{"id":"https://openalex.org/W1984985727","doi":"https://doi.org/10.1109/icassp.2014.6854213","title":"Submodular subset selection for large-scale speech training data","display_name":"Submodular subset selection for large-scale speech training data","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W1984985727","doi":"https://doi.org/10.1109/icassp.2014.6854213","mag":"1984985727"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6854213","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854213","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5101693020","display_name":"Kai Wei","orcid":"https://orcid.org/0000-0001-7068-6114"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kai Wei","raw_affiliation_strings":["Department of Electrical Engineering, University of Washington Seattle, WA, USA","Dept. of Electr. Eng., Univ. of Washington, Seattle, WA, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Washington Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]},{"raw_affiliation_string":"Dept. of Electr. Eng., Univ. of Washington, Seattle, WA, USA#TAB#","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000919546","display_name":"Yuzong Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuzong Liu","raw_affiliation_strings":["Department of Electrical Engineering, University of Washington Seattle, WA, USA","Dept. of Electr. Eng., Univ. of Washington, Seattle, WA, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Washington Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]},{"raw_affiliation_string":"Dept. of Electr. Eng., Univ. of Washington, Seattle, WA, USA#TAB#","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050325468","display_name":"Katrin Kirchhoff","orcid":"https://orcid.org/0000-0002-6645-6030"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Katrin Kirchhoff","raw_affiliation_strings":["Department of Electrical Engineering, University of Washington Seattle, WA, USA","Dept. of Electr. Eng., Univ. of Washington, Seattle, WA, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Washington Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]},{"raw_affiliation_string":"Dept. of Electr. Eng., Univ. of Washington, Seattle, WA, USA#TAB#","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031137004","display_name":"Chris Bartels","orcid":null},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chris Bartels","raw_affiliation_strings":["SRI International, Menlo Park, CA, USA","SRI Int., Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI International, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]},{"raw_affiliation_string":"SRI Int., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113478221","display_name":"Jeff Bilmes","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeff Bilmes","raw_affiliation_strings":["Department of Electrical Engineering, University of Washington Seattle, WA, USA","Dept. of Electr. Eng., Univ. of Washington, Seattle, WA, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Washington Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]},{"raw_affiliation_string":"Dept. of Electr. Eng., Univ. of Washington, Seattle, WA, USA#TAB#","institution_ids":["https://openalex.org/I201448701"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101693020"],"corresponding_institution_ids":["https://openalex.org/I201448701"],"apc_list":null,"apc_paid":null,"fwci":13.952,"has_fulltext":false,"cited_by_count":80,"citation_normalized_percentile":{"value":0.98855076,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3311","last_page":"3315"},"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9980999827384949,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9940999746322632,"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/submodular-set-function","display_name":"Submodular set function","score":0.9491774439811707},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7806278467178345},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5809228420257568},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5759066939353943},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5563920140266418},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.49980688095092773},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.49868273735046387},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.49544990062713623},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.491328626871109},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47935372591018677},{"id":"https://openalex.org/keywords/greedy-algorithm","display_name":"Greedy algorithm","score":0.4311855733394623},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.41681915521621704},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.4100051522254944},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.36569714546203613},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35510939359664917},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.17824921011924744},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.16472724080085754},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11929446458816528}],"concepts":[{"id":"https://openalex.org/C178621042","wikidata":"https://www.wikidata.org/wiki/Q7631710","display_name":"Submodular