{"id":"https://openalex.org/W4378231186","doi":"https://doi.org/10.1007/s10772-023-10030-3","title":"Mouth2Audio: intelligible audio synthesis from videos with distinctive vowel articulation","display_name":"Mouth2Audio: intelligible audio synthesis from videos with distinctive vowel articulation","publication_year":2023,"publication_date":"2023-05-25","ids":{"openalex":"https://openalex.org/W4378231186","doi":"https://doi.org/10.1007/s10772-023-10030-3"},"language":"en","primary_location":{"id":"doi:10.1007/s10772-023-10030-3","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10772-023-10030-3","pdf_url":null,"source":{"id":"https://openalex.org/S4650632","display_name":"International Journal of Speech Technology","issn_l":"1381-2416","issn":["1381-2416","1572-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Speech Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013136179","display_name":"Saurabh Garg","orcid":"https://orcid.org/0000-0001-8719-284X"},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Saurabh Garg","raw_affiliation_strings":["Language and Brain Lab, Department of Linguistics, Simon Fraser University, Burnaby, Canada","School of Computing Science, Simon Fraser University, Burnaby, Canada"],"affiliations":[{"raw_affiliation_string":"Language and Brain Lab, Department of Linguistics, Simon Fraser University, Burnaby, Canada","institution_ids":["https://openalex.org/I18014758"]},{"raw_affiliation_string":"School of Computing Science, Simon Fraser University, Burnaby, Canada","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005850573","display_name":"Haoyao Ruan","orcid":null},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Haoyao Ruan","raw_affiliation_strings":["Language and Brain Lab, Department of Linguistics, Simon Fraser University, Burnaby, Canada"],"affiliations":[{"raw_affiliation_string":"Language and Brain Lab, Department of Linguistics, Simon Fraser University, Burnaby, Canada","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072684302","display_name":"Ghassan Hamarneh","orcid":"https://orcid.org/0000-0001-5040-7448"},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ghassan Hamarneh","raw_affiliation_strings":["School of Computing Science, Simon Fraser University, Burnaby, Canada"],"affiliations":[{"raw_affiliation_string":"School of Computing Science, Simon Fraser University, Burnaby, Canada","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074465040","display_name":"Dawn M. Behne","orcid":null},"institutions":[{"id":"https://openalex.org/I204778367","display_name":"Norwegian University of Science and Technology","ror":"https://ror.org/05xg72x27","country_code":"NO","type":"education","lineage":["https://openalex.org/I204778367"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Dawn M. Behne","raw_affiliation_strings":["Department of Psychology, Norwegian University of Science and Technology, Trondheim, Norway"],"affiliations":[{"raw_affiliation_string":"Department of Psychology, Norwegian University of Science and Technology, Trondheim, Norway","institution_ids":["https://openalex.org/I204778367"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068290371","display_name":"Allard Jongman","orcid":"https://orcid.org/0000-0002-7384-2036"},"institutions":[{"id":"https://openalex.org/I146416000","display_name":"University of Kansas","ror":"https://ror.org/001tmjg57","country_code":"US","type":"education","lineage":["https://openalex.org/I146416000"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Allard Jongman","raw_affiliation_strings":["KU Phonetics and Psycholinguistics Lab, Department of Linguistics, The University of Kansas, Lawrence, USA"],"affiliations":[{"raw_affiliation_string":"KU Phonetics and Psycholinguistics Lab, Department of Linguistics, The University of Kansas, Lawrence, USA","institution_ids":["https://openalex.org/I146416000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080409793","display_name":"Joan A. Sereno","orcid":"https://orcid.org/0000-0002-1227-7715"},"institutions":[{"id":"https://openalex.org/I146416000","display_name":"University of Kansas","ror":"https://ror.org/001tmjg57","country_code":"US","type":"education","lineage":["https://openalex.org/I146416000"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joan Sereno","raw_affiliation_strings":["KU Phonetics and Psycholinguistics Lab, Department of Linguistics, The University of Kansas, Lawrence, USA"],"affiliations":[{"raw_affiliation_string":"KU Phonetics and Psycholinguistics Lab, Department of Linguistics, The University of Kansas, Lawrence, USA","institution_ids":["https://openalex.org/I146416000"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100371992","display_name":"Yue Wang","orcid":"https://orcid.org/0000-0002-0981-935X"},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Yue Wang","raw_affiliation_strings":["Language and Brain Lab, Department of Linguistics, Simon Fraser University, Burnaby, Canada"],"affiliations":[{"raw_affiliation_string":"Language and Brain Lab, Department of Linguistics, Simon Fraser