{"id":"https://openalex.org/W2042349506","doi":"https://doi.org/10.1109/asru.2011.6163904","title":"Speaker adaptation based on speaker-dependent eigenphone estimation","display_name":"Speaker adaptation based on speaker-dependent eigenphone estimation","publication_year":2011,"publication_date":"2011-12-01","ids":{"openalex":"https://openalex.org/W2042349506","doi":"https://doi.org/10.1109/asru.2011.6163904","mag":"2042349506"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2011.6163904","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2011.6163904","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE Workshop on Automatic Speech Recognition & Understanding","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/A5100635256","display_name":"Wenlin Zhang","orcid":"https://orcid.org/0000-0002-6842-9722"},"institutions":[{"id":"https://openalex.org/I4210119388","display_name":"Zhejiang Science and Technology Information Institute","ror":"https://ror.org/02rzte064","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210119388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen-Lin Zhang","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China","Department of Information Science, Zhengzhou Information Science and Technology Institute, Zhengzhou, China","Department of Information Science, Zhengzhou Information Science and Technology Institute, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Information Science, Zhengzhou Information Science and Technology Institute, Zhengzhou, China","institution_ids":["https://openalex.org/I4210119388"]},{"raw_affiliation_string":"Department of Information Science, Zhengzhou Information Science and Technology Institute, China","institution_ids":["https://openalex.org/I4210119388"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100692904","display_name":"Wei-Qiang Zhang","orcid":"https://orcid.org/0000-0003-3841-1959"},"institutions":[{"id":"https://openalex.org/I4210119388","display_name":"Zhejiang Science and Technology Information Institute","ror":"https://ror.org/02rzte064","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210119388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei-Qiang Zhang","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China","Department of Information Science, Zhengzhou Information Science and Technology Institute, Zhengzhou, China","Department of Electronic Engineering, Tsinghua University, Beijing, CHINA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Information Science, Zhengzhou Information Science and Technology Institute, Zhengzhou, China","institution_ids":["https://openalex.org/I4210119388"]},{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, CHINA#TAB#","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039649740","display_name":"Bicheng Li","orcid":"https://orcid.org/0000-0003-2218-3146"},"institutions":[{"id":"https://openalex.org/I4210119388","display_name":"Zhejiang Science and Technology Information Institute","ror":"https://ror.org/02rzte064","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210119388"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bi-Cheng Li","raw_affiliation_strings":["Department of Information Science, Zhengzhou Information Science and Technology Institute, Zhengzhou, China","Department of Information Science, Zhengzhou Information Science and Technology Institute, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Science, Zhengzhou Information Science and Technology Institute, Zhengzhou, China","institution_ids":["https://openalex.org/I4210119388"]},{"raw_affiliation_string":"Department of Information Science, Zhengzhou Information Science and Technology Institute, China","institution_ids":["https://openalex.org/I4210119388"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2698,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.48894224,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"48","last_page":"52"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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":0.9990000128746033,"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":0.998199999332428,"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":0.9779999852180481,"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":0.7803407907485962},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.755574107170105},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6379039883613586},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.6366218328475952},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.5402756333351135},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5070431232452393},{"id":"https://openalex.org/keywords/maximum-a-posteriori-estimation","display_name":"Maximum a posteriori estimation","score":0.49943089485168457},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.49725034832954407},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.44358205795288086},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4410480260848999},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40479809045791626},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38476699590682983},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14565056562423706},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.14380070567131042}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7803407907485962},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.755574107170105},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6379039883613586},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.6366218328475952},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.5402756333351135},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5070431232452393},{"id":"https://openalex.org/C9810830","wikidata":"https://www.wikidata.org/wiki/Q635384","display_name":"Maximum a posteriori estimation","level":3,"score":0.49943089485168457},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.49725034832954407},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.44358205795288086},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4410480260848999},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40479809045791626},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38476699590682983},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14565056562423706},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.14380070567131042},{"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},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2011.6163904","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2011.6163904","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE Workshop on Automatic Speech Recognition & Understanding","raw_type":"proceedings-article"}],"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/W88081813","https://openalex.org/W142477701","https://openalex.org/W2104687512","https://openalex.org/W2133278758","https://openalex.org/W2139801919","https://openalex.org/W2165108269","https://openalex.org/W2166731551","https://openalex.org/W6605686022"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1503532423","https://openalex.org/W2149220986","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1967494390","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W245717845"],"abstract_inverted_index":{"Based":[0],"on":[1,90],"speaker":[2,8,19,32,56,65,87],"dependent":[3],"eigenphone":[4],"estimation,":[5],"a":[6,81,91],"novel":[7],"adaptation":[9,20,88,115],"technique":[10],"is":[11,44,117],"proposed":[12,23],"in":[13,36],"this":[14],"paper.":[15],"Different":[16],"from":[17],"conventional":[18],"approaches,":[21],"the":[22,27,37,63,100],"method":[24,102],"explicitly":[25],"models":[26],"phone":[28,38,41,67],"variations":[29],"for":[30,60],"each":[31],"through":[33],"subspace":[34],"modeling":[35],"space.":[39],"The":[40],"coordinate,":[42],"which":[43],"shared":[45],"by":[46],"all":[47],"speakers,":[48],"contains":[49],"correlation":[50],"information":[51],"between":[52],"different":[53],"phones.":[54],"During":[55],"adaptation,":[57],"two":[58],"schemes":[59],"estimation":[61],"of":[62],"new":[64,101],"specific":[66],"variation":[68],"bases":[69],"(namely":[70],"eigenphones)":[71],"are":[72],"derived":[73],"under":[74],"maximum":[75,80,107],"likelihood":[76,108],"(ML)":[77],"criterion":[78,84],"and":[79,106],"posteriori":[82],"(MAP)":[83],"respectively.":[85],"Supervised":[86],"experiments":[89],"Mandarin":[92],"Chinese":[93],"continuous":[94],"speech":[95],"recognition":[96],"task":[97],"show":[98],"that":[99],"outperforms":[103],"both":[104],"eigenvoice":[105],"linear":[109],"regression":[110],"(MLLR)":[111],"methods":[112],"when":[113],"sufficient":[114],"data":[116],"available.":[118]},"counts_by_year":[{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}