{"id":"https://openalex.org/W1972875704","doi":"https://doi.org/10.1109/apsipa.2013.6694112","title":"Speech recognition with large-scale speaker-class-based acoustic modeling","display_name":"Speech recognition with large-scale speaker-class-based acoustic modeling","publication_year":2013,"publication_date":"2013-10-01","ids":{"openalex":"https://openalex.org/W1972875704","doi":"https://doi.org/10.1109/apsipa.2013.6694112","mag":"1972875704"},"language":"en","primary_location":{"id":"doi:10.1109/apsipa.2013.6694112","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2013.6694112","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference","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/A5088094121","display_name":"K. Konno","orcid":null},"institutions":[{"id":"https://openalex.org/I112524849","display_name":"Yamagata University","ror":"https://ror.org/00xy44n04","country_code":"JP","type":"education","lineage":["https://openalex.org/I112524849"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Kazuki Konno","raw_affiliation_strings":["Graduate School of Science and Engineering, Yamagata University, Yonezawa, Japan","[Grad. Sch. of Sci. & Eng., Yamagata Univ., Yonezawa, Japan]"],"affiliations":[{"raw_affiliation_string":"Graduate School of Science and Engineering, Yamagata University, Yonezawa, Japan","institution_ids":["https://openalex.org/I112524849"]},{"raw_affiliation_string":"[Grad. Sch. of Sci. & Eng., Yamagata Univ., Yonezawa, Japan]","institution_ids":["https://openalex.org/I112524849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101139126","display_name":"Masaharu Kato","orcid":null},"institutions":[{"id":"https://openalex.org/I112524849","display_name":"Yamagata University","ror":"https://ror.org/00xy44n04","country_code":"JP","type":"education","lineage":["https://openalex.org/I112524849"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masaharu Kato","raw_affiliation_strings":["Graduate School of Science and Engineering, Yamagata University, Yonezawa, Japan","[Grad. Sch. of Sci. & Eng., Yamagata Univ., Yonezawa, Japan]"],"affiliations":[{"raw_affiliation_string":"Graduate School of Science and Engineering, Yamagata University, Yonezawa, Japan","institution_ids":["https://openalex.org/I112524849"]},{"raw_affiliation_string":"[Grad. Sch. of Sci. & Eng., Yamagata Univ., Yonezawa, Japan]","institution_ids":["https://openalex.org/I112524849"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112342909","display_name":"Tetsuo Kosaka","orcid":null},"institutions":[{"id":"https://openalex.org/I112524849","display_name":"Yamagata University","ror":"https://ror.org/00xy44n04","country_code":"JP","type":"education","lineage":["https://openalex.org/I112524849"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsuo Kosaka","raw_affiliation_strings":["Graduate School of Science and Engineering, Yamagata University, Yonezawa, Japan","[Grad. Sch. of Sci. & Eng., Yamagata Univ., Yonezawa, Japan]"],"affiliations":[{"raw_affiliation_string":"Graduate School of Science and Engineering, Yamagata University, Yonezawa, Japan","institution_ids":["https://openalex.org/I112524849"]},{"raw_affiliation_string":"[Grad. Sch. of Sci. & Eng., Yamagata Univ., Yonezawa, Japan]","institution_ids":["https://openalex.org/I112524849"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5088094121"],"corresponding_institution_ids":["https://openalex.org/I112524849"],"apc_list":null,"apc_paid":null,"fwci":0.9618,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.80946621,"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":"1","last_page":"4"},"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":0.9991000294685364,"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":0.9973000288009644,"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/speaker-recognition","display_name":"Speaker recognition","score":0.8011618852615356},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7734295129776001},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7646270990371704},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7439444661140442},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6769578456878662},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6346718072891235},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.611528754234314},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48601680994033813},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44791847467422485}],"concepts":[{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.8011618852615356},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7734295129776001},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7646270990371704},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7439444661140442},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6769578456878662},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6346718072891235},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.611528754234314},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48601680994033813},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44791847467422485}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipa.2013.6694112","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2013.6694112","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference","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":11,"referenced_works":["https://openalex.org/W68151333","https://openalex.org/W165923638","https://openalex.org/W2045877685","https://openalex.org/W2116708935","https://openalex.org/W2119902425","https://openalex.org/W2131118559","https://openalex.org/W2141132023","https://openalex.org/W2545766074","https://openalex.org/W2565973836","https://openalex.org/W6729209586","https://openalex.org/W6731009986"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4389984014","https://openalex.org/W2144208207","https://openalex.org/W1509309911","https://openalex.org/W1940231550","https://openalex.org/W1599425004","https://openalex.org/W2118860825","https://openalex.org/W2096510939","https://openalex.org/W2499802997","https://openalex.org/W2112059504"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"speaker-independent":[3],"speech":[4],"recognition":[5,88],"with":[6,101,120],"speaker-class":[7,43,66,105,123,140],"models.":[8,106,124],"In":[9,36,55,86,107,125],"previous":[10],"studies":[11],"based":[12],"on":[13],"this":[14,37],"method,":[15],"the":[16,30,34,87,127,134,139],"number":[17],"of":[18,52,61,104,132],"speaker":[19,53,78],"classes":[20],"was":[21,26,95,112,143],"relatively":[22],"small":[23],"and":[24],"it":[25],"difficult":[27],"to":[28,47,57,81,83],"improve":[29],"performance":[31,94],"significantly":[32],"over":[33],"baseline.":[35],"work,":[38],"as":[39,41],"many":[40],"500":[42],"models":[44],"are":[45],"used":[46,73],"enable":[48],"more":[49,145],"precise":[50],"modeling":[51],"characteristics.":[54],"order":[56],"avoid":[58],"a":[59,68,76,90,98,109,130],"lack":[60],"training":[62,77],"data":[63],"for":[64],"each":[65],"model,":[67],"soft":[69,117],"clustering":[70,118],"technique":[71],"is":[72,79],"in":[74,93],"which":[75],"allowed":[80],"belong":[82],"several":[84,102,121],"classes.":[85],"experiments,":[89],"slight":[91],"improvement":[92,111],"obtained":[96,113],"using":[97,114],"conventional":[99],"method":[100,119],"tens":[103],"contrast,":[108],"significant":[110],"an":[115],"unsupervised":[116],"hundred":[122],"addition,":[126],"results":[128],"indicated":[129],"possibility":[131],"reducing":[133],"error":[135],"rate":[136],"drastically":[137],"if":[138],"model":[141],"selection":[142],"conducted":[144],"effectively.":[146]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}