{"id":"https://openalex.org/W4391678256","doi":"https://doi.org/10.1109/sii58957.2024.10417556","title":"Synthesis of Speech Reflecting Features from Lip Images","display_name":"Synthesis of Speech Reflecting Features from Lip Images","publication_year":2024,"publication_date":"2024-01-08","ids":{"openalex":"https://openalex.org/W4391678256","doi":"https://doi.org/10.1109/sii58957.2024.10417556"},"language":"en","primary_location":{"id":"doi:10.1109/sii58957.2024.10417556","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/sii58957.2024.10417556","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/SICE International Symposium on System Integration (SII)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5076264855","display_name":"Atsushi Matsuura","orcid":null},"institutions":[{"id":"https://openalex.org/I171481255","display_name":"Shibaura Institute of Technology","ror":"https://ror.org/020wjcq07","country_code":"JP","type":"education","lineage":["https://openalex.org/I171481255"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsushi Matsuura","raw_affiliation_strings":["Shibaura Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shibaura Institute of Technology","institution_ids":["https://openalex.org/I171481255"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112678712","display_name":"Sota Shimizu","orcid":null},"institutions":[{"id":"https://openalex.org/I171481255","display_name":"Shibaura Institute of Technology","ror":"https://ror.org/020wjcq07","country_code":"JP","type":"education","lineage":["https://openalex.org/I171481255"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sota Shimizu","raw_affiliation_strings":["Shibaura Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shibaura Institute of Technology","institution_ids":["https://openalex.org/I171481255"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I171481255"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"153","last_page":"158"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9991000294685364,"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":0.9991000294685364,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11448","display_name":"Face recognition and analysis","score":0.9847999811172485,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6510894894599915},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5405716896057129},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4866710305213928},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.40953370928764343}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6510894894599915},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5405716896057129},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4866710305213928},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40953370928764343}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sii58957.2024.10417556","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/sii58957.2024.10417556","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/SICE International Symposium on System Integration (SII)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3374738166","display_name":"Study on Drive Control Method for Rapid Attention Point Movement of Liquid Crystal Wide Angle Fovea Sensor","funder_award_id":"21K03983","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W2120847449","https://openalex.org/W2519091744","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W3015645837","https://openalex.org/W3160077247"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Recently,":[0],"models":[1],"that":[2,32,55,66],"synthesize":[3],"speech":[4,30,65],"from":[5],"multimodal":[6],"information":[7,24],"other":[8],"than":[9],"text":[10],"have":[11,15,61],"been":[12],"devised":[13],"and":[14,25,47],"attracted":[16],"much":[17],"attention.":[18],"We":[19,60],"focus":[20],"on":[21],"lip":[22,34,68],"image":[23,41],"propose":[26],"a":[27,57],"model":[28,50],"for":[29],"synthesis":[31],"reflects":[33,67],"movements.":[35],"The":[36],"architecture":[37],"consists":[38],"of":[39],"an":[40,45,48],"feature":[42],"extractor":[43],"using":[44],"autoencoder":[46],"encoder-decoder":[49],"similar":[51],"to":[52],"the":[53],"Tacotron2":[54],"outputs":[56],"mel":[58],"spectrogram.":[59],"succeeded":[62],"in":[63],"synthesizing":[64],"movements":[69],"under":[70],"limited":[71],"conditions.":[72]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
