{"id":"https://openalex.org/W3184415155","doi":"https://doi.org/10.1109/taslp.2021.3098764","title":"Guided Generative Adversarial Neural Network for Representation Learning and Audio Generation Using Fewer Labelled Audio Data","display_name":"Guided Generative Adversarial Neural Network for Representation Learning and Audio Generation Using Fewer Labelled Audio Data","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3184415155","doi":"https://doi.org/10.1109/taslp.2021.3098764","mag":"3184415155"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2021.3098764","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3098764","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://eprints.usq.edu.au/43207/1/GGAN_final_submission__PROOF.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087783982","display_name":"Kazi Nazmul Haque","orcid":"https://orcid.org/0000-0001-8882-5194"},"institutions":[{"id":"https://openalex.org/I185523456","display_name":"University of Southern Queensland","ror":"https://ror.org/04sjbnx57","country_code":"AU","type":"education","lineage":["https://openalex.org/I185523456"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Kazi Nazmul Haque","raw_affiliation_strings":["University of Southern Queensland, Darling Heights, QLD, Australia"],"raw_orcid":"https://orcid.org/0000-0001-8882-5194","affiliations":[{"raw_affiliation_string":"University of Southern Queensland, Darling Heights, QLD, Australia","institution_ids":["https://openalex.org/I185523456"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080929578","display_name":"Rajib Rana","orcid":"https://orcid.org/0000-0002-0506-2409"},"institutions":[{"id":"https://openalex.org/I185523456","display_name":"University of Southern Queensland","ror":"https://ror.org/04sjbnx57","country_code":"AU","type":"education","lineage":["https://openalex.org/I185523456"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Rajib Rana","raw_affiliation_strings":["University of Southern Queensland, Darling Heights, QLD, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern Queensland, Darling Heights, QLD, Australia","institution_ids":["https://openalex.org/I185523456"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108050347","display_name":"Jiajun Liu","orcid":"https://orcid.org/0000-0002-5301-8314"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jiajun Liu","raw_affiliation_strings":["Distributed Sensing Systems Group, Data61, CSIRO Australia, Pullenvale, Queensland, Australia"],"raw_orcid":"https://orcid.org/0000-0002-5301-8314","affiliations":[{"raw_affiliation_string":"Distributed Sensing Systems Group, Data61, CSIRO Australia, Pullenvale, Queensland, Australia","institution_ids":["https://openalex.org/I1292875679","https://openalex.org/I42894916"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057910370","display_name":"John H. L. Hansen","orcid":"https://orcid.org/0000-0003-1382-9929"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Hansen","raw_affiliation_strings":["University of Texas at Dallas, Richardson, TX, USA"],"raw_orcid":"https://orcid.org/0000-0003-1382-9929","affiliations":[{"raw_affiliation_string":"University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090485343","display_name":"Nicholas Cummins","orcid":"https://orcid.org/0000-0002-1178-917X"},"institutions":[{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nicholas Cummins","raw_affiliation_strings":["King's College London, London, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King's College London, London, U.K","institution_ids":["https://openalex.org/I183935753"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040793194","display_name":"Carlos Busso","orcid":"https://orcid.org/0000-0002-4075-4072"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carlos Busso","raw_affiliation_strings":["University of Texas at Dallas, Richardson, TX, USA"],"raw_orcid":"https://orcid.org/0000-0002-4075-4072","affiliations":[{"raw_affiliation_string":"University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043060302","display_name":"Bj\u00f6rn W. Schuller","orcid":"https://orcid.org/0000-0002-6478-8699"},"institutions":[{"id":"https://openalex.org/I179225836","display_name":"University of Augsburg","ror":"https://ror.org/03p14d497","country_code":"DE","type":"education","lineage":["https://openalex.org/I179225836"]},{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["DE","GB"],"is_corresponding":false,"raw_author_name":"Bjorn Schuller","raw_affiliation_strings":["Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Augsburg, Germany","GLAM \u2013 Group on Language, Audio, and Music, Imperial College London, London, U.K"],"raw_orcid":"https://orcid.org/0000-0002-6478-8699","affiliations":[{"raw_affiliation_string":"Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]},{"raw_affiliation_string":"GLAM \u2013 Group on Language, Audio, and Music, Imperial College London, London, U.K","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5317,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.82475797,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":98},"biblio":{"volume":"29","issue":null,"first_page":"2575","last_page":"2590"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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/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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9962999820709229,"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/computer-science","display_name":"Computer