{"id":"https://openalex.org/W4225325562","doi":"https://doi.org/10.1109/icassp43922.2022.9747003","title":"Importantaug: A Data Augmentation Agent for Speech","display_name":"Importantaug: A Data Augmentation Agent for Speech","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225325562","doi":"https://doi.org/10.1109/icassp43922.2022.9747003"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747003","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747003","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5085746637","display_name":"Viet Anh Trinh","orcid":"https://orcid.org/0000-0002-1660-6627"},"institutions":[{"id":"https://openalex.org/I121847817","display_name":"The Graduate Center, CUNY","ror":"https://ror.org/00awd9g61","country_code":"US","type":"education","lineage":["https://openalex.org/I121847817"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Viet Anh Trinh","raw_affiliation_strings":["CUNY,The Graduate Center,New York,USA","The Graduate Center, CUNY, New York, USA"],"affiliations":[{"raw_affiliation_string":"CUNY,The Graduate Center,New York,USA","institution_ids":["https://openalex.org/I121847817"]},{"raw_affiliation_string":"The Graduate Center, CUNY, New York, USA","institution_ids":["https://openalex.org/I121847817"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021099241","display_name":"Hassan Salami Kavaki","orcid":null},"institutions":[{"id":"https://openalex.org/I121847817","display_name":"The Graduate Center, CUNY","ror":"https://ror.org/00awd9g61","country_code":"US","type":"education","lineage":["https://openalex.org/I121847817"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hassan Salami Kavaki","raw_affiliation_strings":["CUNY,The Graduate Center,New York,USA","The Graduate Center, CUNY, New York, USA"],"affiliations":[{"raw_affiliation_string":"CUNY,The Graduate Center,New York,USA","institution_ids":["https://openalex.org/I121847817"]},{"raw_affiliation_string":"The Graduate Center, CUNY, New York, USA","institution_ids":["https://openalex.org/I121847817"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043596676","display_name":"Michael Mandel","orcid":null},"institutions":[{"id":"https://openalex.org/I121847817","display_name":"The Graduate Center, CUNY","ror":"https://ror.org/00awd9g61","country_code":"US","type":"education","lineage":["https://openalex.org/I121847817"]},{"id":"https://openalex.org/I83041322","display_name":"Brooklyn College","ror":"https://ror.org/019k4jq75","country_code":"US","type":"education","lineage":["https://openalex.org/I83041322"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael I Mandel","raw_affiliation_strings":["CUNY,The Graduate Center,New York,USA","Brooklyn College, CUNY, New York, USA","The Graduate Center, CUNY, New York, USA"],"affiliations":[{"raw_affiliation_string":"CUNY,The Graduate Center,New York,USA","institution_ids":["https://openalex.org/I121847817"]},{"raw_affiliation_string":"Brooklyn College, CUNY, New York, USA","institution_ids":["https://openalex.org/I83041322"]},{"raw_affiliation_string":"The Graduate Center, CUNY, New York, USA","institution_ids":["https://openalex.org/I121847817"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5085746637"],"corresponding_institution_ids":["https://openalex.org/I121847817"],"apc_list":null,"apc_paid":null,"fwci":1.1434,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.79433312,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"8592","last_page":"8596"},"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/T10860","display_name":"Speech 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/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"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":0.7614341974258423},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.7592355012893677},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7005213499069214},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6825137734413147},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6007891297340393},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5985441207885742},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5973326563835144},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5433441400527954},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.5023291110992432},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4793039858341217},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.4677002429962158},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4552153944969177},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4323510229587555},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3665171265602112},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3450279235839844},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12720194458961487}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7614341974258423},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.7592355012893677},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7005213499069214},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6825137734413147},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6007891297340393},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5985441207885742},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5973326563835144},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5433441400527954},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.5023291110992432},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4793039858341217},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.4677002429962158},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4552153944969177},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4323510229587555},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3665171265602112},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3450279235839844},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12720194458961487},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","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},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747003","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747003","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W891534129","https://openalex.org/W1922655562","https://openalex.org/W2128272608","https://openalex.org/W2135957164","https://openalex.org/W2146103513","https://openalex.org/W2219249508","https://openalex.org/W2407080277","https://openalex.org/W2442293398","https://openalex.org/W2531409750","https://openalex.org/W2583180462","https://openalex.org/W2617258110","https://openalex.org/W2738450183","https://openalex.org/W2744592570","https://openalex.org/W2747899975","https://openalex.org/W2797583228","https://openalex.org/W2889118710","https://openalex.org/W2889239910","https://openalex.org/W2936774411","https://openalex.org/W2963454111","https://openalex.org/W3015889230","https://openalex.org/W3026827614","https://openalex.org/W3096788328","https://openalex.org/W3097018422","https://openalex.org/W3109931032","https://openalex.org/W3177330184","https://openalex.org/W6640090968","https://openalex.org/W6680437723","https://openalex.org/W6688816777","https://openalex.org/W6732940373","https://openalex.org/W6739879593","https://openalex.org/W6750665317"],"related_works":["https://openalex.org/W4375869276","https://openalex.org/W3156260480","https://openalex.org/W4221152531","https://openalex.org/W2319316830","https://openalex.org/W2600379459","https://openalex.org/W2914064142","https://openalex.org/W2046186789","https://openalex.org/W2150750161","https://openalex.org/W2143693287","https://openalex.org/W4225325562"],"abstract_inverted_index":{"We":[0],"introduce":[1],"ImportantAug,":[2],"a":[3,36,83,111,118],"technique":[4],"to":[5,18,26,43,90,97,101,117],"augment":[6],"training":[7],"data":[8,37,121],"for":[9,32],"speech":[10,23,98],"classification":[11],"and":[12,24,132],"recognition":[13,56],"models":[14],"by":[15,35],"adding":[16],"noise":[17,48,92,96,130,141],"unimportant":[19],"regions":[20],"of":[21,47,60,68],"the":[22,45,69,76,124,128,133],"not":[25],"important":[27],"regions.":[28],"Importance":[29],"is":[30,41,63],"predicted":[31],"each":[33],"utterance":[34],"augmentation":[38,93,131],"agent":[39],"that":[40],"trained":[42],"maximize":[44],"amount":[46],"it":[49,81,103],"adds":[50],"while":[51],"minimizing":[52],"its":[53],"impact":[54],"on":[55,65,135],"performance.":[57],"The":[58],"effectiveness":[59],"our":[61],"method":[62],"illustrated":[64],"version":[66],"two":[67,136],"Google":[70],"Speech":[71],"Commands":[72],"(GSC)":[73],"dataset.":[74],"On":[75],"standard":[77],"GSC":[78],"test":[79,137],"set,":[80],"achieves":[82],"23.3%":[84],"relative":[85],"error":[86,113],"rate":[87,114],"reduction":[88,115],"compared":[89,116],"conventional":[91,129],"which":[94],"applies":[95],"without":[99,120],"regard":[100],"where":[102],"might":[104],"be":[105],"most":[106],"effective.":[107],"It":[108],"also":[109],"provides":[110],"25.4%":[112],"baseline":[119,134],"augmentation.":[122],"Additionally,":[123],"proposed":[125],"ImportantAug":[126],"outperforms":[127],"sets":[138],"with":[139],"additional":[140],"added.":[142]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}