{"id":"https://openalex.org/W2293856338","doi":"https://doi.org/10.21437/interspeech.2015-139","title":"Reconstructing intelligible audio speech from visual speech features","display_name":"Reconstructing intelligible audio speech from visual speech features","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W2293856338","doi":"https://doi.org/10.21437/interspeech.2015-139","mag":"2293856338"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-139","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-139","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://ueaeprints.uea.ac.uk/id/eprint/56718/1/interspeech_v2a_2015.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022796258","display_name":"Thomas Le Cornu","orcid":null},"institutions":[{"id":"https://openalex.org/I1118541","display_name":"University of East Anglia","ror":"https://ror.org/026k5mg93","country_code":"GB","type":"education","lineage":["https://openalex.org/I1118541"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Thomas Le Cornu","raw_affiliation_strings":["University of East Anglia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of East Anglia","institution_ids":["https://openalex.org/I1118541"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023076395","display_name":"Ben Milner","orcid":null},"institutions":[{"id":"https://openalex.org/I1118541","display_name":"University of East Anglia","ror":"https://ror.org/026k5mg93","country_code":"GB","type":"education","lineage":["https://openalex.org/I1118541"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ben Milner","raw_affiliation_strings":["University of East Anglia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of East Anglia","institution_ids":["https://openalex.org/I1118541"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0297,"has_fulltext":true,"cited_by_count":46,"citation_normalized_percentile":{"value":0.88061418,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3355","last_page":"3359"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7674434781074524},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.742816150188446},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.616127073764801},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.5556040406227112},{"id":"https://openalex.org/keywords/viseme","display_name":"Viseme","score":0.5096733570098877},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.48214980959892273},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.4527549743652344},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.42833733558654785},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.3836022913455963},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.36207157373428345},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35554149746894836},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.1786903440952301}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7674434781074524},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.742816150188446},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.616127073764801},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.5556040406227112},{"id":"https://openalex.org/C33767174","wikidata":"https://www.wikidata.org/wiki/Q371190","display_name":"Viseme","level":4,"score":0.5096733570098877},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.48214980959892273},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.4527549743652344},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.42833733558654785},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.3836022913455963},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.36207157373428345},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35554149746894836},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.1786903440952301}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2015-139","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-139","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},{"id":"pmh:oai:ueaeprints.uea.ac.uk:56718","is_oa":true,"landing_page_url":null,"pdf_url":"https://ueaeprints.uea.ac.uk/id/eprint/56718/1/interspeech_v2a_2015.pdf","source":{"id":"https://openalex.org/S4306400384","display_name":"UEA Digital Repository (University of East Anglia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1118541","host_organization_name":"University of East Anglia","host_organization_lineage":["https://openalex.org/I1118541"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"best_oa_location":{"id":"pmh:oai:ueaeprints.uea.ac.uk:56718","is_oa":true,"landing_page_url":null,"pdf_url":"https://ueaeprints.uea.ac.uk/id/eprint/56718/1/interspeech_v2a_2015.pdf","source":{"id":"https://openalex.org/S4306400384","display_name":"UEA Digital Repository (University of East Anglia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1118541","host_organization_name":"University of East Anglia","host_organization_lineage":["https://openalex.org/I1118541"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2293856338.pdf","grobid_xml":"https://content.openalex.org/works/W2293856338.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W142803501","https://openalex.org/W1554064406","https://openalex.org/W1588594383","https://openalex.org/W1875231349","https://openalex.org/W1999673299","https://openalex.org/W2015143272","https://openalex.org/W2018651852","https://openalex.org/W2038010270","https://openalex.org/W2049686551","https://openalex.org/W2062227835","https://openalex.org/W2069238044","https://openalex.org/W2104263160","https://openalex.org/W2116529913","https://openalex.org/W2121430128","https://openalex.org/W2127211243","https://openalex.org/W2129082420","https://openalex.org/W2143908786","https://openalex.org/W2160815625","https://openalex.org/W2164764235","https://openalex.org/W2165856656","https://openalex.org/W2172803778","https://openalex.org/W2397008871","https://openalex.org/W3143833948"],"related_works":["https://openalex.org/W2496295964","https://openalex.org/W2336887028","https://openalex.org/W1984921740","https://openalex.org/W2365485488","https://openalex.org/W2070982348","https://openalex.org/W1911859126","https://openalex.org/W1891685057","https://openalex.org/W642007152","https://openalex.org/W2184127972","https://openalex.org/W2218471654"],"abstract_inverted_index":{"This":[0],"work":[1],"describes":[2],"an":[3,37,53],"investigation":[4],"into":[5],"the":[6,81,94,97,105],"feasibility":[7],"of":[8,47,58,71,80,96],"producing":[9],"intelligible":[10],"audio":[11,54,59,83],"speech":[12,16,48,84],"from":[13,29],"only":[14,100],"visual":[15,30,61],"fea-":[17],"tures.":[18],"The":[19,78],"proposed":[20],"method":[21,70],"aims":[22],"to":[23,51,93],"estimate":[24],"a":[25,45,68,74],"spectral":[26],"enve-":[27],"lope":[28],"features":[31,62],"which":[32],"is":[33,85],"then":[34,91],"combined":[35,103],"with":[36,66,104],"arti-":[38],"ficial":[39],"excitation":[40],"signal":[41,99],"and":[42,60,73,90,101],"used":[43],"within":[44],"model":[46],"pro-":[49],"duction":[50],"reconstruct":[52],"signal.":[55],"Different":[56],"combinations":[57],"are":[63],"considered,":[64],"along":[65],"both":[67],"statistical":[69],"estimation":[72],"deep":[75],"neural":[76],"network.":[77],"intelligibility":[79,95],"reconstructed":[82,106],"measured":[86],"by":[87],"human":[88],"listeners,":[89],"compared":[92],"video":[98],"when":[102],"audio.":[107]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
