{"id":"https://openalex.org/W3015723617","doi":"https://doi.org/10.1109/icassp40776.2020.9053098","title":"Aipnet: Generative Adversarial Pre-Training of Accent-Invariant Networks for End-To-End Speech Recognition","display_name":"Aipnet: Generative Adversarial Pre-Training of Accent-Invariant Networks for End-To-End Speech Recognition","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015723617","doi":"https://doi.org/10.1109/icassp40776.2020.9053098","mag":"3015723617"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053098","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053098","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5100450914","display_name":"Yi\u2010Chen Chen","orcid":"https://orcid.org/0000-0002-4616-2115"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yi-Chen Chen","raw_affiliation_strings":["Facebook AI, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026640062","display_name":"Yang Zhao-jun","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhaojun Yang","raw_affiliation_strings":["Facebook AI, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087421101","display_name":"Ching-Feng Yeh","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ching-Feng Yeh","raw_affiliation_strings":["Facebook AI, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112701957","display_name":"Mahaveer Jain","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mahaveer Jain","raw_affiliation_strings":["Facebook AI, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041313589","display_name":"Michael L. Seltzer","orcid":"https://orcid.org/0000-0003-3474-2451"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael L. Seltzer","raw_affiliation_strings":["Facebook AI, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100450914"],"corresponding_institution_ids":["https://openalex.org/I4210114444"],"apc_list":null,"apc_paid":null,"fwci":3.4465,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.93744512,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6979","last_page":"6983"},"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":0.998199999332428,"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":0.9973999857902527,"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/speech-recognition","display_name":"Speech recognition","score":0.7290464639663696},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6896302700042725},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.5619100332260132},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.55039381980896},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5466507077217102},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5015618801116943},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.48679348826408386},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4522840678691864},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38195526599884033},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16370588541030884}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7290464639663696},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6896302700042725},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.5619100332260132},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.55039381980896},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5466507077217102},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5015618801116943},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.48679348826408386},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4522840678691864},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38195526599884033},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16370588541030884},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053098","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053098","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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","score":0.6100000143051147,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W143647774","https://openalex.org/W1882958252","https://openalex.org/W2099471712","https://openalex.org/W2106440210","https://openalex.org/W2130414229","https://openalex.org/W2153579005","https://openalex.org/W2163605009","https://openalex.org/W2187089797","https://openalex.org/W2294108103","https://openalex.org/W2327501763","https://openalex.org/W2405866807","https://openalex.org/W2408195107","https://openalex.org/W2584009249","https://openalex.org/W2584667682","https://openalex.org/W2587080466","https://openalex.org/W2603679025","https://openalex.org/W2758785877","https://openalex.org/W2884305338","https://openalex.org/W2896457183","https://openalex.org/W2938374794","https://openalex.org/W2962684181","https://openalex.org/W2962893195","https://openalex.org/W2963341956","https://openalex.org/W2963618559","https://openalex.org/W2963826681","https://openalex.org/W2964099675","https://openalex.org/W4294170691","https://openalex.org/W4320013936","https://openalex.org/W6639480849","https://openalex.org/W6682691769","https://openalex.org/W6684191040","https://openalex.org/W6696757691","https://openalex.org/W6713969595","https://openalex.org/W6732862412","https://openalex.org/W6745117592","https://openalex.org/W6755207826"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W4246396837","https://openalex.org/W2482350142","https://openalex.org/W3176240006","https://openalex.org/W3126451824","https://openalex.org/W1561927205","https://openalex.org/W3191453585","https://openalex.org/W4297672492","https://openalex.org/W4288019534","https://openalex.org/W4310988119"],"abstract_inverted_index":{"As":[0],"one":[1],"of":[2,18],"the":[3,16,93,106,129,134],"major":[4],"sources":[5],"in":[6,149,164],"speech":[7,19,33,103],"variability,":[8],"accents":[9,126,151],"have":[10],"posed":[11],"a":[12,30,46],"grand":[13],"challenge":[14],"to":[15,28],"robustness":[17],"recognition":[20,34],"systems.":[21],"In":[22,105],"this":[23,42],"paper,":[24],"our":[25,108],"goal":[26],"is":[27,110],"build":[29],"unified":[31],"end-to-end":[32],"system":[35],"that":[36,128],"generalizes":[37],"well":[38],"across":[39],"accents.":[40],"For":[41],"purpose,":[43],"we":[44],"propose":[45],"novel":[47],"pre-training":[48],"framework":[49],"AIPNetbased":[50],"on":[51,78,123,142],"generative":[52],"adversarial":[53,76],"nets":[54],"(GAN)":[55],"for":[56,81,101],"accent-invariant":[57,68,94],"representation":[58],"learning:":[59],"Accent":[60],"Invariant":[61],"Pre-training":[62],"Networks.":[63],"We":[64,88],"pre-train":[65],"AIPNetto":[66],"disentangle":[67],"and":[69,118,152],"accent-specific":[70],"characteristics":[71],"from":[72],"acoustic":[73],"features":[74],"through":[75],"training":[77],"accented":[79],"data":[80],"which":[82],"transcriptions":[83,146,160],"are":[84,147,161],"not":[85],"necessarily":[86],"available.":[87],"further":[89],"fine-tune":[90],"AIPNetby":[91],"connecting":[92],"module":[95],"with":[96],"an":[97],"attention-based":[98],"encoder-decoder":[99],"model":[100],"multi-accent":[102],"recognition.":[104],"experiments,":[107],"approach":[109,131],"compared":[111],"against":[112],"four":[113],"baselines":[114,135],"including":[115],"both":[116],"accent-dependent":[117],"accent-independent":[119],"models.":[120],"Experimental":[121],"results":[122],"9":[124],"English":[125],"show":[127],"proposed":[130],"outperforms":[132],"all":[133,150],"by":[136,153],"2.3":[137],"~":[138,155],"4.5%":[139],"relative":[140,157],"reduction":[141,158],"average":[143],"WER":[144],"when":[145,159],"available":[148,163],"1.6":[154],"6.1%":[156],"only":[162],"US":[165],"accent.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}