{"id":"https://openalex.org/W3136786651","doi":"https://doi.org/10.1109/icassp39728.2021.9413703","title":"Fine-Tuning of Pre-Trained End-to-End Speech Recognition with Generative Adversarial Networks","display_name":"Fine-Tuning of Pre-Trained End-to-End Speech Recognition with Generative Adversarial Networks","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3136786651","doi":"https://doi.org/10.1109/icassp39728.2021.9413703","mag":"3136786651"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413703","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413703","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":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2103.13329","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006199508","display_name":"Akmal Haidar","orcid":null},"institutions":[{"id":"https://openalex.org/I4210115038","display_name":"Huawei Technologies (Canada)","ror":"https://ror.org/026venb53","country_code":"CA","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210115038"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Md. Akmal Haidar","raw_affiliation_strings":["Montreal Research Centre,Huawei Noah’s Ark Lab,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Montreal Research Centre,Huawei Noah’s Ark Lab,Canada","institution_ids":["https://openalex.org/I4210115038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028862918","display_name":"Mehdi Rezagholizadeh","orcid":"https://orcid.org/0000-0003-4014-6007"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]},{"id":"https://openalex.org/I4210115038","display_name":"Huawei Technologies (Canada)","ror":"https://ror.org/026venb53","country_code":"CA","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210115038"]}],"countries":["CA","CN"],"is_corresponding":false,"raw_author_name":"Mehdi Rezagholizadeh","raw_affiliation_strings":["Montreal Research Centre,Huawei Noah’s Ark Lab,Canada","Huawei#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Montreal Research Centre,Huawei Noah’s Ark Lab,Canada","institution_ids":["https://openalex.org/I4210115038"]},{"raw_affiliation_string":"Huawei#TAB#","institution_ids":["https://openalex.org/I2250955327"]}]}],"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":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6204","last_page":"6208"},"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":0.9993000030517578,"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/T11309","display_name":"Music and Audio Processing","score":0.9987999796867371,"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/discriminator","display_name":"Discriminator","score":0.9727630019187927},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8138565421104431},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5912418365478516},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.5687437653541565},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5629249215126038},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5298005938529968},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5289801359176636},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4648764133453369},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44959911704063416},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.42590415477752686},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.08705973625183105},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.061228662729263306}],"concepts":[{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.9727630019187927},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8138565421104431},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5912418365478516},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.5687437653541565},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5629249215126038},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5298005938529968},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5289801359176636},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4648764133453369},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44959911704063416},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42590415477752686},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.08705973625183105},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.061228662729263306},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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":5,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413703","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413703","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"},{"id":"pmh:oai:arXiv.org:2103.13329","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.13329","pdf_url":"https://arxiv.org/pdf/2103.13329","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":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3136786651","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2103.13329.pdf","pdf_url":null,"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":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2103.13329","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2103.13329","pdf_url":null,"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":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.17023/frh7-pr72","is_oa":true,"landing_page_url":"https://doi.org/10.17023/frh7-pr72","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Audiovisual"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2103.13329","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.13329","pdf_url":"https://arxiv.org/pdf/2103.13329","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":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7300000190734863,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3136786651.pdf","grobid_xml":"https://content.openalex.org/works/W3136786651.