{"id":"https://openalex.org/W4297841320","doi":"https://doi.org/10.21437/interspeech.2022-52","title":"A Multi-Scale Time-Frequency Spectrogram Discriminator for GAN-based Non-Autoregressive TTS","display_name":"A Multi-Scale Time-Frequency Spectrogram Discriminator for GAN-based Non-Autoregressive TTS","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4297841320","doi":"https://doi.org/10.21437/interspeech.2022-52"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-52","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-52","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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/A5072447806","display_name":"Haohan Guo","orcid":"https://orcid.org/0000-0002-3393-9984"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haohan Guo","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047322900","display_name":"Hui L\u00fc","orcid":"https://orcid.org/0000-0003-1640-239X"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Lu","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025119324","display_name":"Xixin Wu","orcid":"https://orcid.org/0000-0001-9543-1572"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xixin Wu","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5072447806"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":0.7372,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.71748926,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1566","last_page":"1570"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12131","display_name":"Wireless Signal Modulation Classification","score":0.5763999819755554,"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/T12131","display_name":"Wireless Signal Modulation Classification","score":0.5763999819755554,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.07559999823570251,"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/T10220","display_name":"Machine Fault Diagnosis Techniques","score":0.05649999901652336,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.9204779863357544},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.9132699966430664},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.7712002992630005},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5780611634254456},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5504388809204102},{"id":"https://openalex.org/keywords/time\u2013frequency-analysis","display_name":"Time\u2013frequency analysis","score":0.5264029502868652},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.440609335899353},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1727595329284668},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.14903226494789124},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.12845072150230408},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.11669909954071045}],"concepts":[{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.9204779863357544},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9132699966430664},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.7712002992630005},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5780611634254456},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5504388809204102},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.5264029502868652},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.440609335899353},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1727595329284668},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.14903226494789124},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12845072150230408},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.11669909954071045},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"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/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-52","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-52","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2120847449","https://openalex.org/W2284050935","https://openalex.org/W2746654391","https://openalex.org/W2903739847","https://openalex.org/W2946200149","https://openalex.org/W2963609956","https://openalex.org/W2963929654","https://openalex.org/W2963971656","https://openalex.org/W2964153283","https://openalex.org/W2964243274","https://openalex.org/W2970006822","https://openalex.org/W2994143516","https://openalex.org/W3026874504","https://openalex.org/W3033411150","https://openalex.org/W3035687950","https://openalex.org/W3092028330","https://openalex.org/W3161296985","https://openalex.org/W3197273793","https://openalex.org/W3197294703","https://openalex.org/W3198213150","https://openalex.org/W4287083773","https://openalex.org/W4287111234","https://openalex.org/W4288265053"],"related_works":["https://openalex.org/W1889291648","https://openalex.org/W2897924318","https://openalex.org/W2138997758","https://openalex.org/W2533590149","https://openalex.org/W335396218","https://openalex.org/W1504214173","https://openalex.org/W1600447354","https://openalex.org/W1589126043","https://openalex.org/W200102888","https://openalex.org/W2035480840"],"abstract_inverted_index":{"The":[0],"generative":[1],"adversarial":[2],"network":[3],"(GAN)":[4],"has":[5],"shown":[6,128],"its":[7],"outstanding":[8],"capability":[9],"in":[10,80,117],"improving":[11],"Non-Autoregressive":[12],"TTS":[13],"(NAR-TTS)":[14],"by":[15],"adversarially":[16],"training":[17],"it":[18,37,126],"with":[19],"an":[20],"extra":[21],"model":[22,86],"that":[23,45],"discriminates":[24],"between":[25],"the":[26,29,33,67,75,81,107,118,123,135,139,148],"real":[27],"and":[28,99,111,120,131],"generated":[30],"speech.To":[31],"maximize":[32],"benefits":[34],"of":[35,150],"GAN,":[36],"is":[38,88,127],"crucial":[39],"to":[40,60,73,90,95,105,142,146],"find":[41],"a":[42,55,70,84],"powerful":[43],"discriminator":[44,59],"can":[46],"capture":[47,96],"rich":[48],"distinguishable":[49],"information.In":[50],"this":[51],"paper,":[52],"we":[53,137],"propose":[54],"multi-scale":[56,110],"time-frequency":[57,82,112],"spectrogram":[58,68],"help":[61],"NAR-TTS":[62],"generate":[63],"high-fidelity":[64],"Mel-spectrograms.It":[65],"treats":[66],"as":[69],"2D":[71],"image":[72],"exploit":[74],"correlation":[76],"among":[77],"different":[78,93],"components":[79],"domain.And":[83],"U-Net-based":[85],"structure":[87],"employed":[89],"discriminate":[91],"at":[92],"scales":[94],"both":[97],"coarse-grained":[98],"fine-grained":[100],"information.We":[101],"conduct":[102],"subjective":[103],"tests":[104],"evaluate":[106],"proposed":[108],"approach.Both":[109],"discriminating":[113,140],"bring":[114],"significant":[115],"improvement":[116],"naturalness":[119],"fidelity.When":[121],"combining":[122],"neural":[124],"vocoder,":[125],"more":[129],"effective":[130],"concise":[132],"than":[133],"fine-tuning":[134],"vocoder.Finally,":[136],"visualize":[138],"maps":[141],"compare":[143],"their":[144],"difference":[145],"verify":[147],"effectiveness":[149],"multiscale":[151],"discriminating.":[152]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-03T08:47:05.690250","created_date":"2025-10-10T00:00:00"}