{"id":"https://openalex.org/W117449184","doi":"https://doi.org/10.21437/interspeech.2010-576","title":"Robust word recognition using articulatory trajectories and gestures","display_name":"Robust word recognition using articulatory trajectories and gestures","publication_year":2010,"publication_date":"2010-09-26","ids":{"openalex":"https://openalex.org/W117449184","doi":"https://doi.org/10.21437/interspeech.2010-576","mag":"117449184"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2010-576","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-576","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/A5091201226","display_name":"Vikramjit Mitra","orcid":"https://orcid.org/0000-0002-2721-3976"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Vikramjit Mitra","raw_affiliation_strings":["University of Maryland, College Park"],"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058543204","display_name":"Hosung Nam","orcid":"https://orcid.org/0000-0002-1523-346X"},"institutions":[{"id":"https://openalex.org/I1319306116","display_name":"Haskins Laboratories","ror":"https://ror.org/003j5cv40","country_code":"US","type":"facility","lineage":["https://openalex.org/I1319306116"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hosung Nam","raw_affiliation_strings":["Haskins Laboratories"],"affiliations":[{"raw_affiliation_string":"Haskins Laboratories","institution_ids":["https://openalex.org/I1319306116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078241735","display_name":"Carol Espy-Wilson","orcid":"https://orcid.org/0000-0002-1012-183X"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carol Espy-Wilson","raw_affiliation_strings":["University of Maryland, College Park"],"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009226999","display_name":"Elliot Saltzman","orcid":null},"institutions":[{"id":"https://openalex.org/I1319306116","display_name":"Haskins Laboratories","ror":"https://ror.org/003j5cv40","country_code":"US","type":"facility","lineage":["https://openalex.org/I1319306116"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elliot Saltzman","raw_affiliation_strings":["Haskins Laboratories","Boston University"],"affiliations":[{"raw_affiliation_string":"Haskins Laboratories","institution_ids":["https://openalex.org/I1319306116"]},{"raw_affiliation_string":"Boston University","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110122617","display_name":"Louis Goldstein","orcid":null},"institutions":[{"id":"https://openalex.org/I2800817003","display_name":"Southern California University for Professional Studies","ror":"https://ror.org/058zz0t50","country_code":"US","type":"education","lineage":["https://openalex.org/I2800817003"]},{"id":"https://openalex.org/I1319306116","display_name":"Haskins Laboratories","ror":"https://ror.org/003j5cv40","country_code":"US","type":"facility","lineage":["https://openalex.org/I1319306116"]},{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Louis Goldstein","raw_affiliation_strings":["University of Southern California","Haskins Laboratories"],"affiliations":[{"raw_affiliation_string":"University of Southern California","institution_ids":["https://openalex.org/I2800817003","https://openalex.org/I1174212"]},{"raw_affiliation_string":"Haskins Laboratories","institution_ids":["https://openalex.org/I1319306116"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5091201226"],"corresponding_institution_ids":["https://openalex.org/I66946132"],"apc_list":null,"apc_paid":null,"fwci":3.1573,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.91563239,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2038","last_page":"2041"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9997000098228455,"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/T10860","display_name":"Speech and Audio Processing","score":0.998199999332428,"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/gesture","display_name":"Gesture","score":0.8632845878601074},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8122466802597046},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7719444036483765},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.7625304460525513},{"id":"https://openalex.org/keywords/speech-production","display_name":"Speech production","score":0.5527184009552002},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5447152853012085},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5306481122970581},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3993222415447235}],"concepts":[{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.8632845878601074},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8122466802597046},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7719444036483765},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.7625304460525513},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.5527184009552002},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5447152853012085},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5306481122970581},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3993222415447235},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2010-576","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-576","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"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6299999952316284,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W60202269","https://openalex.org/W126529980","https://openalex.org/W635648883","https://openalex.org/W1490506669","https://openalex.org/W1969229349","https://openalex.org/W1984095937","https://openalex.org/W2027297142","https://openalex.org/W2039763773","https://openalex.org/W2043199434","https://openalex.org/W2048449762","https://openalex.org/W2068447135","https://openalex.org/W2131127238","https://openalex.org/W2131770202","https://openalex.org/W2137075158","https://openalex.org/W2151484683","https://openalex.org/W2154074091"],"related_works":["https://openalex.org/W2082000062","https://openalex.org/W4234201046","https://openalex.org/W2058733683","https://openalex.org/W166167026","https://openalex.org/W2150243332","https://openalex.org/W2804836678","https://openalex.org/W953964455","https://openalex.org/W2010642486","https://openalex.org/W1445695360","https://openalex.org/W2120882262"],"abstract_inverted_index":{"Articulatory":[0],"Phonology":[1],"views":[2],"speech":[3,61,69,81,91,136],"as":[4],"an":[5],"ensemble":[6],"of":[7,41,59,66,90,161],"constricting":[8],"events":[9],"(e.g.":[10],"narrowing":[11],"lips,":[12],"raising":[13],"tongue":[14,21,23],"tip),":[15],"gestures,":[16],"at":[17],"distinct":[18],"organs":[19],"(lips,":[20],"tip,":[22],"body,":[24],"velum,":[25],"and":[26,43,101,105,118,145],"glottis)":[27],"along":[28,168],"the":[29,39,57,116,120,126,134,151,158,170],"vocal":[30],"tract.":[31],"This":[32],"study":[33],"shows":[34],"that":[35,93,150],"articulatory":[36,73,129,153],"information":[37,74,154],"in":[38,138],"form":[40],"gestures":[42,104,117,144],"their":[44,143],"output":[45],"trajectories":[46],"(tract":[47],"variable":[48],"time":[49],"functions":[50],"or":[51],"TVs)":[52],"can":[53],"help":[54],"to":[55,77,114,133,141,156],"improve":[56,157],"performance":[58],"automatic":[60],"recognition":[62,164],"systems.":[63],"The":[64],"lack":[65],"any":[67],"natural":[68,135],"database":[70],"containing":[71],"such":[72],"prompted":[75],"us":[76],"use":[78],"a":[79,98,162],"synthetic":[80],"dataset":[82],"(obtained":[83],"from":[84,122],"Haskins":[85],"Laboratories":[86],"TAsk":[87],"Dynamic":[88],"model":[89],"production)":[92],"contains":[94],"acoustic":[95,123],"waveform":[96],"for":[97],"given":[99],"utterance":[100],"its":[102],"corresponding":[103],"TVs.":[106,146],"First,":[107],"we":[108,148],"propose":[109],"neural":[110],"network":[111],"based":[112],"models":[113,130],"recognize":[115],"estimate":[119,142],"TVs":[121],"information.":[124],"Second,":[125],"\u201csynthetic-data":[127],"trained\u201d":[128],"were":[131],"applied":[132],"utterances":[137],"Aurora-2":[139],"corpus":[140],"Finally,":[147],"show":[149],"estimated":[152],"helps":[155],"noise":[159],"robustness":[160],"word":[163],"system":[165],"when":[166],"used":[167],"with":[169],"cepstral":[171]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