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W385466589","https://openalex.org/W1494198834","https://openalex.org/W1828163288","https://openalex.org/W1895481600","https://openalex.org/W2099471712","https://openalex.org/W2102113734","https://openalex.org/W2127141656","https://openalex.org/W2327501763","https://openalex.org/W2514741789","https://openalex.org/W2605135824","https://openalex.org/W2739748921","https://openalex.org/W2766210095","https://openalex.org/W2795050058","https://openalex.org/W2795935804","https://openalex.org/W2885185669","https://openalex.org/W2892356933","https://openalex.org/W2913851961","https://openalex.org/W2936774411","https://openalex.org/W2962760690","https://openalex.org/W2962780374","https://openalex.org/W2963250244","https://openalex.org/W2963341071","https://openalex.org/W2963362078","https://openalex.org/W2963400424","https://openalex.org/W2963403868","https://openalex.org/W2964201867","https://openalex.org/W2972389417","https://openalex.org/W2972818416","https://openalex.org/W2981857663","https://openalex.org/W2990205979","https://openalex.org/W2991213871","https://openalex.org/W2992632249","https://openalex.org/W2998814410","https://openalex.org/W3005078977","https://openalex.org/W3015974384","https://openalex.org/W3095189764","https://openalex.org/W3097649098","https://openalex.org/W3103005696","https://openalex.org/W6613206883","https://openalex.org/W6638749077","https://openalex.org/W6675365184","https://openalex.org/W6732249622","https://openalex.org/W6735913928","https://openalex.org/W6739901393","https://openalex.org/W6741832134","https://openalex.org/W6745905863","https://openalex.org/W6770506093","https://openalex.org/W6770655456","https://openalex.org/W6773579204","https://openalex.org/W6929019831"],"related_works":["https://openalex.org/W3163888473","https://openalex.org/W3147607624","https://openalex.org/W3137489363","https://openalex.org/W2913566369","https://openalex.org/W3105804405","https://openalex.org/W2804884650","https://openalex.org/W3155168732","https://openalex.org/W3168872064","https://openalex.org/W2992448548","https://openalex.org/W2903015118","https://openalex.org/W2952010730","https://openalex.org/W3182974804","https://openalex.org/W1504449689","https://openalex.org/W3095773170","https://openalex.org/W3097573669","https://openalex.org/W3186546663","https://openalex.org/W3198413388","https://openalex.org/W3094225009","https://openalex.org/W3131305672","https://openalex.org/W3081494755"],"abstract_inverted_index":{"Adversarial":[0],"training":[1,34],"of":[2,135,149],"end-to-end":[3],"(E2E)":[4],"ASR":[5,18,37,42,80,88,101,109,117,151,160],"systems":[6],"using":[7,39,82,168],"generative":[8],"adversarial":[9,171,188],"networks":[10],"(GAN)":[11],"has":[12,48],"recently":[13],"been":[14,50],"explored":[15],"for":[16,76],"low-resource":[17],"corpora.":[19],"GANs":[20],"help":[21],"to":[22,60,98,124],"learn":[23],"the":[24,83,87,100,104,108,116,129,133,136,147,150,154,158,166],"true":[25],"data":[26],"representation":[27],"through":[28],"a":[29,40,45,73,78,92,95],"two-player":[30],"min-max":[31],"game.":[32],"However,":[33],"an":[35,169],"E2E":[36],"model":[38,81,89,110,118,152,161],"large":[41],"corpus":[43],"with":[44],"GAN":[46,84,141],"framework":[47,75],"never":[49],"explored,":[51],"because":[52],"it":[53],"might":[54],"take":[55],"excessively":[56],"long":[57],"time":[58],"due":[59],"high-variance":[61],"gradient":[62],"updates":[63],"and":[64,94,131,185],"face":[65],"convergence":[66],"issues.":[67],"In":[68],"this":[69],"paper,":[70],"we":[71,113],"introduce":[72],"novel":[74],"fine-tuning":[77,155],"pre-trained":[79,159],"objective":[85],"where":[86],"acts":[90],"as":[91],"generator":[93],"discriminator":[96,130,137,167],"tries":[97],"distinguish":[99],"output":[102,119],"from":[103,128],"real":[105],"data.":[106],"Since":[107],"is":[111,162],"pre-trained,":[112],"hypothesize":[114],"that":[115,179],"(soft":[120],"distribution":[121],"vectors)":[122],"helps":[123],"get":[125],"higher":[126],"scores":[127],"makes":[132],"task":[134],"harder":[138],"within":[139],"our":[140,180],"framework,":[142],"which":[143],"in":[144,153],"turn":[145],"improves":[146],"performance":[148],"stage.":[156],"Here,":[157],"fine-tuned":[163],"adversarially":[164],"against":[165],"additional":[170],"loss.":[172],"Experiments":[173],"on":[174],"full":[175],"LibriSpeech":[176],"dataset":[177],"show":[178],"proposed":[181],"approach":[182],"outperforms":[183],"baselines":[184],"conventional":[186],"GAN-based":[187],"models.":[189]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}