{"id":"https://openalex.org/W2040454151","doi":"https://doi.org/10.1109/icassp.2014.6854158","title":"The effect of speaking rate on audio and visual speech","display_name":"The effect of speaking rate on audio and visual speech","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2040454151","doi":"https://doi.org/10.1109/icassp.2014.6854158","mag":"2040454151"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6854158","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854158","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5101923852","display_name":"Sarah Taylor","orcid":"https://orcid.org/0000-0003-1299-0446"},"institutions":[{"id":"https://openalex.org/I4210142140","display_name":"Walt Disney (United States)","ror":"https://ror.org/04eg47h42","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142140"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sarah Taylor","raw_affiliation_strings":["Disney Research, Pittsburgh, PA","Disney Res., Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Disney Research, Pittsburgh, PA","institution_ids":["https://openalex.org/I4210142140"]},{"raw_affiliation_string":"Disney Res., Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I4210142140"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112911728","display_name":"Barry-John Theobald","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":"Barry-John Theobald","raw_affiliation_strings":["University of East Anglia, Norwich, UK","Univ. of East Anglia, Norwich, UK#TAB#"],"affiliations":[{"raw_affiliation_string":"University of East Anglia, Norwich, UK","institution_ids":["https://openalex.org/I1118541"]},{"raw_affiliation_string":"Univ. of East Anglia, Norwich, UK#TAB#","institution_ids":["https://openalex.org/I1118541"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069055807","display_name":"Iain Matthews","orcid":"https://orcid.org/0009-0000-5004-2397"},"institutions":[{"id":"https://openalex.org/I4210142140","display_name":"Walt Disney (United States)","ror":"https://ror.org/04eg47h42","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142140"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Iain Matthews","raw_affiliation_strings":["Disney Research, Pittsburgh, PA","Disney Res., Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Disney Research, Pittsburgh, PA","institution_ids":["https://openalex.org/I4210142140"]},{"raw_affiliation_string":"Disney Res., Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I4210142140"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101923852"],"corresponding_institution_ids":["https://openalex.org/I4210142140"],"apc_list":null,"apc_paid":null,"fwci":2.3553,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.89046017,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3037","last_page":"3041"},"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/T12032","display_name":"Multisensory perception and integration","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9959999918937683,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7749233841896057},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7172836661338806},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6615063548088074},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.5985211730003357},{"id":"https://openalex.org/keywords/viseme","display_name":"Viseme","score":0.5859977602958679},{"id":"https://openalex.org/keywords/speech-production","display_name":"Speech production","score":0.5239080190658569},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4346349537372589},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4334614872932434},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4244108200073242},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.225913405418396},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.16779452562332153},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.08821135759353638}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7749233841896057},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7172836661338806},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6615063548088074},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.5985211730003357},{"id":"https://openalex.org/C33767174","wikidata":"https://www.wikidata.org/wiki/Q371190","display_name":"Viseme","level":4,"score":0.5859977602958679},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.5239080190658569},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4346349537372589},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4334614872932434},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4244108200073242},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.225913405418396},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.16779452562332153},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.08821135759353638},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2014.6854158","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854158","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:ueaeprints.uea.ac.uk:48553","is_oa":false,"landing_page_url":null,"pdf_url":null,"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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.886.4547","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.886.4547","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.disneyresearch.com/wp-content/uploads/The-Effect-of-Speaking-Rate-on-Audio-and-Visual-Speech-Paper.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.889.53","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.889.53","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://mirlab.org/conference_papers/International_Conference/ICASSP%202014/papers/p3061-taylor.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W113396932","https://openalex.org/W121610373","https://openalex.org/W947265762","https://openalex.org/W1647671624","https://openalex.org/W2000911139","https://openalex.org/W2006482757","https://openalex.org/W2013699441","https://openalex.org/W2045933515","https://openalex.org/W2071096833","https://openalex.org/W2071828724","https://openalex.org/W2080416463","https://openalex.org/W2083050334","https://openalex.org/W2087964571","https://openalex.org/W2088603884","https://openalex.org/W2096651761","https://openalex.org/W2152826865","https://openalex.org/W2337732708","https://openalex.org/W2394527494","https://openalex.org/W2400566389","https://openalex.org/W2619993508","https://openalex.org/W3127686677","https://openalex.org/W4390912168","https://openalex.org/W6605039604","https://openalex.org/W6636915900","https://openalex.org/W6650605322","https://openalex.org/W6703684149","https://openalex.org/W6711842774"],"related_works":["https://openalex.org/W1974357398","https://openalex.org/W2053099149","https://openalex.org/W1559261064","https://openalex.org/W2299511660","https://openalex.org/W2124254345","https://openalex.org/W2334129531","https://openalex.org/W2515097069","https://openalex.org/W2105537028","https://openalex.org/W2164147372","https://openalex.org/W2550171623"],"abstract_inverted_index":{"The":[0],"speed":[1],"that":[2,23,80],"an":[3,45],"utterance":[4],"is":[5,98],"spoken":[6,74],"affects":[7],"both":[8,81],"the":[9,12,15,18,21,30,35,50,71,91,96],"duration":[10],"of":[11,17,34,52,64,93],"speech":[13,60,85],"and":[14,32,39,58,66,83],"position":[16,31],"articulators.":[19,42],"Consequently,":[20],"sounds":[22],"are":[24,26,29,87],"produced":[25],"modified,":[27],"as":[28],"appearance":[33],"lips,":[36],"teeth,":[37],"tongue":[38],"other":[40],"visible":[41],"We":[43,78],"describe":[44],"experiment":[46],"designed":[47],"to":[48],"measure":[49],"effect":[51,97],"variable":[53],"speaking":[54],"rate":[55,92],"on":[56],"audio":[57,82],"visual":[59,84,103],"by":[61,89],"comparing":[62],"sequences":[63],"phonemes":[65],"dynamic":[67],"visemes":[68],"appearing":[69],"in":[70,102],"same":[72],"sentences":[73],"at":[75],"different":[76],"speeds.":[77],"find":[79],"production":[86],"affected":[88],"varying":[90],"speech,":[94],"however,":[95],"significantly":[99],"more":[100],"prominent":[101],"speech.":[104]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}