{"id":"https://openalex.org/W3116323437","doi":"https://doi.org/10.1109/ictc49870.2020.9289283","title":"GAN-based Augmentation for Populating Speech Dataset with High Fidelity Synthesized Audio","display_name":"GAN-based Augmentation for Populating Speech Dataset with High Fidelity Synthesized Audio","publication_year":2020,"publication_date":"2020-10-21","ids":{"openalex":"https://openalex.org/W3116323437","doi":"https://doi.org/10.1109/ictc49870.2020.9289283","mag":"3116323437"},"language":"en","primary_location":{"id":"doi:10.1109/ictc49870.2020.9289283","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictc49870.2020.9289283","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Conference on Information and Communication Technology Convergence (ICTC)","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/A5001906335","display_name":"Moon-Ki Back","orcid":"https://orcid.org/0000-0001-7695-970X"},"institutions":[{"id":"https://openalex.org/I196345858","display_name":"Chungnam National University","ror":"https://ror.org/0227as991","country_code":"KR","type":"education","lineage":["https://openalex.org/I196345858"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Moon-Ki Back","raw_affiliation_strings":["Chungnam National University, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"Chungnam National University, Daejeon, South Korea","institution_ids":["https://openalex.org/I196345858"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080421614","display_name":"Seungwon Yoon","orcid":"https://orcid.org/0000-0003-1366-6920"},"institutions":[{"id":"https://openalex.org/I196345858","display_name":"Chungnam National University","ror":"https://ror.org/0227as991","country_code":"KR","type":"education","lineage":["https://openalex.org/I196345858"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seung-Won Yoon","raw_affiliation_strings":["Chungnam National University, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"Chungnam National University, Daejeon, South Korea","institution_ids":["https://openalex.org/I196345858"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027905802","display_name":"Kyu-Chul Lee","orcid":"https://orcid.org/0000-0003-0857-807X"},"institutions":[{"id":"https://openalex.org/I196345858","display_name":"Chungnam National University","ror":"https://ror.org/0227as991","country_code":"KR","type":"education","lineage":["https://openalex.org/I196345858"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyu-Chul Lee","raw_affiliation_strings":["Chungnam National University, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"Chungnam National University, Daejeon, South Korea","institution_ids":["https://openalex.org/I196345858"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5001906335"],"corresponding_institution_ids":["https://openalex.org/I196345858"],"apc_list":null,"apc_paid":null,"fwci":0.1515,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.46649111,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1267","last_page":"1269"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9983999729156494,"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":0.9864000082015991,"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/high-fidelity","display_name":"High fidelity","score":0.7912386655807495},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7728631496429443},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.6871402263641357},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5289961099624634},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5138504505157471},{"id":"https://openalex.org/keywords/harmonic","display_name":"Harmonic","score":0.4667259752750397},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.42413803935050964},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4201662242412567},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4168747663497925},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.20535767078399658},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10458657145500183}],"concepts":[{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.7912386655807495},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7728631496429443},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.6871402263641357},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5289961099624634},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5138504505157471},{"id":"https://openalex.org/C127934551","wikidata":"https://www.wikidata.org/wiki/Q1148098","display_name":"Harmonic","level":2,"score":0.4667259752750397},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.42413803935050964},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4201662242412567},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4168747663497925},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.20535767078399658},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10458657145500183},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ictc49870.2020.9289283","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictc49870.2020.9289283","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Conference on Information and Communication Technology Convergence (ICTC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.44999998807907104,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2163605009","https://openalex.org/W2173520492","https://openalex.org/W2194775991","https://openalex.org/W2797583228","https://openalex.org/W2893749619","https://openalex.org/W2910577860","https://openalex.org/W2950299304","https://openalex.org/W2952716587","https://openalex.org/W2962760235","https://openalex.org/W2963185411","https://openalex.org/W2963684088","https://openalex.org/W2963804063","https://openalex.org/W2963981733","https://openalex.org/W2990706204","https://openalex.org/W4294643831","https://openalex.org/W4297817572","https://openalex.org/W4301206121","https://openalex.org/W6684191040","https://openalex.org/W6685352114","https://openalex.org/W6745560452","https://openalex.org/W6750665317","https://openalex.org/W6751990271","https://openalex.org/W6755257315","https://openalex.org/W6755312952","https://openalex.org/W6758675244","https://openalex.org/W6765779288","https://openalex.org/W6770622103"],"related_works":["https://openalex.org/W4313443006","https://openalex.org/W2945374968","https://openalex.org/W4385452045","https://openalex.org/W4293777179","https://openalex.org/W2164070813","https://openalex.org/W2135608140","https://openalex.org/W2895525995","https://openalex.org/W4224231624","https://openalex.org/W1546240199","https://openalex.org/W2332512904"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"present":[4],"an":[5],"audio":[6,12,43],"augmentation":[7],"method":[8,49],"that":[9,23],"generates":[10],"synthetic":[11],"using":[13],"Generative":[14],"Adversarial":[15],"Networks":[16],"(GANs).":[17],"We":[18],"propose":[19],"a":[20,53],"training":[21],"strategy":[22],"first":[24],"uses":[25],"Harmonic":[26],"Percussive":[27],"Source":[28],"Separation":[29],"(HPSS)":[30],"to":[31],"extract":[32],"spectral":[33],"features":[34],"and":[35],"then":[36],"improves":[37],"the":[38,41,65,79],"fidelity":[39],"of":[40],"synthesized":[42],"by":[44,58,68],"applying":[45],"progressively-growing":[46],"GANs.":[47],"Our":[48],"is":[50],"demonstrated":[51],"on":[52],"public":[54],"speech":[55],"dataset":[56],"released":[57],"Google":[59],"TensorFlow.":[60],"When":[61],"employing":[62],"our":[63],"method,":[64],"performance":[66],"evaluated":[67],"Fr\u00e8chet":[69],"Inception":[70],"Distance":[71],"(FID)":[72],"showed":[73],"12.514,":[74],"but":[75],"14.012":[76],"as":[77],"for":[78],"existing":[80],"image-generating":[81],"GANs":[82],"(lower":[83],"FID":[84],"indicates":[85],"better":[86],"fidelity).":[87]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}