{"id":"https://openalex.org/W26996859","doi":"https://doi.org/10.21437/interspeech.2010-711","title":"Audio-visual anticipatory coarticulation modeling by human and machine","display_name":"Audio-visual anticipatory coarticulation modeling by human and machine","publication_year":2010,"publication_date":"2010-09-26","ids":{"openalex":"https://openalex.org/W26996859","doi":"https://doi.org/10.21437/interspeech.2010-711","mag":"26996859"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2010-711","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-711","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":"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/A5059307358","display_name":"Louis H. Terry","orcid":null},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Louis H. Terry","raw_affiliation_strings":["Northwestern University****"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern University****","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015602781","display_name":"Karen Livescu","orcid":"https://orcid.org/0000-0003-4962-946X"},"institutions":[{"id":"https://openalex.org/I4840577","display_name":"Toyota Technological Institute","ror":"https://ror.org/001hv0k59","country_code":"JP","type":"education","lineage":["https://openalex.org/I4840577"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Karen Livescu","raw_affiliation_strings":["Toyota Technological Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute","institution_ids":["https://openalex.org/I4840577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049920688","display_name":"Janet B. Pierrehumbert","orcid":"https://orcid.org/0000-0002-5989-3574"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Janet B. Pierrehumbert","raw_affiliation_strings":["Northwestern University****"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern University****","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048650003","display_name":"Aggelos K. Katsaggelos","orcid":"https://orcid.org/0000-0003-4554-0070"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aggelos K. Katsaggelos","raw_affiliation_strings":["Electrical Engineering and Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical Engineering and Computer Science","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3201,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.38332038,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2682","last_page":"2685"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9975000023841858,"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/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.9922999739646912,"subfield":{"id":"https://openalex.org/subfields/1309","display_name":"Developmental Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/coarticulation","display_name":"Coarticulation","score":0.9650592803955078},{"id":"https://openalex.org/keywords/asynchrony","display_name":"Asynchrony (computer programming)","score":0.8978656530380249},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6879762411117554},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6348977088928223},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5975133776664734},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41425538063049316},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34839484095573425},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.08926671743392944}],"concepts":[{"id":"https://openalex.org/C130727458","wikidata":"https://www.wikidata.org/wiki/Q1639109","display_name":"Coarticulation","level":3,"score":0.9650592803955078},{"id":"https://openalex.org/C2779019669","wikidata":"https://www.wikidata.org/wiki/Q25203946","display_name":"Asynchrony (computer programming)","level":3,"score":0.8978656530380249},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6879762411117554},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6348977088928223},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5975133776664734},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41425538063049316},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34839484095573425},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.08926671743392944},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2010-711","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-711","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:10.1.1.343.1932","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.343.1932","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ivpl.ece.northwestern.edu/system/files/async_align.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.661.8636","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.661.8636","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://faculty.wcas.northwestern.edu/%7Ejbp/publications/AV_Interspeech.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5600000023841858},{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1493001747","https://openalex.org/W1974783905","https://openalex.org/W1982707956","https://openalex.org/W2015143272","https://openalex.org/W2029996593","https://openalex.org/W2048198238","https://openalex.org/W2076347773","https://openalex.org/W2122678358","https://openalex.org/W2144491988","https://openalex.org/W2157190406","https://openalex.org/W2164450870","https://openalex.org/W2167159094"],"related_works":["https://openalex.org/W2990278625","https://openalex.org/W1993499045","https://openalex.org/W1604595447","https://openalex.org/W4200613756","https://openalex.org/W2983489261","https://openalex.org/W2988239832","https://openalex.org/W2075885261","https://openalex.org/W2174601236","https://openalex.org/W2172236910","https://openalex.org/W2149105670"],"abstract_inverted_index":{"The":[0,117,149],"phenomenon":[1],"of":[2,18,26,48,75,108,167],"anticipatory":[3,147,180],"coarticulation":[4],"provides":[5],"a":[6,71,121,131],"ba-sis":[7],"for":[8,155,164,170],"the":[9,13,66,78,96,106,114,127,165],"observed":[10],"asynchrony":[11,27,44,56],"between":[12,87],"acoustic":[14],"and":[15,59,89,98,135],"vi-sual":[16],"onsets":[17],"phones":[19],"in":[20,33,50,125,130],"certain":[21],"linguistic":[22,171],"contexts.":[23],"This":[24,83],"type":[25],"is":[28],"typically":[29],"not":[30,103],"explicitly":[31],"modeled":[32],"audio-visual":[34,43,55,76,175,178],"speech":[35,156,176],"models.":[36],"In":[37],"this":[38],"work,":[39],"we":[40,160],"study":[41],"within-word":[42],"using":[45],"manual":[46],"labels":[47,64,129],"words":[49],"which":[51],"theory":[52],"suggests":[53],"that":[54,61,109],"should":[57],"occur,":[58],"show":[60],"these":[62],"hand":[63,128],"confirm":[65],"theory.":[67],"We":[68],"then":[69],"introduce":[70],"new":[72],"statistical":[73],"model":[74,84,119,124,151],"speech,":[77],"asynchrony-dependent":[79],"transition":[80],"(ADT)":[81],"model.":[82],"allows":[85],"asyn-chrony":[86],"audio":[88,97],"video":[90,99],"states":[91],"within":[92],"word":[93],"boundaries,":[94],"where":[95],"state":[100,107],"transitions":[101],"depend":[102],"only":[104,163],"on":[105,113],"modality,":[110],"but":[111],"also":[112],"instantaneous":[115],"asyn-chrony.":[116],"ADT":[118],"outperforms":[120],"baseline":[122],"synchronous":[123],"mimicking":[126],"forced":[132,168],"alignment":[133,169],"task,":[134],"its":[136],"behavior":[137],"as":[138],"parameters":[139],"are":[140],"changed":[141],"conforms":[142],"to":[143],"our":[144],"ex-pectations":[145],"about":[146],"coarticulation.":[148],"same":[150],"could":[152],"be":[153],"used":[154],"recognition,":[157,177],"although":[158],"here":[159],"consider":[161],"it":[162],"task":[166],"analysis.":[172],"Index":[173],"Terms:":[174],"asynchrony,":[179],"coarticulation,":[181],"dynamic":[182],"Bayesian":[183],"net-works":[184],"1.":[185]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
