract_inverted_index.contextual | 32 |
| abstract_inverted_index.evaluation | 172, 181, 204 |
| abstract_inverted_index.generation | 161 |
| abstract_inverted_index.individual | 71 |
| abstract_inverted_index.marginally | 207 |
| abstract_inverted_index.movements. | 128 |
| abstract_inverted_index.predictive | 130 |
| abstract_inverted_index.properties | 102 |
| abstract_inverted_index.understand | 59 |
| abstract_inverted_index.vocabulary | 192 |
| abstract_inverted_index.lip-reading | 21 |
| abstract_inverted_index.notoriously | 11 |
| abstract_inverted_index.outperforms | 187, 208 |
| abstract_inverted_index.qualitative | 175 |
| abstract_inverted_index.transformer | 89 |
| abstract_inverted_index.vocabulary. | 78 |
| abstract_inverted_index.auto-encoder | 92 |
| abstract_inverted_index.quantitative | 177 |
| abstract_inverted_index.Understanding | 0 |
| abstract_inverted_index.dataset(large | 191 |
| abstract_inverted_index.environmental | 34 |
| abstract_inverted_index.unconstrained | 75, 168, 195 |
| abstract_inverted_index.synchronization | 111 |
| abstract_inverted_index.state-of-the-art | 210 |
| abstract_inverted_index.correlation/mapping | 61 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 4 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/4 |
| sustainable_development_goals[0].score | 0.8500000238418579 |
| sustainable_development_goals[0].display_name | Quality Education |
| citation_normalized_percentile |