{"id":"https://openalex.org/W1989588065","doi":"https://doi.org/10.1109/icassp.2013.6639049","title":"Articulatory trajectories for large-vocabulary speech recognition","display_name":"Articulatory trajectories for large-vocabulary speech recognition","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W1989588065","doi":"https://doi.org/10.1109/icassp.2013.6639049","mag":"1989588065"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6639049","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639049","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","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/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]},{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Vikramjit Mitra","raw_affiliation_strings":["Speech Technology and Research Laboratory, SRI International, Menlo Park, CA, USA","Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA"],"affiliations":[{"raw_affiliation_string":"Speech Technology and Research Laboratory, SRI International, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152"]},{"raw_affiliation_string":"Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100396375","display_name":"Wen Wang","orcid":"https://orcid.org/0000-0002-0356-1968"},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wen Wang","raw_affiliation_strings":["Speech Technology and Research Laboratory, SRI International, Menlo Park, CA, USA","Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA"],"affiliations":[{"raw_affiliation_string":"Speech Technology and Research Laboratory, SRI International, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152"]},{"raw_affiliation_string":"Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060979948","display_name":"Andreas Stolcke","orcid":"https://orcid.org/0000-0002-9925-905X"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andreas Stolcke","raw_affiliation_strings":["Microsoft Research, Mountain View, CA, USA","Microsoft Research, Mountain View, CA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Research, Mountain View, CA, USA#TAB#","institution_ids":["https://openalex.org/I1290206253"]}]},{"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, New Haven, CT, USA","Haskins Laboratories New Haven CT USA"],"affiliations":[{"raw_affiliation_string":"Haskins Laboratories, New Haven, CT, USA","institution_ids":["https://openalex.org/I1319306116"]},{"raw_affiliation_string":"Haskins Laboratories New Haven CT USA","institution_ids":["https://openalex.org/I1319306116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066868305","display_name":"Colleen Richey","orcid":null},"institutions":[{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]},{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Colleen Richey","raw_affiliation_strings":["Speech Technology and Research Laboratory, SRI International, Menlo Park, CA, USA","Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA"],"affiliations":[{"raw_affiliation_string":"Speech Technology and Research Laboratory, SRI International, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152"]},{"raw_affiliation_string":"Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043406907","display_name":"Jiahong Yuan","orcid":"https://orcid.org/0009-0008-2162-7167"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiahong Yuan","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, PA, USA","University of Pennsylvania Philadelphia PA USA"],"affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I79576946"]},{"raw_affiliation_string":"University of Pennsylvania Philadelphia PA USA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055868875","display_name":"Mark Liberman","orcid":"https://orcid.org/0000-0002-8605-9024"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Liberman","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, PA, USA","University of Pennsylvania Philadelphia PA USA"],"affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I79576946"]},{"raw_affiliation_string":"University of Pennsylvania Philadelphia PA USA","institution_ids":["https://openalex.org/I79576946"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5091201226"],"corresponding_institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"],"apc_list":null,"apc_paid":null,"fwci":1.9769,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.88068036,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"85","issue":null,"first_page":"7145","last_page":"7149"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9998000264167786,"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":0.9987999796867371,"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":0.8222348690032959},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8121411800384521},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.7026352286338806},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.5432146787643433},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.491271436214447},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.4830775558948517},