set function","level":2,"score":0.9491774439811707},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7806278467178345},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5809228420257568},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5759066939353943},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5563920140266418},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.49980688095092773},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.49868273735046387},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.49544990062713623},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.491328626871109},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47935372591018677},{"id":"https://openalex.org/C51823790","wikidata":"https://www.wikidata.org/wiki/Q504353","display_name":"Greedy algorithm","level":2,"score":0.4311855733394623},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.41681915521621704},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.4100051522254944},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.36569714546203613},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35510939359664917},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.17824921011924744},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.16472724080085754},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11929446458816528},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2014.6854213","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854213","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.496.6287","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.496.6287","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://melodi.ee.washington.edu/~bilmes/mypubs/wei2014-supervised-large-icassp.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6399999856948853,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W195739637","https://openalex.org/W1524333225","https://openalex.org/W1566959760","https://openalex.org/W1579799841","https://openalex.org/W1596641231","https://openalex.org/W1680189815","https://openalex.org/W1898824936","https://openalex.org/W1975113979","https://openalex.org/W2032020816","https://openalex.org/W2045563462","https://openalex.org/W2053625667","https://openalex.org/W2118544668","https://openalex.org/W2125610823","https://openalex.org/W2135241496","https://openalex.org/W2143996311","https://openalex.org/W2144933361","https://openalex.org/W2150907703","https://openalex.org/W2161482971","https://openalex.org/W2250289728","https://openalex.org/W2411442511","https://openalex.org/W3149335959","https://openalex.org/W6631362777","https://openalex.org/W6634582008","https://openalex.org/W6635914189","https://openalex.org/W6677550685","https://openalex.org/W6681106510","https://openalex.org/W6691617551"],"related_works":["https://openalex.org/W4294276810","https://openalex.org/W4298470087","https://openalex.org/W2159208002","https://openalex.org/W2949672782","https://openalex.org/W4280632553","https://openalex.org/W2144629587","https://openalex.org/W2413963148","https://openalex.org/W2112634534","https://openalex.org/W2545766074","https://openalex.org/W2168237838"],"abstract_inverted_index":{"We":[0,55,94],"address":[1],"the":[2,37,122,126,134,145,151,156,162],"problem":[3,40],"of":[4,9,65,133,150],"subselecting":[5,60],"a":[6,24,46,112],"large":[7],"set":[8],"acoustic":[10,84],"data":[11,26,61,69,98,136,153],"to":[12,70,139,167],"train":[13,71],"automatic":[14],"speech":[15,75],"recognition":[16],"(ASR)":[17],"systems.":[18],"To":[19],"this":[20,169],"end,":[21],"we":[22],"apply":[23],"novel":[25],"selection":[27,110,115,124,159],"technique":[28,106],"based":[29,83,88],"on":[30,89,142],"constrained":[31],"submodular":[32,123],"function":[33],"maximization.":[34],"Though":[35],"NP-hard,":[36],"combinatorial":[38],"optimization":[39],"can":[41,99],"be":[42,100],"approximately":[43],"solved":[44],"by":[45,59],"simple":[47],"and":[48,86,103,111],"scalable":[49],"greedy":[50],"algorithm":[51],"with":[52,78,144,155],"constant-factor":[53],"guarantees.":[54],"evaluate":[56],"our":[57,105],"approach":[58],"from":[62],"1300":[63],"hours":[64],"conversational":[66],"English":[67],"telephone":[68],"two":[72],"types":[73],"large-vocabulary":[74],"recognizers,":[76],"one":[77],"Gaussian":[79],"mixture":[80],"model":[81],"(GMM)":[82],"models,":[85],"another":[87],"deep":[90],"neural":[91],"networks":[92],"(DNNs).":[93],"show":[95],"that":[96,104],"training":[97,135,152],"reduced":[101],"significantly,":[102],"outperforms":[107],"both":[108],"random":[109],"previously":[113],"proposed":[114],"method":[116],"utilizing":[117],"comparable":[118],"resources.":[119],"Notably,":[120],"using":[121,129,148],"method,":[125],"DNN":[127,163],"system":[128,147,164],"only":[130],"about":[131],"5%":[132],"is":[137,165],"able":[138],"achieve":[140],"performance":[141],"par":[143],"GMM":[146],"100%":[149],"-":[154],"baseline":[157],"subset":[158],"methods,":[160],"however,":[161],"unable":[166],"accomplish":[168],"correspondence.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":16},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":3}],"updated_date":"2026-05-19T08:33:51.333923","created_date":"2025-10-10T00:00:00"}