{"id":"https://openalex.org/W4224939570","doi":"https://doi.org/10.1109/icassp43922.2022.9747390","title":"Unsupervised Data Selection for Speech Recognition with Contrastive Loss Ratios","display_name":"Unsupervised Data Selection for Speech Recognition with Contrastive Loss Ratios","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224939570","doi":"https://doi.org/10.1109/icassp43922.2022.9747390"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747390","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2207.12028","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102020512","display_name":"Chanho Park","orcid":"https://orcid.org/0000-0001-6671-1671"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Chanho Park","raw_affiliation_strings":["Department of Computer Science, University of Sheffield"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Sheffield","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060629604","display_name":"Rehan Ahmad","orcid":"https://orcid.org/0000-0002-0194-6653"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Rehan Ahmad","raw_affiliation_strings":["Department of Computer Science, University of Sheffield"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Sheffield","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030528300","display_name":"Thomas Hain","orcid":"https://orcid.org/0000-0003-0939-3464"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Thomas Hain","raw_affiliation_strings":["Department of Computer Science, University of Sheffield"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Sheffield","institution_ids":["https://openalex.org/I91136226"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.964,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":6,"citation_normalized_percentile":{"value":0.999875,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":85,"max":87},"biblio":{"volume":null,"issue":null,"first_page":"8587","last_page":"8591"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998,"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":0.9998,"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":0.9994,"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":0.9964,"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/submodular-set-function","display_name":"Submodular set function","score":0.8686223},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.57972735},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.5461463},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.41600406}],"concepts":[{"id":"https://openalex.org/C178621042","wikidata":"https://www.wikidata.org/wiki/Q7631710","display_name":"Submodular set function","level":2,"score":0.8686223},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.68264395},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.57972735},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.566186},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.56162924},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.5461463},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.52922064},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.50722504},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47795796},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4695761},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4428165},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.43738204},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.41600406},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24155244},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.18762642},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747390","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2207.12028","pdf_url":"https://arxiv.org/pdf/2207.12028","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":false,"landing_page_url":"https://api.datacite.org/dois/10.48550/arxiv.2207.12028","pdf_url":null,"source":{"id":"https://openalex.org/S4393179698","display_name":"DataCite API","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210145204","host_organization_name":"DataCite","host_organization_lineage":["https://openalex.org/I4210145204"],"host_organization_lineage_names":["DataCite"],"type":"metadata"},"license":null,"license_id":null,"version":null}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2207.12028","pdf_url":"https://arxiv.org/pdf/2207.12028","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[{"score":0.49,"display_name":"Quality education","id":"https://metadata.un.org/sdg/4"}],"grants":[],"datasets":[],"versions":["https://openalex.org/W4224939570"],"referenced_works_count":17,"referenced_works":["https://openalex.org/W1579799841","https://openalex.org/W2053625667","https://openalex.org/W2125336414","https://openalex.org/W2130722890","https://openalex.org/W2500139799","https://openalex.org/W2954732411","https://openalex.org/W2962907457","https://openalex.org/W2963683295","https://openalex.org/W2973049979","https://openalex.org/W3093579165","https://openalex.org/W3163169798","https://openalex.org/W3198771897","https://openalex.org/W4287173589","https://openalex.org/W4297797495","https://openalex.org/W4297808394","https://openalex.org/W4298302210","https://openalex.org/W97072897"],"related_works":["https://openalex.org/W4381430104","https://openalex.org/W4245698648","https://openalex.org/W3133710586","https://openalex.org/W2991483587","https://openalex.org/W2786391746","https://openalex.org/W2405257913","https://openalex.org/W2146197305","https://openalex.org/W2125964738","https://openalex.org/W2098529290","https://openalex.org/W2026402306"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"an":[3],"unsupervised":[4],"data":[5,22,66,77,134,164,177],"selection":[6,86],"method":[7,83,87,127],"by":[8,47,80,92,168],"using":[9,26,52],"a":[10,27,48,56,104],"submodular":[11,49,54],"function":[12,30],"based":[13,88],"on":[14,33,75,89,120,146,151,161],"contrastive":[15,28],"loss":[16,29],"ratios":[17],"of":[18,39,97,110,117,138,148],"target":[19,65],"and":[20],"training":[21,57,154],"sets.":[23,35],"A":[24],"model":[25,44],"is":[31,45,68],"trained":[32,74,150],"both":[34],"Then":[36],"the":[37,53,64,76,81,85,112,115,136,152,159,162,175],"ratio":[38],"frame-level":[40],"losses":[41],"for":[42,59],"each":[43],"used":[46,131],"function.":[50],"By":[51],"function,":[55],"set":[58,67,165],"automatic":[60],"speech":[61],"recognition":[62],"matching":[63],"selected.":[69],"Experiments":[70],"show":[71,157],"that":[72,158],"models":[73,149],"sets":[78],"selected":[79],"proposed":[82],"outperform":[84],"log-likelihoods":[90],"produced":[91],"GMM-HMM":[93],"models,":[94],"in":[95],"terms":[96],"word":[98],"error":[99],"rate":[100],"(WER).":[101],"When":[102],"selecting":[103,172],"fixed":[105],"amount,":[106],"e.g.":[107],"10":[108],"hours":[109],"data,":[111],"difference":[113],"between":[114],"results":[116],"two":[118],"methods":[119],"Tedtalks":[121],"was":[122,166],"20.23%":[123],"WER":[124,160],"relative.":[125],"The":[126],"can":[128],"also":[129],"be":[130],"to":[132],"select":[133],"with":[135],"aim":[137],"minimising":[139],"negative":[140],"transfer,":[141],"while":[142],"maintaining":[143],"or":[144],"improving":[145],"performance":[147],"whole":[153,176],"set.":[155,178],"Results":[156],"WSJCAM0":[163],"reduced":[167],"6.26%":[169],"relative":[170],"when":[171],"85%":[173],"from":[174]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4224939570","counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2025-01-06T07:59:52.209271","created_date":"2022-04-28"}