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.46074357628822327},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4553958475589752},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4545353055000305},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3803097903728485}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8222348690032959},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8121411800384521},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.7026352286338806},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.5432146787643433},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.491271436214447},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.4830775558948517},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.46074357628822327},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4553958475589752},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4545353055000305},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3803097903728485},{"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:10.1109/icassp.2013.6639049","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639049","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.300.1879","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.300.1879","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.speech.sri.com/papers/Mitra_MODTV_LVCSR_ICASSP2013_prepub.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5299999713897705,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W3285877","https://openalex.org/W959678087","https://openalex.org/W1490506669","https://openalex.org/W1549321558","https://openalex.org/W1631260214","https://openalex.org/W1904457459","https://openalex.org/W1995312914","https://openalex.org/W1995451491","https://openalex.org/W1998474788","https://openalex.org/W2002352051","https://openalex.org/W2005741747","https://openalex.org/W2027297142","https://openalex.org/W2048449762","https://openalex.org/W2052382192","https://openalex.org/W2053280194","https://openalex.org/W2068447135","https://openalex.org/W2091288983","https://openalex.org/W2097560587","https://openalex.org/W2097978681","https://openalex.org/W2101802380","https://openalex.org/W2131770202","https://openalex.org/W2134950286","https://openalex.org/W2140518672","https://openalex.org/W2140979961","https://openalex.org/W2154074091","https://openalex.org/W2159731626","https://openalex.org/W2991401689","https://openalex.org/W6600140005","https://openalex.org/W6636811518","https://openalex.org/W6674334065","https://openalex.org/W6675504311"],"related_works":["https://openalex.org/W2100203012","https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W2373675101","https://openalex.org/W4385672897","https://openalex.org/W106160982","https://openalex.org/W2359140082","https://openalex.org/W2074132948","https://openalex.org/W2160511961"],"abstract_inverted_index":{"Studies":[0],"have":[1,27,38,52,72],"demonstrated":[2],"that":[3,153],"articulatory":[4,25,50,83,117,155],"information":[5,26,51,156],"can":[6,12],"model":[7,80,90,102,108],"speech":[8,17,44,61,86,95,104,158],"variability":[9],"effectively":[10,30],"and":[11,35,63,114,182,195],"potentially":[13],"help":[14],"to":[15,56,65,81,111,131],"improve":[16],"recognition":[18,47,137,159],"performance.":[19],"Most":[20],"of":[21,103],"the":[22,89,115,121,147,183],"studies":[23,37,48],"involving":[24],"focused":[28],"on":[29,191],"estimating":[31],"them":[32,67],"from":[33,85,120],"speech,":[34,113],"few":[36],"actually":[39],"used":[40,124,145],"such":[41],"features":[42,130,175],"for":[43,135],"recognition.":[45],"Speech":[46],"using":[49,93],"been":[53,73],"mostly":[54],"confined":[55],"digit":[57],"or":[58],"medium":[59],"vocabulary":[60,70],"recognition,":[62],"efforts":[64],"incorporate":[66],"into":[68],"large":[69],"systems":[71,189],"limited.":[74],"We":[75],"present":[76],"a":[77],"neural":[78],"network":[79],"estimate":[82],"trajectories":[84,118],"signals":[87,96],"where":[88],"was":[91,109,186],"trained":[92,107],"synthetic":[94],"generated":[97],"by":[98],"Haskins":[99],"Laboratories'":[100],"task-dynamic":[101],"production.":[105],"The":[106],"applied":[110],"natural":[112],"estimated":[116],"obtained":[119,187],"models":[122,134],"were":[123,144,176,199],"in":[125,146,179],"conjunction":[126],"with":[127],"standard":[128,193],"cepstral":[129,194],"train":[132],"acoustic":[133],"large-vocabulary":[136,141],"systems.":[138],"Two":[139],"different":[140],"English":[142],"datasets":[143],"experiments":[148],"reported":[149],"here.":[150],"Results":[151],"indicate":[152],"employing":[154],"improves":[157],"performance":[160,185],"not":[161],"only":[162],"under":[163,168],"clean":[164],"conditions":[165],"but":[166],"also":[167,177],"noisy":[169],"background":[170],"conditions.":[171],"Perceptually":[172],"motivated":[173,197],"robust":[174],"explored":[178],"this":[180],"study":[181],"best":[184],"when":[188],"based":[190],"articulatory,":[192],"perceptually":[196],"feature":[198],"all":[200],"combined.":[201]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}