{"id":"https://openalex.org/W184194209","doi":"https://doi.org/10.21437/interspeech.2010-13","title":"Unsupervised discovery and training of maximally dissimilar cluster models","display_name":"Unsupervised discovery and training of maximally dissimilar cluster models","publication_year":2010,"publication_date":"2010-09-26","ids":{"openalex":"https://openalex.org/W184194209","doi":"https://doi.org/10.21437/interspeech.2010-13","mag":"184194209"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2010-13","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-13","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","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/A5110711540","display_name":"Fran\u00e7oise Beaufays","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fran\u00e7oise Beaufays","raw_affiliation_strings":["Google\u2020#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google\u2020#TAB#","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013813527","display_name":"Vincent Vanhoucke","orcid":"https://orcid.org/0000-0003-0544-2791"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vincent Vanhoucke","raw_affiliation_strings":["Google\u2020#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google\u2020#TAB#","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001487094","display_name":"Brian Strope","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Strope","raw_affiliation_strings":["Google\u2020#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google\u2020#TAB#","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"66","last_page":"69"},"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":0.9997000098228455,"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/T10860","display_name":"Speech 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":0.7790762186050415},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5654008984565735},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.5389547944068909},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.518335223197937},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4761628806591034},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46227914094924927},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46064522862434387},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.45101481676101685},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.4490436613559723},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.42927423119544983},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4247969090938568},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4222833514213562},{"id":"https://openalex.org/keywords/data-space","display_name":"Data space","score":0.41802069544792175},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34268367290496826},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.24604472517967224},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.11982735991477966}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7790762186050415},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5654008984565735},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.5389547944068909},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.518335223197937},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4761628806591034},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46227914094924927},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46064522862434387},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.45101481676101685},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.4490436613559723},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.42927423119544983},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4247969090938568},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4222833514213562},{"id":"https://openalex.org/C2988382989","wikidata":"https://www.wikidata.org/wiki/Q370685","display_name":"Data space","level":2,"score":0.41802069544792175},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34268367290496826},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.24604472517967224},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.11982735991477966},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2010-13","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-13","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.308.77","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.308.77","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://static.googleusercontent.com/external_content/untrusted_dlcp/research.google.com/en/us/pubs/archive/36487.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":14,"referenced_works":["https://openalex.org/W10987127","https://openalex.org/W1509455084","https://openalex.org/W1599512239","https://openalex.org/W1953949349","https://openalex.org/W1967676196","https://openalex.org/W1967707915","https://openalex.org/W2069631319","https://openalex.org/W2103633133","https://openalex.org/W2106554350","https://openalex.org/W2121981798","https://openalex.org/W2125234026","https://openalex.org/W2168132435","https://openalex.org/W2173213060","https://openalex.org/W3145606929"],"related_works":["https://openalex.org/W3161249280","https://openalex.org/W2267059662","https://openalex.org/W2364268683","https://openalex.org/W4388411807","https://openalex.org/W3008857645","https://openalex.org/W3037605386","https://openalex.org/W1986600592","https://openalex.org/W2142596579","https://openalex.org/W2091777168","https://openalex.org/W184194209"],"abstract_inverted_index":{"One":[0],"of":[1,5,21,47,82,105,112,146],"the":[2,18,29,45,83,113],"difficult":[3],"problems":[4],"acoustic":[6,22,87,114,150],"modeling":[7,99],"for":[8,36],"Automatic":[9],"Speech":[10],"Recognition":[11],"(ASR)":[12],"is":[13,33,52,70,74],"how":[14],"to":[15,76,96,143],"adequately":[16],"model":[17,80],"wide":[19],"variety":[20],"conditions":[23,128],"which":[24,93],"may":[25],"be":[26],"present":[27],"in":[28,126],"data.":[30,157],"The":[31],"problem":[32],"especially":[34],"acute":[35],"tasks":[37],"such":[38],"as":[39],"Google":[40],"Search":[41],"by":[42,107],"Voice,":[43],"where":[44],"amount":[46],"speech":[48],"available":[49,71],"per":[50],"transaction":[51],"small,":[53],"and":[54,78,116],"adaptation":[55],"techniques":[56],"start":[57],"showing":[58],"their":[59],"limitations.":[60],"As":[61],"training":[62],"data":[63,84,106],"from":[64],"a":[65,91,109],"very":[66],"large":[67,103],"user":[68],"population":[69],"however,":[72],"it":[73],"possible":[75],"identify":[77],"jointly":[79],"subsets":[81],"with":[85],"similar":[86],"qualities.":[88],"We":[89],"describe":[90],"technique":[92,140],"allows":[94],"us":[95],"perform":[97],"this":[98,139],"at":[100],"scale":[101],"on":[102],"amounts":[104],"learning":[108],"treestructured":[110],"partition":[111],"space,":[115],"we":[117,120],"demonstrate":[118],"that":[119],"can":[121],"significantly":[122],"improve":[123],"recognition":[124],"accuracy":[125],"various":[127],"through":[129],"unsupervised":[130,152],"Maximum":[131],"Mutual":[132],"Information":[133],"(MMI)":[134],"training.":[135],"Being":[136],"fully":[137],"unsupervised,":[138],"scales":[141],"easily":[142],"increasing":[144],"numbers":[145],"conditions.":[147],"Index":[148],"Terms:":[149],"modeling,":[151],"learning,":[153],"clustering,":[154],"too":[155],"much":[156]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}