{"id":"https://openalex.org/W2119167612","doi":"https://doi.org/10.1109/icassp.2011.5946965","title":"Automatic recognition of speech without any audio information","display_name":"Automatic recognition of speech without any audio information","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2119167612","doi":"https://doi.org/10.1109/icassp.2011.5946965","mag":"2119167612"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5946965","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5946965","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5029779616","display_name":"Panikos Heracleous","orcid":"https://orcid.org/0000-0002-7709-8195"},"institutions":[{"id":"https://openalex.org/I4210104143","display_name":"Advanced Telecommunications Research Institute International","ror":"https://ror.org/01pe1d703","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210104143"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Panikos Heracleous","raw_affiliation_strings":["ATR Intelligent Robotics and Communication Laboratories, Soraku-gun, Kyoto, Japan","ATR, Intelligent Robotics and Communication Laboratories, 2-2-2 Hikaridai Seika-cho, Soraku-gun, Kyoto-fu 619-0288, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ATR Intelligent Robotics and Communication Laboratories, Soraku-gun, Kyoto, Japan","institution_ids":["https://openalex.org/I4210104143"]},{"raw_affiliation_string":"ATR, Intelligent Robotics and Communication Laboratories, 2-2-2 Hikaridai Seika-cho, Soraku-gun, Kyoto-fu 619-0288, Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058513264","display_name":"Norihiro Hagita","orcid":"https://orcid.org/0000-0001-8007-4701"},"institutions":[{"id":"https://openalex.org/I4210104143","display_name":"Advanced Telecommunications Research Institute International","ror":"https://ror.org/01pe1d703","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210104143"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Norihiro Hagita","raw_affiliation_strings":["ATR Intelligent Robotics and Communication Laboratories, Soraku-gun, Kyoto, Japan","ATR, Intelligent Robotics and Communication Laboratories, 2-2-2 Hikaridai Seika-cho, Soraku-gun, Kyoto-fu 619-0288, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ATR Intelligent Robotics and Communication Laboratories, Soraku-gun, Kyoto, Japan","institution_ids":["https://openalex.org/I4210104143"]},{"raw_affiliation_string":"ATR, Intelligent Robotics and Communication Laboratories, 2-2-2 Hikaridai Seika-cho, Soraku-gun, Kyoto-fu 619-0288, Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210104143"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2392","last_page":"2395"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9969000220298767,"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/T13289","display_name":"Infant Health and Development","score":0.9926999807357788,"subfield":{"id":"https://openalex.org/subfields/3611","display_name":"Pharmacy"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8369364738464355},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7938151955604553},{"id":"https://openalex.org/keywords/voice","display_name":"Voice","score":0.7620887756347656},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7415475249290466},{"id":"https://openalex.org/keywords/articulation","display_name":"Articulation (sociology)","score":0.6698918342590332},{"id":"https://openalex.org/keywords/manner-of-articulation","display_name":"Manner of articulation","score":0.5896556377410889},{"id":"https://openalex.org/keywords/tongue","display_name":"Tongue","score":0.45009949803352356},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44898372888565063},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4365467429161072},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33321183919906616},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07737752795219421}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8369364738464355},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7938151955604553},{"id":"https://openalex.org/C552089266","wikidata":"https://www.wikidata.org/wiki/Q494510","display_name":"Voice","level":2,"score":0.7620887756347656},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7415475249290466},{"id":"https://openalex.org/C2779337067","wikidata":"https://www.wikidata.org/wiki/Q4800961","display_name":"Articulation (sociology)","level":3,"score":0.6698918342590332},{"id":"https://openalex.org/C66029223","wikidata":"https://www.wikidata.org/wiki/Q210847","display_name":"Manner of articulation","level":2,"score":0.5896556377410889},{"id":"https://openalex.org/C2779744641","wikidata":"https://www.wikidata.org/wiki/Q9614","display_name":"Tongue","level":2,"score":0.45009949803352356},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44898372888565063},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4365467429161072},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33321183919906616},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07737752795219421},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2011.5946965","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5946965","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.652.3329","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.652.3329","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+2011/pdfs/0002392.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1589867908","https://openalex.org/W1999209169","https://openalex.org/W2028971373","https://openalex.org/W2055115647","https://openalex.org/W2096391593","https://openalex.org/W2109455879","https://openalex.org/W2409998918","https://openalex.org/W3014296750","https://openalex.org/W6635242571","https://openalex.org/W6775121089"],"related_works":["https://openalex.org/W2022221551","https://openalex.org/W1994373804","https://openalex.org/W1037709911","https://openalex.org/W2086165807","https://openalex.org/W1552694876","https://openalex.org/W2777500320","https://openalex.org/W2981059406","https://openalex.org/W2063579271","https://openalex.org/W2891508361","https://openalex.org/W4225259993"],"abstract_inverted_index":{"This":[0],"article":[1],"introduces":[2],"automatic":[3,39],"recognition":[4,41],"of":[5,12],"speech":[6,40],"without":[7],"any":[8],"audio":[9],"information.":[10],"Movements":[11],"the":[13,83],"tongue,":[14],"lips,":[15],"and":[16,26,37],"jaw":[17],"are":[18,27,49,58],"tracked":[19],"by":[20],"an":[21],"Electro-Magnetic":[22],"Articulography":[23],"(EMA)":[24],"device":[25],"used":[28],"as":[29,59,61],"features":[30,55],"to":[31],"create":[32],"hidden":[33],"Markov":[34],"models":[35],"(HMMs)":[36],"conduct":[38],"in":[42,77],"a":[43,78],"conventional":[44],"way.":[45],"The":[46,68],"results":[47,69],"obtained":[48],"promising,":[50],"which":[51],"confirm":[52],"that":[53,72],"phonetic":[54],"characterizing":[56,63],"articulation":[57],"discriminating":[60],"those":[62],"acoustics":[64],"(except":[65],"for":[66],"voicing).":[67],"also":[70],"show":[71],"using":[73],"tongue":[74],"parameters":[75],"result":[76],"higher":[79],"accuracy":[80],"compared":[81],"with":[82],"lip":[84],"parameters.":[85]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}