{"id":"https://openalex.org/W179800749","doi":"https://doi.org/10.21437/interspeech.2005-162","title":"Rapid speaker adaptation for continuous speech recognition using merging eigenvoices","display_name":"Rapid speaker adaptation for continuous speech recognition using merging eigenvoices","publication_year":2005,"publication_date":"2005-09-04","ids":{"openalex":"https://openalex.org/W179800749","doi":"https://doi.org/10.21437/interspeech.2005-162","mag":"179800749"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2005-162","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2005-162","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101439511","display_name":"Dong-Jin Choi","orcid":"https://orcid.org/0000-0003-0153-5595"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Dong-jin Choi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101108235","display_name":"Yung\u2010Hwan Oh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yung-Hwan Oh","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101439511"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02246573,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"297","last_page":"300"},"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":0.9994000196456909,"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":0.9954000115394592,"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":0.8310210704803467},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7798421382904053},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.7433290481567383},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5931329727172852},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5494734644889832},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.46736380457878113},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4425230920314789},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3822650909423828},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3365901708602905},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.046476930379867554}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8310210704803467},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7798421382904053},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.7433290481567383},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5931329727172852},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5494734644889832},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.46736380457878113},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4425230920314789},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3822650909423828},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3365901708602905},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.046476930379867554},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2005-162","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2005-162","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:CiteSeerX.psu:10.1.1.595.7219","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.595.7219","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://vilab.kaist.ac.kr/result/upfile/outsoc/4d0a6958_2005_Rapid Speaker Adaptation for Continuous Speech Recognition Using Merging Eigenvoices.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1578604476","https://openalex.org/W1953949349","https://openalex.org/W2104687512","https://openalex.org/W2131858147","https://openalex.org/W2143970252","https://openalex.org/W2146871184","https://openalex.org/W2165108269","https://openalex.org/W2798909945"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2938358845","https://openalex.org/W2997340161"],"abstract_inverted_index":{"Speaker":[0],"adaptation":[1],"in":[2,56,111],"eigenvoice":[3],"space":[4],"is":[5,93,101],"a":[6,34,57,65],"popular":[7],"method":[8,19,66],"for":[9,75],"rapid":[10],"speaker":[11],"adaptation.":[12],"To":[13],"improve":[14],"the":[15,18,25,43,83,90,99,103,106,118],"performance":[16,100],"of":[17,27,37,108],"and":[20,33,79],"to":[21,48,67,114],"obtain":[22],"stabilized":[23],"results,":[24],"number":[26,36],"speaker-dependent":[28,77,109],"models":[29,78,110],"should":[30,39],"be":[31,40,115],"increased":[32],"greater":[35],"eigenvoices":[38,50,73],"re-estimated.":[41],"However,":[42],"huge":[44],"computation":[45,69,91],"time":[46,70,92],"required":[47],"find":[49],"makes":[51],"these":[52],"solutions":[53],"difficult,":[54],"especially":[55],"continuous":[58],"speech":[59],"recognition":[60],"system.":[61],"This":[62],"paper":[63],"describes":[64],"reduce":[68],"by":[71,95],"estimating":[72],"only":[74],"supplementary":[76],"merging":[80],"them":[81],"with":[82],"used":[84],"eigenvoices.":[85],"Experimental":[86],"results":[87],"show":[88],"that":[89],"reduced":[94],"73.7":[96],"%":[97],"while":[98],"almost":[102],"same":[104],"when":[105],"numbers":[107],"two":[112],"sets":[113],"merged":[116],"are":[117],"same.":[119],"1.":[120]},"counts_by_year":[],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}