{"id":"https://openalex.org/W2129973155","doi":"https://doi.org/10.1109/icassp.2004.1326113","title":"Studies in massively speaker-specific speech recognition","display_name":"Studies in massively speaker-specific speech recognition","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https://openalex.org/W2129973155","doi":"https://doi.org/10.1109/icassp.2004.1326113","mag":"2129973155"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2004.1326113","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326113","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","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/A5028585584","display_name":"Yu Shi","orcid":"https://orcid.org/0000-0003-3891-7175"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yu Shi","raw_affiliation_strings":["Microsoft Research Asia, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087298985","display_name":"Eric Chang","orcid":"https://orcid.org/0000-0002-9678-5994"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Eric Chang","raw_affiliation_strings":["Microsoft Research Asia, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5028585584"],"corresponding_institution_ids":["https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":0.4625,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.76598622,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"825"},"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/T11309","display_name":"Music and Audio Processing","score":0.9980999827384949,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9972000122070312,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7792580127716064},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7052163481712341},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.637047529220581},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6277433037757874},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.595609724521637},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5715157985687256},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24833688139915466}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7792580127716064},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7052163481712341},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.637047529220581},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6277433037757874},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.595609724521637},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5715157985687256},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24833688139915466},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2004.1326113","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326113","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.187.9576","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.187.9576","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/pubs/69067/0100825.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322392","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W104579193","https://openalex.org/W142477701","https://openalex.org/W231674987","https://openalex.org/W1520930749","https://openalex.org/W1599512239","https://openalex.org/W2013891821","https://openalex.org/W2016243284","https://openalex.org/W2112059504","https://openalex.org/W6604309427","https://openalex.org/W6605686022","https://openalex.org/W6609141048","https://openalex.org/W6631216164"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1521049138","https://openalex.org/W2144208207","https://openalex.org/W1813780412","https://openalex.org/W1509309911","https://openalex.org/W1940231550","https://openalex.org/W2148232863","https://openalex.org/W2160753975","https://openalex.org/W2096510939","https://openalex.org/W2161543916"],"abstract_inverted_index":{"Over":[0],"the":[1,5,9,19,34,92,103,109,118],"past":[2],"several":[3],"years,":[4],"primary":[6],"focus":[7,119],"for":[8,45,62],"speech-recognition":[10],"research":[11],"community":[12],"has":[13],"been":[14],"speaker-independent":[15],"speech":[16,58,133],"recognition,":[17],"with":[18,25,131],"emphasis":[20],"of":[21,30,47,49,72,105],"working":[22],"on":[23],"databases":[24],"larger":[26,28],"and":[27,66],"numbers":[29],"speakers.":[31,50],"For":[32],"example,":[33],"most":[35],"recent":[36],"EARS":[37],"program,":[38],"which":[39],"is":[40],"sponsored":[41],"by":[42,116],"DARPA,":[43],"calls":[44],"recordings":[46],"thousands":[48],"However,":[51],"we":[52,67,90,95],"are":[53],"interested":[54],"in":[55,77],"making":[56],"a":[57,88],"interface":[59],"work":[60,100],"well":[61],"one":[63,150],"particular":[64,151],"individual,":[65],"propose":[68],"using":[69],"massive":[70],"amounts":[71],"speaker-specific":[73,84],"training":[74],"data":[75],"recorded":[76],"daily":[78],"life.":[79],"We":[80],"call":[81],"this":[82],"massively":[83],"recognition":[85,134],"(MSSR).":[86],"As":[87],"pre-research,":[89],"leverage":[91],"large":[93],"corpus":[94],"have":[96],"available":[97],"from":[98,108],"speech-synthesis":[99],"to":[101,120,146,149],"study":[102],"benefit":[104],"MSSR":[106,136],"only":[107],"acoustic-modeling":[110],"aspect.":[111],"Initial":[112],"results":[113],"show":[114],"that,":[115],"changing":[117],"MSSR,":[121],"word":[122],"error":[123],"rates":[124],"can":[125,143],"drop":[126],"very":[127],"significantly.":[128],"In":[129],"comparison":[130],"speaker-adaptive":[132],"systems,":[135],"also":[137],"performs":[138],"better":[139],"since":[140],"model":[141],"parameters":[142],"be":[144,147],"tuned":[145],"suitable":[148],"individual.":[152]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}