{"id":"https://openalex.org/W3023137581","doi":"https://doi.org/10.1587/transinf.2019edl8183","title":"Orthogonal Gradient Penalty for Fast Training of Wasserstein GAN Based Multi-Task Autoencoder toward Robust Speech Recognition","display_name":"Orthogonal Gradient Penalty for Fast Training of Wasserstein GAN Based Multi-Task Autoencoder toward Robust Speech Recognition","publication_year":2020,"publication_date":"2020-04-30","ids":{"openalex":"https://openalex.org/W3023137581","doi":"https://doi.org/10.1587/transinf.2019edl8183","mag":"3023137581"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2019edl8183","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2019edl8183","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E103.D/5/E103.D_2019EDL8183/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/transinf/E103.D/5/E103.D_2019EDL8183/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112527030","display_name":"Chao-Yuan KAO","orcid":null},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Chao-Yuan KAO","raw_affiliation_strings":["School of Electrical Engineering, Korea University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Korea University","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100750094","display_name":"Sangwook Park","orcid":"https://orcid.org/0000-0002-6817-4846"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sangwook PARK","raw_affiliation_strings":["School of Electrical and Computer Engineering, Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110631591","display_name":"Alzahra Badi","orcid":null},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Alzahra BADI","raw_affiliation_strings":["School of Electrical Engineering, Korea University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Korea University","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102000970","display_name":"David K. Han","orcid":"https://orcid.org/0000-0001-5055-5408"},"institutions":[{"id":"https://openalex.org/I166416128","display_name":"DEVCOM Army Research Laboratory","ror":"https://ror.org/011hc8f90","country_code":"US","type":"government","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I166416128","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David K. HAN","raw_affiliation_strings":["US Army Research Laboratory (ARL)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"US Army Research Laboratory (ARL)","institution_ids":["https://openalex.org/I166416128"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026204977","display_name":"Hanseok Ko","orcid":"https://orcid.org/0000-0002-8744-4514"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hanseok KO","raw_affiliation_strings":["School of Electrical Engineering, Korea University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Korea University","institution_ids":["https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1521,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.4123402,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"E103.D","issue":"5","first_page":"1195","last_page":"1198"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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/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/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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/autoencoder","display_name":"Autoencoder","score":0.8835719227790833},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8633455038070679},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6552573442459106},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5887731909751892},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5603346228599548},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49009644985198975},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45089295506477356},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4486791491508484},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.29822027683258057}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8835719227790833},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8633455038070679},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6552573442459106},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5887731909751892},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5603346228599548},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49009644985198975},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45089295506477356},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4486791491508484},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.29822027683258057},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1587/transinf.2019edl8183","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2019edl8183","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E103.D/5/E103.D_2019EDL8183/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1587/transinf.2019edl8183","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2019edl8183","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E103.D/5/E103.D_2019EDL8183/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5600000023841858,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321373","display_name":"Korea University","ror":"https://ror.org/047dqcg40"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3023137581.pdf","grobid_xml":"https://content.openalex.org/works/W3023137581.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W114517082","https://openalex.org/W1815076433","https://openalex.org/W1973681148","https://openalex.org/W2015337779","https://openalex.org/W2044893557","https://openalex.org/W2290318471","https://openalex.org/W2405774341","https://openalex.org/W2605135824","https://openalex.org/W2746457594","https://openalex.org/W2774615752","https://openalex.org/W2787069756","https://openalex.org/W2787133659","https://openalex.org/W2790871512","https://openalex.org/W2807791502","https://openalex.org/W2892356933","https://openalex.org/W2962866211","https://openalex.org/W2963321191","https://openalex.org/W2963341071","https://openalex.org/W2963453742"],"related_works":["https://openalex.org/W3013693939","https://openalex.org/W2159052453","https://openalex.org/W2566616303","https://openalex.org/W3131327266","https://openalex.org/W4297051394","https://openalex.org/W2752972570","https://openalex.org/W2734887215","https://openalex.org/W2803255133","https://openalex.org/W2551249631","https://openalex.org/W3098003361"],"abstract_inverted_index":{"Performance":[0],"in":[1,8,83,95],"Automatic":[2],"Speech":[3],"Recognition":[4],"(ASR)":[5],"degrades":[6],"dramatically":[7],"noisy":[9,77],"environments.":[10],"To":[11],"alleviate":[12],"this":[13,38],"problem,":[14],"a":[15,42,63],"variety":[16],"of":[17],"deep":[18],"networks":[19,24,28],"based":[20],"on":[21],"convolutional":[22],"neural":[23,27],"and":[25,58,97,102,110],"recurrent":[26],"were":[29],"proposed":[30,89],"by":[31],"applying":[32],"L1":[33],"or":[34],"L2":[35],"loss.":[36],"In":[37],"Letter,":[39],"we":[40],"propose":[41],"new":[43],"orthogonal":[44],"gradient":[45],"penalty":[46],"(OGP)":[47],"method":[48],"for":[49],"Wasserstein":[50,84],"Generative":[51],"Adversarial":[52],"Networks":[53],"(WGAN)":[54],"applied":[55],"to":[56],"denoising":[57],"despeeching":[59],"models.":[60,112],"WGAN":[61],"integrates":[62],"multi-task":[64],"autoencoder":[65],"which":[66],"estimates":[67],"not":[68],"only":[69],"speech":[70],"features":[71,75,92],"but":[72],"also":[73],"noise":[74],"from":[76],"speech.":[78],"While":[79],"achieving":[80],"14.1%":[81],"improvement":[82],"distance":[85],"convergence":[86],"rate,":[87],"the":[88],"OGP":[90],"enhanced":[91],"are":[93],"tested":[94],"ASR":[96],"achieve":[98],"9.7%,":[99],"8.6%,":[100],"6.2%,":[101],"4.8%":[103],"WER":[104],"improvements":[105],"over":[106],"DDAE,":[107],"MTAE,":[108],"R-CED(CNN)":[109],"RNN":[111]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}