{"id":"https://openalex.org/W3208049241","doi":"https://doi.org/10.1109/icassp43922.2022.9746217","title":"SYNT++: Utilizing Imperfect Synthetic Data to Improve Speech Recognition","display_name":"SYNT++: Utilizing Imperfect Synthetic Data to Improve Speech Recognition","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3208049241","doi":"https://doi.org/10.1109/icassp43922.2022.9746217","mag":"3208049241"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746217","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746217","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":"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/A5062098630","display_name":"Ting-Yao Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ting-Yao Hu","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053849494","display_name":"Mohammadreza Armandpour","orcid":null},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammadreza Armandpour","raw_affiliation_strings":["Texas A&#x0026;M University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Texas A&#x0026;M University","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002740493","display_name":"Ashish Shrivastava","orcid":"https://orcid.org/0000-0002-2465-0708"},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ashish Shrivastava","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066816752","display_name":"Jen-Hao Rick Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jen-Hao Rick Chang","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064400393","display_name":"Hema Swetha Koppula","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hema Koppula","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028613002","display_name":"Oncel Tuzel","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Oncel Tuzel","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7682","last_page":"7686"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9993000030517578,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9977999925613403,"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/synthetic-data","display_name":"Synthetic data","score":0.7757118344306946},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7692019939422607},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.6946399807929993},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6206395626068115},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5076225996017456},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4883868098258972},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46935850381851196},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4617919921875},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4429765045642853},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.4411535859107971},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.43822187185287476},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3747500479221344},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.09196352958679199}],"concepts":[{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.7757118344306946},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7692019939422607},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6946399807929993},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6206395626068115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5076225996017456},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4883868098258972},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46935850381851196},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4617919921875},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4429765045642853},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.4411535859107971},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.43822187185287476},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3747500479221344},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.09196352958679199},{"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/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746217","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746217","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1836465849","https://openalex.org/W2099471712","https://openalex.org/W2770173563","https://openalex.org/W2794490148","https://openalex.org/W2797583228","https://openalex.org/W2883586237","https://openalex.org/W2897371726","https://openalex.org/W2898741639","https://openalex.org/W2903739847","https://openalex.org/W2912937645","https://openalex.org/W2936774411","https://openalex.org/W2943008652","https://openalex.org/W2948211236","https://openalex.org/W2950247758","https://openalex.org/W2962780374","https://openalex.org/W2963272440","https://openalex.org/W2963432880","https://openalex.org/W2963581463","https://openalex.org/W2963691546","https://openalex.org/W2963709863","https://openalex.org/W2963739817","https://openalex.org/W2964151866","https://openalex.org/W2964243274","https://openalex.org/W2972359262","https://openalex.org/W2972889948","https://openalex.org/W3008480565","https://openalex.org/W3015212100","https://openalex.org/W3015399080","https://openalex.org/W3015449694","https://openalex.org/W3015654635","https://openalex.org/W3025165719","https://openalex.org/W3033411150","https://openalex.org/W3035743198","https://openalex.org/W3097777922","https://openalex.org/W3097890746","https://openalex.org/W3130016944","https://openalex.org/W3132711939","https://openalex.org/W3153492756","https://openalex.org/W3161143478","https://openalex.org/W3162244132","https://openalex.org/W3163074978","https://openalex.org/W3201970400","https://openalex.org/W4212863985","https://openalex.org/W4286909631","https://openalex.org/W4299292578","https://openalex.org/W4320013936","https://openalex.org/W6629510986","https://openalex.org/W6638667902","https://openalex.org/W6746638498","https://openalex.org/W6749489859","https://openalex.org/W6750042782","https://openalex.org/W6750489868","https://openalex.org/W6750665317","https://openalex.org/W6755358316","https://openalex.org/W6778823374","https://openalex.org/W6802119844"],"related_works":["https://openalex.org/W2016839265","https://openalex.org/W2508457823","https://openalex.org/W1991269640","https://openalex.org/W2092619848","https://openalex.org/W197875813","https://openalex.org/W4366608932","https://openalex.org/W2162397380","https://openalex.org/W4385453371","https://openalex.org/W2123003832","https://openalex.org/W3015611303"],"abstract_inverted_index":{"With":[0],"recent":[1],"advances":[2],"in":[3,51],"speech":[4,18,125],"synthesis,":[5],"synthetic":[6,25,36,113,129,161],"data":[7,15,26,40,53,78],"is":[8,27],"becoming":[9],"a":[10,70,97],"viable":[11],"alternative":[12],"to":[13,31,73,87,92,148,157],"real":[14,39,52,110],"for":[16,108],"training":[17,86,123],"recognition":[19,126],"models.":[20],"However,":[21],"machine":[22],"learning":[23],"with":[24],"not":[28,49],"trivial":[29],"due":[30,72,91],"the":[32,35,38,65,77,89,93,109,112,122,133,160],"gap":[33],"between":[34],"and":[37,101,111,139,145,150],"distributions.":[41],"Synthetic":[42],"datasets":[43],"may":[44,68],"contain":[45],"artifacts":[46],"that":[47,117],"do":[48],"exist":[50],"such":[54],"as":[55],"structured":[56],"noise,":[57],"content":[58],"errors,":[59],"or":[60],"unrealistic":[61],"speaking":[62],"styles.":[63],"Moreover,":[64],"synthesis":[66],"process":[67],"introduce":[69],"bias":[71],"uneven":[74],"sampling":[75,99],"of":[76,124],"manifold.":[79],"We":[80,115,131],"propose":[81],"two":[82],"novel":[83],"techniques":[84],"during":[85],"mitigate":[88],"problems":[90],"distribution":[94],"gap:":[95],"(i)":[96],"rejection":[98],"algorithm":[100],"(ii)":[102],"using":[103,128,159],"separate":[104],"batch":[105],"normalization":[106],"statistics":[107],"samples.":[114],"show":[116],"these":[118],"methods":[119],"significantly":[120],"improve":[121],"models":[127],"data.":[130,162],"evaluate":[132],"proposed":[134],"approach":[135],"on":[136],"keyword":[137],"detection":[138],"Automatic":[140],"Speech":[141],"Recognition":[142],"(ASR)":[143],"tasks,":[144],"observe":[146],"up":[147],"18%":[149],"13%":[151],"relative":[152],"error":[153],"reduction,":[154],"respectively,":[155],"compared":[156],"naively":[158]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
