{"id":"https://openalex.org/W2099036271","doi":"https://doi.org/10.1109/icassp.2006.1660192","title":"Improving Rapid Unsupervised Speaker Adaptation Based On Hmm Sufficient Statistics","display_name":"Improving Rapid Unsupervised Speaker Adaptation Based On Hmm Sufficient Statistics","publication_year":2006,"publication_date":"2006-08-02","ids":{"openalex":"https://openalex.org/W2099036271","doi":"https://doi.org/10.1109/icassp.2006.1660192","mag":"2099036271"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2006.1660192","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2006.1660192","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2006 IEEE International Conference on Acoustics Speed and Signal Processing Proceedings","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://naist.repo.nii.ac.jp/records/4626","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052470310","display_name":"Randy G\u00f3mez","orcid":"https://orcid.org/0000-0002-3191-6818"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"R. Gomez","raw_affiliation_strings":["Graduate School of Information Science, Nara Institute of Science and Technology, Japan","Graduate School of Information Science, Nara Institute of Science and Technology, JAPAN. E-mail: randy-g@is.naist.jp"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology, JAPAN. E-mail: randy-g@is.naist.jp","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"T. Toda","raw_affiliation_strings":["Graduate School of Information Science, Nara Institute of Science and Technology, Japan","Graduate Sch. of Information Sci., Nara Inst. of Sci. & Tech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"Graduate Sch. of Information Sci., Nara Inst. of Sci. & Tech","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003814223","display_name":"Hiroshi Saruwatari","orcid":"https://orcid.org/0000-0003-0876-5617"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"H. Saruwatari","raw_affiliation_strings":["Graduate School of Information Science, Nara Institute of Science and Technology, Japan","Graduate Sch. of Information Sci., Nara Inst. of Sci. & Tech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"Graduate Sch. of Information Sci., Nara Inst. of Sci. & Tech","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021868389","display_name":"Kiyohiro Shikano","orcid":null},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"K. Shikano","raw_affiliation_strings":["Graduate School of Information Science, Nara Institute of Science and Technology, Japan","Graduate Sch. of Information Sci., Nara Inst. of Sci. & Tech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"Graduate Sch. of Information Sci., Nara Inst. of Sci. & Tech","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I75917431"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"1001"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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":0.9969000220298767,"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":0.7568343877792358},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7331276535987854},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7163379788398743},{"id":"https://openalex.org/keywords/maximum-a-posteriori-estimation","display_name":"Maximum a posteriori estimation","score":0.6696209907531738},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6176205277442932},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.6124099493026733},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5322617888450623},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.5079324841499329},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48513659834861755},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4562384784221649},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.2642200291156769},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.2641792893409729},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14618650078773499}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7568343877792358},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7331276535987854},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7163379788398743},{"id":"https://openalex.org/C9810830","wikidata":"https://www.wikidata.org/wiki/Q635384","display_name":"Maximum a posteriori estimation","level":3,"score":0.6696209907531738},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6176205277442932},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6124099493026733},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5322617888450623},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.5079324841499329},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48513659834861755},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4562384784221649},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2642200291156769},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.2641792893409729},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14618650078773499},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2006.1660192","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2006.1660192","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2006 IEEE International Conference on Acoustics Speed and Signal Processing Proceedings","raw_type":"proceedings-article"},{"id":"pmh:oai:irdb.nii.ac.jp:01146:0005783077","is_oa":true,"landing_page_url":"https://naist.repo.nii.ac.jp/records/4626","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"conference paper"},{"id":"pmh:oai:library.naist.jp:10061/8058","is_oa":true,"landing_page_url":"http://hdl.handle.net/10061/8058","pdf_url":null,"source":{"id":"https://openalex.org/S4377196843","display_name":"NAIST Digital Library (Nara Institute of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I75917431","host_organization_name":"Nara Institute of Science and Technology","host_organization_lineage":["https://openalex.org/I75917431"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":{"id":"pmh:oai:irdb.nii.ac.jp:01146:0005783077","is_oa":true,"landing_page_url":"https://naist.repo.nii.ac.jp/records/4626","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"conference paper"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W88081813","https://openalex.org/W97132582","https://openalex.org/W124356247","https://openalex.org/W1494375335","https://openalex.org/W1571223402","https://openalex.org/W1594640407","https://openalex.org/W1602232401","https://openalex.org/W2034630336","https://openalex.org/W2044408773","https://openalex.org/W2113159725","https://openalex.org/W2141132023","https://openalex.org/W2146871184","https://openalex.org/W2164579587","https://openalex.org/W6603870740","https://openalex.org/W6605133283"],"related_works":["https://openalex.org/W2079194684","https://openalex.org/W2617269004","https://openalex.org/W35292311","https://openalex.org/W1748856376","https://openalex.org/W1911592522","https://openalex.org/W2087669554","https://openalex.org/W3044757496","https://openalex.org/W1595191759","https://openalex.org/W2010299594","https://openalex.org/W2129915831"],"abstract_inverted_index":{"In":[0],"real-time":[1],"speech":[2],"recognition":[3,74,109],"applications,":[4],"there":[5],"is":[6],"a":[7,11,19,37,58,66,100,141],"need":[8],"to":[9,21,52,57,77,82,120],"implement":[10],"fast":[12],"and":[13,98,144,157,168],"reliable":[14],"adaptation":[15,23,29,56,69,104,115],"algorithm.":[16],"We":[17,34,111],"propose":[18],"method":[20,133],"reduce":[22],"time":[24,105,116],"of":[25,63,79,89,125],"the":[26,45,85,90,108,114,126],"unsupervised":[27],"speaker":[28],"based":[30],"on":[31],"HMM-sufficient":[32,92],"statistics.":[33],"use":[35],"only":[36],"single":[38],"arbitrary":[39],"utterance":[40],"without":[41,106,123],"transcriptions":[42],"in":[43,68,103,153,161],"selecting":[44],"N-best":[46,64],"speakers'":[47],"sufficient":[48],"statistics":[49,93],"created":[50],"offline":[51],"provide":[53],"data":[54,80],"for":[55],"target":[59],"speaker.":[60],"Further":[61],"reduction":[62,67,102],"implies":[65],"time.":[70],"However,":[71],"it":[72],"degrades":[73],"performance":[75],"due":[76],"insufficiency":[78],"needed":[81],"robustly":[83],"adapt":[84],"model.":[86],"Linear":[87],"interpolation":[88],"global":[91],"offsets":[94],"this":[95],"negative":[96],"effect":[97],"achieves":[99],"50%":[101],"compromising":[107],"performance.":[110],"have":[112],"reduced":[113],"from":[117],"10":[118,162],"sec":[119,122],"5":[121],"degradation":[124],"word":[127],"accuracy.":[128],"Furthermore,":[129],"we":[130,151],"compared":[131],"our":[132],"with":[134],"vocal":[135],"tract":[136],"length":[137],"normalization":[138],"(VTLN),":[139],"maximum":[140,145],"posteriori":[142],"(MAP)":[143],"likelihood":[146],"linear":[147],"regression":[148],"(MLLR).":[149],"Moreover,":[150],"tested":[152],"office,":[154],"car,":[155],"crowd":[156],"booth":[158],"noise":[159],"environments":[160],"dB,":[163,165],"15":[164],"20":[166],"dB":[167,170],"25":[169],"SNRs":[171]},"counts_by_year":[{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}