{"id":"https://openalex.org/W1852631781","doi":"https://doi.org/10.21437/interspeech.2005-838","title":"Cluster-based modeling for ubiquitous speech recognition","display_name":"Cluster-based modeling for ubiquitous speech recognition","publication_year":2005,"publication_date":"2005-09-04","ids":{"openalex":"https://openalex.org/W1852631781","doi":"https://doi.org/10.21437/interspeech.2005-838","mag":"1852631781"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2005-838","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2005-838","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2005","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://t2r2.star.titech.ac.jp/rrws/file/CTT100391969/ATD100000413/","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009532108","display_name":"Sadaoki Furui","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Sadaoki Furui","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077005885","display_name":"Tomohisa Ichiba","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tomohisa Ichiba","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103015161","display_name":"Takahiro Shinozaki","orcid":"https://orcid.org/0000-0001-8114-8450"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takahiro Shinozaki","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108632126","display_name":"Edward W. D. Whittaker","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Edward W. D. Whittaker","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5084374665","display_name":"Koji Iwano","orcid":"https://orcid.org/0000-0002-7373-5353"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Koji Iwano","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5009532108"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.08696413,"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":"2865","last_page":"2868"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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/T10860","display_name":"Speech and Audio Processing","score":0.9883999824523926,"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":0.9836000204086304,"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/computer-science","display_name":"Computer science","score":0.830926775932312},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7185074090957642},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5924490094184875},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.562324583530426},{"id":"https://openalex.org/keywords/presentation","display_name":"Presentation (obstetrics)","score":0.4929018020629883},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.45240670442581177},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4306037425994873},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.4254096448421478},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.41744425892829895},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4078618884086609},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34242337942123413}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.830926775932312},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7185074090957642},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5924490094184875},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.562324583530426},{"id":"https://openalex.org/C2777601897","wikidata":"https://www.wikidata.org/wiki/Q3409113","display_name":"Presentation (obstetrics)","level":2,"score":0.4929018020629883},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.45240670442581177},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4306037425994873},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.4254096448421478},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.41744425892829895},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4078618884086609},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34242337942123413},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2005-838","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2005-838","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2005","raw_type":"proceedings-article"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:00202748","is_oa":true,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100391969","pdf_url":"http://t2r2.star.titech.ac.jp/rrws/file/CTT100391969/ATD100000413/","source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.408.6271","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.408.6271","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ewdw.com/PUBLICATIONS/Furui_Eurospeech2005.pdf","raw_type":"text"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:00205170","is_oa":false,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100394073","pdf_url":null,"source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":{"id":"pmh:oai:t2r2.star.titech.ac.jp:00202748","is_oa":true,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100391969","pdf_url":"http://t2r2.star.titech.ac.jp/rrws/file/CTT100391969/ATD100000413/","source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1852631781.pdf","grobid_xml":"https://content.openalex.org/works/W1852631781.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W47415966","https://openalex.org/W87954838","https://openalex.org/W113268911","https://openalex.org/W285205250","https://openalex.org/W1488377236","https://openalex.org/W2034838793","https://openalex.org/W2041695853","https://openalex.org/W2102582131","https://openalex.org/W2111305191","https://openalex.org/W2138309071","https://openalex.org/W2153513468","https://openalex.org/W2159518412","https://openalex.org/W2402326842","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2157598242","https://openalex.org/W3159882232","https://openalex.org/W4241650944","https://openalex.org/W2620660273","https://openalex.org/W4243125559","https://openalex.org/W1541790149","https://openalex.org/W2964829415","https://openalex.org/W2131711534","https://openalex.org/W642007152","https://openalex.org/W2341426843"],"abstract_inverted_index":{"In":[0],"order":[1],"to":[2,19,25,44,64,87,116,133],"realize":[3],"speech":[4,38,45,66],"recognition":[5,11,39,68,124,150],"systems":[6,22],"that":[7,41,111],"can":[8,42,113,129,144],"achieve":[9],"high":[10],"accuracy":[12],"for":[13,141],"ubiquitous":[14],"speech,":[15],"it":[16,106,112,120],"is":[17],"crucial":[18],"make":[20],"the":[21,74,97,137,142],"flexible":[23],"enough":[24],"cope":[26],"with":[27],"a":[28,48,61,101],"large":[29,49,102],"variability":[30],"of":[31,51,104,139,149],"spontaneous":[32],"speech.":[33,95],"This":[34],"paper":[35],"investigates":[36],"two":[37],"methods":[40,83],"adapt":[43],"variation":[46],"using":[47,67,93],"number":[50],"models":[52,79],"trained":[53],"based":[54],"on":[55],"clustering":[56],"techniques;":[57],"one":[58],"automatically":[59],"builds":[60],"model":[62],"adapted":[63],"input":[65],"hypotheses":[69],"and":[70,73],"clustered":[71,78],"models,":[72],"other":[75],"directly":[76],"uses":[77],"in":[80,110,147],"parallel.":[81],"Both":[82],"have":[84],"been":[85],"confirmed":[86],"be":[88,114,131,145],"effective":[89],"by":[90],"evaluation":[91],"experiments":[92],"presentation":[94,143],"Although":[96],"latter":[98],"method":[99,128],"needs":[100],"amount":[103],"computation,":[105],"has":[107],"an":[108],"advantage":[109],"applied":[115,132],"online":[117,134],"recognition,":[118,135],"since":[119],"does":[121],"not":[122],"need":[123],"hypotheses.":[125,151],"The":[126],"former":[127],"also":[130],"if":[136],"text":[138],"proceedings":[140],"used":[146],"place":[148],"1.":[152]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}