{"id":"https://openalex.org/W3162334527","doi":"https://doi.org/10.1109/icassp39728.2021.9413869","title":"Improved Data Selection for Domain Adaptation in ASR","display_name":"Improved Data Selection for Domain Adaptation in ASR","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3162334527","doi":"https://doi.org/10.1109/icassp39728.2021.9413869","mag":"3162334527"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413869","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413869","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5022128897","display_name":"Shannon Wotherspoon","orcid":null},"institutions":[{"id":"https://openalex.org/I1306686416","display_name":"RTX (United States)","ror":"https://ror.org/0354t7b78","country_code":"US","type":"company","lineage":["https://openalex.org/I1306686416"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shannon Wotherspoon","raw_affiliation_strings":["Raytheon BBN,Cambridge,MA,USA","Raytheon BBN, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Raytheon BBN,Cambridge,MA,USA","institution_ids":["https://openalex.org/I1306686416"]},{"raw_affiliation_string":"Raytheon BBN, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1306686416"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047770365","display_name":"William M. Hartmann","orcid":null},"institutions":[{"id":"https://openalex.org/I1306686416","display_name":"RTX (United States)","ror":"https://ror.org/0354t7b78","country_code":"US","type":"company","lineage":["https://openalex.org/I1306686416"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William Hartmann","raw_affiliation_strings":["Raytheon BBN,Cambridge,MA,USA","Raytheon BBN, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Raytheon BBN,Cambridge,MA,USA","institution_ids":["https://openalex.org/I1306686416"]},{"raw_affiliation_string":"Raytheon BBN, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1306686416"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027655932","display_name":"Matthew Snover","orcid":null},"institutions":[{"id":"https://openalex.org/I1306686416","display_name":"RTX (United States)","ror":"https://ror.org/0354t7b78","country_code":"US","type":"company","lineage":["https://openalex.org/I1306686416"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew Snover","raw_affiliation_strings":["Raytheon BBN,Cambridge,MA,USA","Raytheon BBN, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Raytheon BBN,Cambridge,MA,USA","institution_ids":["https://openalex.org/I1306686416"]},{"raw_affiliation_string":"Raytheon BBN, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1306686416"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110205522","display_name":"Owen Kimball","orcid":null},"institutions":[{"id":"https://openalex.org/I1306686416","display_name":"RTX (United States)","ror":"https://ror.org/0354t7b78","country_code":"US","type":"company","lineage":["https://openalex.org/I1306686416"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Owen Kimball","raw_affiliation_strings":["Raytheon BBN,Cambridge,MA,USA","Raytheon BBN, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Raytheon BBN,Cambridge,MA,USA","institution_ids":["https://openalex.org/I1306686416"]},{"raw_affiliation_string":"Raytheon BBN, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1306686416"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1306686416"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7018","last_page":"7022"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9977999925613403,"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":0.9916999936103821,"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":0.7712196111679077},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.6642032861709595},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6118527054786682},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5568380355834961},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5397570729255676},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.505158007144928},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5000028610229492},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.4960709512233734},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4720776081085205},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4663848876953125},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4503374397754669},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35261160135269165},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2727159559726715},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12941798567771912}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7712196111679077},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.6642032861709595},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6118527054786682},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5568380355834961},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5397570729255676},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.505158007144928},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5000028610229492},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.4960709512233734},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4720776081085205},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4663848876953125},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4503374397754669},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35261160135269165},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2727159559726715},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12941798567771912},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413869","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413869","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W23007503","https://openalex.org/W47152650","https://openalex.org/W82886505","https://openalex.org/W97072897","https://openalex.org/W1524333225","https://openalex.org/W1975113979","https://openalex.org/W2056786202","https://openalex.org/W2103933358","https://openalex.org/W2124558353","https://openalex.org/W2136780519","https://openalex.org/W2139453310","https://openalex.org/W2166637769","https://openalex.org/W2189391786","https://openalex.org/W2404463488","https://openalex.org/W2511419867","https://openalex.org/W2514805646","https://openalex.org/W2587088898","https://openalex.org/W2594610113","https://openalex.org/W2729190387","https://openalex.org/W2746930212","https://openalex.org/W2748795451","https://openalex.org/W2889162046","https://openalex.org/W2898630520","https://openalex.org/W2950170869","https://openalex.org/W2962894366","https://openalex.org/W2962907457","https://openalex.org/W2973143291","https://openalex.org/W6603931906","https://openalex.org/W6631362777"],"related_works":["https://openalex.org/W3110702597","https://openalex.org/W2073713056","https://openalex.org/W2125620709","https://openalex.org/W2110441383","https://openalex.org/W2045932760","https://openalex.org/W2326878701","https://openalex.org/W4293864700","https://openalex.org/W2184228419","https://openalex.org/W67445448","https://openalex.org/W2061937230"],"abstract_inverted_index":{"Automatic":[0],"speech":[1],"recognition":[2],"(ASR)":[3],"systems":[4],"are":[5,111],"highly":[6],"sensitive":[7],"to":[8,22,25,45,134],"train-test":[9],"domain":[10,38,100,159],"mismatch.":[11],"However,":[12],"because":[13],"transcription":[14],"is":[15,20,68,77],"often":[16],"prohibitively":[17],"expensive,":[18],"it":[19],"important":[21],"be":[23],"able":[24],"make":[26],"use":[27],"of":[28,37,60,65,95],"available":[29],"transcribed":[30],"out-of-domain":[31,140],"data.":[32],"We":[33,70],"address":[34,117],"the":[35,63,66,91,139],"problem":[36],"adaptation":[39],"with":[40,56],"semi-supervised":[41],"training":[42],"(SST).":[43],"Contrary":[44],"work":[46],"in":[47],"in-domain":[48],"SST,":[49],"we":[50,85,102,116,131],"find":[51,104],"significant":[52],"performance":[53],"improvement":[54],"even":[55],"just":[57],"one":[58],"hour":[59],"target-domain":[61],"data\u2014though,":[62],"selection":[64,124,129,145,155],"data":[67],"critical.":[69],"show":[71],"that":[72,105],"minimum":[73],"phone":[74,93,120],"error":[75],"rate":[76,121],"a":[78,112],"good":[79],"oracle":[80],"measure":[81,88],"for":[82],"selection,":[83],"and":[84,107,149],"approximate":[86],"this":[87,144],"by":[89,118],"using":[90],"average":[92],"confidence":[94,154],"an":[96],"utterance.":[97],"With":[98,126],"larger":[99],"shifts,":[101],"also":[103],"deletions":[106],"low":[108],"lexical":[109],"diversity":[110],"serious":[113],"issue,":[114],"which":[115],"incorporating":[119],"into":[122],"our":[123,127],"metric.":[125],"proposed":[128],"criterion,":[130],"see":[132],"up":[133],"57%":[135],"relative":[136],"improvements":[137],"over":[138],"baseline":[141],"model.":[142],"Furthermore,":[143],"method":[146],"generalizes":[147],"well,":[148],"matches":[150],"or":[151],"outperforms":[152],"word-level":[153],"across":[156],"six":[157],"separate":[158],"shift":[160],"conditions.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}