{"id":"https://openalex.org/W339366133","doi":"https://doi.org/10.21437/interspeech.2010-193","title":"Speech estimation in non-stationary noise environments using timing structures between mouth movements and sound signals","display_name":"Speech estimation in non-stationary noise environments using timing structures between mouth movements and sound signals","publication_year":2010,"publication_date":"2010-09-26","ids":{"openalex":"https://openalex.org/W339366133","doi":"https://doi.org/10.21437/interspeech.2010-193","mag":"339366133"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2010-193","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-193","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-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/A5102185295","display_name":"Hiroaki Kawashima","orcid":null},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I4210129581","display_name":"Kyoto University of Education","ror":"https://ror.org/03zhhr656","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210129581"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Hiroaki Kawashima","raw_affiliation_strings":["Kyoto univ"],"affiliations":[{"raw_affiliation_string":"Kyoto univ","institution_ids":["https://openalex.org/I22299242","https://openalex.org/I4210129581"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113676844","display_name":"Yu Horii","orcid":null},"institutions":[{"id":"https://openalex.org/I4210129581","display_name":"Kyoto University of Education","ror":"https://ror.org/03zhhr656","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210129581"]},{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yu Horii","raw_affiliation_strings":["Kyoto univ"],"affiliations":[{"raw_affiliation_string":"Kyoto univ","institution_ids":["https://openalex.org/I22299242","https://openalex.org/I4210129581"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102940139","display_name":"Takashi Matsuyama","orcid":"https://orcid.org/0000-0003-0666-0512"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I4210129581","display_name":"Kyoto University of Education","ror":"https://ror.org/03zhhr656","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210129581"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takashi Matsuyama","raw_affiliation_strings":["Kyoto univ"],"affiliations":[{"raw_affiliation_string":"Kyoto univ","institution_ids":["https://openalex.org/I22299242","https://openalex.org/I4210129581"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102185295"],"corresponding_institution_ids":["https://openalex.org/I22299242","https://openalex.org/I4210129581"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.01956052,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"442","last_page":"445"},"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":0.9966999888420105,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9937999844551086,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7894680500030518},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.728255033493042},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5893138647079468},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.500525712966919},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.49359095096588135},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.45840054750442505},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4564935266971588},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4492713510990143},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.44005775451660156},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43920961022377014},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3709290027618408},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.290244996547699},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.11919704079627991}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7894680500030518},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.728255033493042},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5893138647079468},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.500525712966919},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.49359095096588135},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.45840054750442505},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4564935266971588},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4492713510990143},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.44005775451660156},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43920961022377014},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3709290027618408},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.290244996547699},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.11919704079627991},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2010-193","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-193","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.593.1693","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.593.1693","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://vision.kuee.kyoto-u.ac.jp/japanese/happyou/pdf/Kawashima_2010_speechestimation_final.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W35070573","https://openalex.org/W1978380426","https://openalex.org/W1988572375","https://openalex.org/W2002591263","https://openalex.org/W2076044107","https://openalex.org/W2083393647","https://openalex.org/W2126597753","https://openalex.org/W2143400343","https://openalex.org/W2149072083","https://openalex.org/W2160337655","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W642007152","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W4304187160","https://openalex.org/W2052688117","https://openalex.org/W2552102772","https://openalex.org/W4294771049","https://openalex.org/W1523214805","https://openalex.org/W2168417340","https://openalex.org/W4229451372"],"abstract_inverted_index":{"A":[0],"variety":[1],"of":[2,16,29,92,95,112,120],"methods":[3,35],"for":[4,26],"audio-visual":[5],"integration,":[6],"which":[7],"inte-grate":[8],"audio":[9],"and":[10,84,98],"visual":[11],"information":[12,42],"at":[13],"the":[14,27,44,117,125,134],"level":[15],"either":[17],"features,":[18],"states,":[19],"or":[20],"classifier":[21],"outputs,":[22],"have":[23],"been":[24],"proposed":[25],"purpose":[28],"robust":[30],"speech":[31,59,74,114,131],"recognition.":[32],"However,":[33],"these":[34],"do":[36],"not":[37],"al-ways":[38],"fully":[39],"utilize":[40],"auditory":[41],"when":[43],"signal-to-noise":[45],"ratio":[46],"becomes":[47],"low.":[48],"In":[49],"this":[50,68],"paper,":[51],"we":[52,106,128],"propose":[53],"a":[54,90,108],"novel":[55],"approach":[56,69],"to":[57,71],"estimate":[58],"signal":[60],"in":[61],"noise":[62],"environments.":[63],"The":[64],"key":[65],"idea":[66],"behind":[67],"is":[70],"exploit":[72],"clean":[73,130],"candidates":[75,132],"gen-erated":[76],"by":[77,115],"using":[78],"timing":[79],"structures":[80],"between":[81],"mouth":[82,136],"movements":[83],"sound":[85],"signals.":[86],"We":[87],"first":[88],"extract":[89],"pair":[91],"feature":[93],"sequences":[94],"media":[96],"signals":[97],"segment":[99],"each":[100],"sequence":[101],"into":[102],"temporal":[103,118],"inter-vals.":[104],"Then,":[105],"construct":[107],"cross-media":[109],"timing-structure":[110],"model":[111],"human":[113],"learning":[116],"relations":[119],"overlap-ping":[121],"intervals.":[122],"Based":[123],"on":[124],"learned":[126],"model,":[127],"generate":[129],"from":[133],"observed":[135],"movements.":[137],"Index":[138],"Terms:":[139],"multimodal,":[140],"non-stationary":[141],"noise,":[142],"timing,":[143],"linear":[144],"dynamical":[145],"system,":[146],"particle":[147],"filtering":[148]},"counts_by_year":[{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