science","score":0.7690948247909546},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6832329034805298},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6349359750747681},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5397658348083496},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5168531537055969},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.48191002011299133},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45568087697029114},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4238142967224121},{"id":"https://openalex.org/keywords/generative-adversarial-network","display_name":"Generative adversarial network","score":0.41093724966049194},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35330379009246826},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.29657864570617676}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7690948247909546},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6832329034805298},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6349359750747681},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5397658348083496},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5168531537055969},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.48191002011299133},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45568087697029114},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4238142967224121},{"id":"https://openalex.org/C2988773926","wikidata":"https://www.wikidata.org/wiki/Q25104379","display_name":"Generative adversarial network","level":3,"score":0.41093724966049194},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35330379009246826},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.29657864570617676},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/taslp.2021.3098764","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3098764","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:eprints.usq.edu.au:43207","is_oa":true,"landing_page_url":null,"pdf_url":"http://eprints.usq.edu.au/43207/1/GGAN_final_submission__PROOF.pdf","source":{"id":"https://openalex.org/S4306400692","display_name":"University of Southern Queensland ePrints (University of Southern Queensland)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I185523456","host_organization_name":"University of Southern Queensland","host_organization_lineage":["https://openalex.org/I185523456"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article (Commonwealth Reporting Category C)"},{"id":"pmh:oai:kclpure.kcl.ac.uk:publications/f2744f7a-8946-4e53-af77-5f1f970b2619","is_oa":false,"landing_page_url":"https://kclpure.kcl.ac.uk/portal/en/publications/f2744f7a-8946-4e53-af77-5f1f970b2619","pdf_url":null,"source":{"id":"https://openalex.org/S4306400216","display_name":"Research Portal (King's College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I183935753","host_organization_name":"King's College London","host_organization_lineage":["https://openalex.org/I183935753"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Haque, K N, Rana, R, Liu, J, Hansen, J H L, Cummins, N, Busso, C & Schuller, B W 2021, 'Guided Generative Adversarial Neural Network for Representation Learning and Audio Generation using Fewer Labelled Audio Data', IEEE/ACM Transactions on Audio Speech and Language Processing, vol. 29, 9492807, pp. 2575-2590. https://doi.org/10.1109/TASLP.2021.3098764","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:uni-augsburg.opus-bayern.de:88921","is_oa":false,"landing_page_url":"https://nbn-resolving.org/urn:nbn:de:bvb:384-opus4-889213","pdf_url":null,"source":{"id":"https://openalex.org/S4306400930","display_name":"OPUS (Augsburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119916105","host_organization_name":"Augsburg University","host_organization_lineage":["https://openalex.org/I119916105"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:eprints.usq.edu.au:43207","is_oa":true,"landing_page_url":null,"pdf_url":"http://eprints.usq.edu.au/43207/1/GGAN_final_submission__PROOF.pdf","source":{"id":"https://openalex.org/S4306400692","display_name":"University of Southern Queensland ePrints (University of Southern Queensland)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I185523456","host_organization_name":"University of Southern Queensland","host_organization_lineage":["https://openalex.org/I185523456"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article (Commonwealth Reporting Category C)"},"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3184415155.pdf"},"referenced_works_count":130,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1834627138","https://openalex.org/W1959608418","https://openalex.org/W2078179989","https://openalex.org/W2097117768","https://openalex.org/W2099471712","https://openalex.org/W2108598243","https://openalex.org/W2120847449","https://openalex.org/W2160473997","https://openalex.org/W2173520492","https://openalex.org/W2178768799","https://openalex.org/W2187089797","https://openalex.org/W2260602646","https://openalex.org/W2295707189","https://openalex.org/W2326925005","https://openalex.org/W2335728318","https://openalex.org/W2412320034","https://openalex.org/W2519091744","https://openalex.org/W2561826558","https://openalex.org/W2584032004","https://openalex.org/W2606176153","https://openalex.org/W2618553051","https://openalex.org/W2749812777","https://openalex.org/W2751205669","https://openalex.org/W2763421725","https://openalex.org/W2782980316","https://openalex.org/W2784918340","https://openalex.org/W2785325870","https://openalex.org/W2797583228","https://openalex.org/W2842511635","https://openalex.org/W2884805522","https://openalex.org