University, Burnaby, Canada","institution_ids":["https://openalex.org/I18014758"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5013136179"],"corresponding_institution_ids":["https://openalex.org/I18014758"],"apc_list":{"value":2190,"currency":"EUR","value_usd":2780},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04787563,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"26","issue":"2","first_page":"459","last_page":"474"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9990000128746033,"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":0.9948999881744385,"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":0.804826021194458},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7327524423599243},{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.7290191054344177},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6367897391319275},{"id":"https://openalex.org/keywords/manner-of-articulation","display_name":"Manner of articulation","score":0.5539700388908386},{"id":"https://openalex.org/keywords/landmark","display_name":"Landmark","score":0.5525151491165161},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.5293638706207275},{"id":"https://openalex.org/keywords/articulation","display_name":"Articulation (sociology)","score":0.5256734490394592},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37014779448509216}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.804826021194458},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7327524423599243},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.7290191054344177},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6367897391319275},{"id":"https://openalex.org/C66029223","wikidata":"https://www.wikidata.org/wiki/Q210847","display_name":"Manner of articulation","level":2,"score":0.5539700388908386},{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.5525151491165161},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.5293638706207275},{"id":"https://openalex.org/C2779337067","wikidata":"https://www.wikidata.org/wiki/Q4800961","display_name":"Articulation (sociology)","level":3,"score":0.5256734490394592},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37014779448509216},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10772-023-10030-3","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10772-023-10030-3","pdf_url":null,"source":{"id":"https://openalex.org/S4650632","display_name":"International Journal of Speech Technology","issn_l":"1381-2416","issn":["1381-2416","1572-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Speech Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.47999998927116394,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G3960574281","display_name":null,"funder_award_id":"435-2019-1065","funder_id":"https://openalex.org/F4320334617","funder_display_name":"Social Sciences and Humanities Research Council of Canada"}],"funders":[{"id":"https://openalex.org/F4320322551","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28"},{"id":"https://openalex.org/F4320334617","display_name":"Social Sciences and Humanities Research Council of Canada","ror":"https://ror.org/04j5jqy92"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W111481493","https://openalex.org/W824148805","https://openalex.org/W1488659701","https://openalex.org/W1608599857","https://openalex.org/W1880232642","https://openalex.org/W1975929202","https://openalex.org/W1978663662","https://openalex.org/W1981298914","https://openalex.org/W1990092081","https://openalex.org/W1995735739","https://openalex.org/W2007415209","https://openalex.org/W2007810428","https://openalex.org/W2008252381","https://openalex.org/W2014621385","https://openalex.org/W2015143272","https://openalex.org/W2021788671","https://openalex.org/W2045322128","https://openalex.org/W2055243886","https://openalex.org/W2056133372","https://openalex.org/W2059169992","https://openalex.org/W2061657237","https://openalex.org/W2064075936","https://openalex.org/W2070696251","https://openalex.org/W2071323752","https://openalex.org/W2087769310","https://openalex.org/W2087919634","https://openalex.org/W2104393052","https://openalex.org/W2109606373","https://openalex.org/W2117429367","https://openalex.org/W2117597945","https://openalex.org/W2118004237","https://openalex.org/W2120847449","https://openalex.org/W2127211243","https://openalex.org/W2144205901","https://openalex.org/W2150411511","https://openalex.org/W2155959083","https://openalex.org/W2163267561","https://openalex.org/W2171878011","https://openalex.org/W2293856338","https://openalex.org/W2341528187","https://openalex.org/W2499854530","https://openalex.org/W2550778560","https://openalex.org/W2585824449","https://openalex.org/W2898060811","https://openalex.org/W2903345706","https://openalex.org/W2916979304","https://openalex.org/W2964352155","https://openalex.org/W2970709561","https://openalex.org/W2972563022","https://openalex.org/W2990138404","https://openalex.org/W3028348164","https://openalex.org/W3035626590","https://openalex.org/W3045497008","https://openalex.org/W3083438180","https://openalex.org/W3101998545","https://openalex.org/W3157840621","https://openalex.org/W4210396727","https://openalex.org/W4213129550","https://openalex.org/W4224926225","https://openalex.org/W4299524734","https://openalex.org/W6639350448","https://openalex.org/W6677618333"],"related_works":["https://openalex.org/W2025848302","https://openalex.org/W1975454382","https://openalex.org/W2799441357","https://openalex.org/W5449343","https://openalex.org/W2409530148","https://openalex.org/W2053642297","https://openalex.org/W4250508028","https://openalex.org/W2028715205","https://openalex.org/W2344358524","https://openalex.org/W2050311283"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