/W2893749619","https://openalex.org/W2894295011","https://openalex.org/W2901997113","https://openalex.org/W2902070858","https://openalex.org/W2903538854","https://openalex.org/W2906424389","https://openalex.org/W2920684403","https://openalex.org/W2948467580","https://openalex.org/W2950662112","https://openalex.org/W2951310434","https://openalex.org/W2951974815","https://openalex.org/W2952716587","https://openalex.org/W2953469440","https://openalex.org/W2962760235","https://openalex.org/W2962770929","https://openalex.org/W2962896155","https://openalex.org/W2962914040","https://openalex.org/W2962927978","https://openalex.org/W2963041308","https://openalex.org/W2963226019","https://openalex.org/W2963237661","https://openalex.org/W2963250052","https://openalex.org/W2963306805","https://openalex.org/W2963373786","https://openalex.org/W2963480200","https://openalex.org/W2963569749","https://openalex.org/W2963609956","https://openalex.org/W2963684088","https://openalex.org/W2963782041","https://openalex.org/W2963975282","https://openalex.org/W2963981733","https://openalex.org/W2964243274","https://openalex.org/W2970006822","https://openalex.org/W2970241862","https://openalex.org/W2970893544","https://openalex.org/W2972667718","https://openalex.org/W2973049979","https://openalex.org/W2975414524","https://openalex.org/W2982039329","https://openalex.org/W2988736778","https://openalex.org/W2996286887","https://openalex.org/W2996889020","https://openalex.org/W2998249245","https://openalex.org/W3015338123","https://openalex.org/W3015734344","https://openalex.org/W3016181583","https://openalex.org/W3095118468","https://openalex.org/W3095950035","https://openalex.org/W3096891716","https://openalex.org/W3100270690","https://openalex.org/W3102342027","https://openalex.org/W3104557543","https://openalex.org/W3104866538","https://openalex.org/W3118608800","https://openalex.org/W3122318757","https://openalex.org/W3125709657","https://openalex.org/W3138521398","https://openalex.org/W3144035034","https://openalex.org/W4288594364","https://openalex.org/W4294568686","https://openalex.org/W4294619240","https://openalex.org/W4294643831","https://openalex.org/W4297808394","https://openalex.org/W4297817572","https://openalex.org/W4301206121","https://openalex.org/W4320013936","https://openalex.org/W6640963894","https://openalex.org/W6685352114","https://openalex.org/W6685777725","https://openalex.org/W6701655646","https://openalex.org/W6703116779","https://openalex.org/W6715501732","https://openalex.org/W6718140377","https://openalex.org/W6718379498","https://openalex.org/W6732429163","https://openalex.org/W6736723571","https://openalex.org/W6743338426","https://openalex.org/W6745245109","https://openalex.org/W6745560452","https://openalex.org/W6747733185","https://openalex.org/W6747899497","https://openalex.org/W6750665317","https://openalex.org/W6753855596","https://openalex.org/W6755257315","https://openalex.org/W6755312952","https://openalex.org/W6756197946","https://openalex.org/W6756663807","https://openalex.org/W6757068045","https://openalex.org/W6758708508","https://openalex.org/W6759880871","https://openalex.org/W6765052341","https://openalex.org/W6765779288","https://openalex.org/W6767111847","https://openalex.org/W6770514103","https://openalex.org/W6772230580","https://openalex.org/W6787972765","https://openalex.org/W6843673214","https://openalex.org/W6844194202","https://openalex.org/W7043259713"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W2888032422","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W2996316059","https://openalex.org/W2280377497","https://openalex.org/W4385421777","https://openalex.org/W3174044702","https://openalex.org/W3178813832","https://openalex.org/W4238433571"],"abstract_inverted_index":{"The":[0],"Generation":[1],"power":[2,34],"of":[3,25,35,111,140],"Generative":[4,93],"Adversarial":[5,94],"Neural":[6,95],"Networks":[7],"(GANs)":[8],"has":[9],"shown":[10],"great":[11],"promise":[12],"to":[13,30,37],"learn":[14,38,100],"representations":[15,102,149],"from":[16],"unlabelled":[17],"data":[18,113,142],"while":[19],"guided":[20],"by":[21],"a":[22,85,108,120,127],"small":[23,109],"amount":[24,110],"labelled":[26,112,141],"data.":[27],"We":[28],"aim":[29],"utilise":[31],"the":[32,151],"generation":[33],"GANs":[36,52],"Audio":[39],"Representations.":[40],"Most":[41],"existing":[42],"studies":[43,50],"are,":[44],"however,":[45],"focused":[46],"on":[47,60,119],"images.":[48],"Some":[49],"use":[51,67],"for":[53,68,76],"speech":[54,77,121],"generation,":[55],"but":[56],"they":[57],"are":[58,80],"conditioned":[59],"text":[61],"or":[62],"acoustic":[63],"features,":[64],"limiting":[65],"their":[66],"other":[69],"audio,":[70],"such":[71],"as":[72,114,143],"instruments,":[73],"and":[74,103,126],"even":[75],"where":[78],"transcripts":[79],"limited.":[81],"This":[82],"paper":[83],"proposes":[84],"novel":[86],"GAN-based":[87],"model":[88],"that":[89,136],"we":[90],"named":[91],"Guided":[92],"Network":[96],"(GGAN),":[97],"which":[98],"can":[99],"powerful":[101],"generate":[104],"good-quality":[105],"samples":[106],"using":[107,137],"guidance.":[115],"Experimental":[116],"results":[117],"based":[118],"[Speech":[122],"Command":[123],"Dataset":[124],"(S09)]":[125],"non-speech":[128],"[Musical":[129],"Instrument":[130],"Sound":[131],"dataset":[132,134],"(Nsyth)]":[133],"demonstrate":[135],"only":[138],"5%":[139],"guidance,":[144],"GGAN":[145],"learns":[146],"significantly":[147],"better":[148],"than":[150],"state-of-the-art":[152],"models.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}