{"id":"https://openalex.org/W4375850690","doi":"https://doi.org/10.1109/icassp49357.2023.10095873","title":"MFCCGAN: A Novel MFCC-Based Speech Synthesizer Using Adversarial Learning","display_name":"MFCCGAN: A Novel MFCC-Based Speech Synthesizer Using Adversarial Learning","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375850690","doi":"https://doi.org/10.1109/icassp49357.2023.10095873"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095873","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095873","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2306.12785","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077137747","display_name":"Mohammad Reza Hasanabadi","orcid":null},"institutions":[{"id":"https://openalex.org/I48379061","display_name":"Shahid Beheshti University","ror":"https://ror.org/0091vmj44","country_code":"IR","type":"education","lineage":["https://openalex.org/I48379061"]}],"countries":["IR"],"is_corresponding":true,"raw_author_name":"Mohammad Reza Hasanabadi","raw_affiliation_strings":["Shahid Beheshti University,Tehran,Iran","Shahid Beheshti University, Tehran, Iran"],"affiliations":[{"raw_affiliation_string":"Shahid Beheshti University,Tehran,Iran","institution_ids":["https://openalex.org/I48379061"]},{"raw_affiliation_string":"Shahid Beheshti University, Tehran, Iran","institution_ids":["https://openalex.org/I48379061"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092336772","display_name":"Majid Behdad","orcid":null},"institutions":[{"id":"https://openalex.org/I48379061","display_name":"Shahid Beheshti University","ror":"https://ror.org/0091vmj44","country_code":"IR","type":"education","lineage":["https://openalex.org/I48379061"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Majid Behdad","raw_affiliation_strings":["Shahid Beheshti University,Tehran,Iran","Shahid Beheshti University, Tehran, Iran"],"affiliations":[{"raw_affiliation_string":"Shahid Beheshti University,Tehran,Iran","institution_ids":["https://openalex.org/I48379061"]},{"raw_affiliation_string":"Shahid Beheshti University, Tehran, Iran","institution_ids":["https://openalex.org/I48379061"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007426240","display_name":"Davood Gharavian","orcid":"https://orcid.org/0000-0002-8555-9342"},"institutions":[{"id":"https://openalex.org/I48379061","display_name":"Shahid Beheshti University","ror":"https://ror.org/0091vmj44","country_code":"IR","type":"education","lineage":["https://openalex.org/I48379061"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Davood Gharavian","raw_affiliation_strings":["Shahid Beheshti University,Tehran,Iran","Shahid Beheshti University, Tehran, Iran"],"affiliations":[{"raw_affiliation_string":"Shahid Beheshti University,Tehran,Iran","institution_ids":["https://openalex.org/I48379061"]},{"raw_affiliation_string":"Shahid Beheshti University, Tehran, Iran","institution_ids":["https://openalex.org/I48379061"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5077137747"],"corresponding_institution_ids":["https://openalex.org/I48379061"],"apc_list":null,"apc_paid":null,"fwci":0.8859,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.78344074,"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":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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/T11309","display_name":"Music and Audio Processing","score":0.9991999864578247,"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/intelligibility","display_name":"Intelligibility (philosophy)","score":0.8399208784103394},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7300658822059631},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6854954361915588},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6694441437721252},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.6446016430854797},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4354923665523529},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.41757437586784363},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4151727557182312},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34730082750320435},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.2548641562461853},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.06217232346534729}],"concepts":[{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.8399208784103394},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7300658822059631},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6854954361915588},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6694441437721252},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.6446016430854797},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4354923665523529},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.41757437586784363},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4151727557182312},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34730082750320435},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2548641562461853},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.06217232346534729},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095873","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095873","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2306.12785","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2306.12785","pdf_url":"https://arxiv.org/pdf/2306.12785","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2306.12785","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2306.12785","pdf_url":"https://arxiv.org/pdf/2306.12785","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.699999988079071,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4375850690.pdf","grobid_xml":"https://content.openalex.org/works/W4375850690.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W1560013842","https://openalex.org/W1567186732","https://openalex.org/W2108532241","https://openalex.org/W2120605154","https://openalex.org/W2121848673","https://openalex.org/W2129142580","https://openalex.org/W2141998673","https://openalex.org/W2151626637","https://openalex.org/W2154278880","https://openalex.org/W2191779130","https://openalex.org/W2292235217","https://openalex.org/W2423557781","https://openalex.org/W2426038346","https://openalex.org/W2471520273","https://openalex.org/W2519091744","https://openalex.org/W2593414223","https://openalex.org/W2752796333","https://openalex.org/W2765811365","https://openalex.org/W2774848319","https://openalex.org/W2775336875","https://openalex.org/W2783599290","https://openalex.org/W2791686384","https://openalex.org/W2807065297","https://openalex.org/W2910577860","https://openalex.org/W2937579788","https://openalex.org/W2949558265","https://openalex.org/W2963091184","https://openalex.org/W2963154580","https://openalex.org/W2963300588","https://openalex.org/W2963799213","https://openalex.org/W2970006822","https://openalex.org/W2991143265","https://openalex.org/W3098557217","https://openalex.org/W3124522394","https://openalex.org/W3196475561","https://openalex.org/W3215615641","https://openalex.org/W4298580827","https://openalex.org/W6696768431","https://openalex.org/W6746801104","https://openalex.org/W6748409065","https://openalex.org/W6758675244","https://openalex.org/W6762114000","https://openalex.org/W6767111847","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W2079655441","https://openalex.org/W2912293245","https://openalex.org/W4252942110","https://openalex.org/W1604114751","https://openalex.org/W2032941915","https://openalex.org/W2075706796","https://openalex.org/W4391272374","https://openalex.org/W4400309480","https://openalex.org/W2549308614","https://openalex.org/W2081919107"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"introduce":[4],"MFCCGAN":[5],"as":[6,18],"a":[7,37,49,91],"novel":[8],"speech":[9,23,32,40,53],"synthesizer":[10,41],"based":[11,47,129],"on":[12,48,130],"adversarial":[13],"learning":[14],"that":[15,64,110],"adopts":[16],"MFCCs":[17],"input":[19],"and":[20,57,82,90,98],"generates":[21],"raw":[22],"waveforms.":[24],"Benefiting":[25],"the":[26,45,113,134,142,145],"GAN":[27],"model":[28,46],"capabilities,":[29],"it":[30],"produces":[31],"with":[33,105],"higher":[34],"intelligibility":[35,54,97],"than":[36],"rule-based":[38,107],"MFCC-based":[39],"WORLD.":[42],"We":[43],"evaluated":[44],"popular":[50],"intrusive":[51],"objective":[52],"measure":[55],"(STOI)":[56],"quality":[58,135,143],"(NISQA":[59],"score).":[60],"Experimental":[61],"results":[62],"show":[63,141],"our":[65],"proposed":[66,146],"system":[67],"outperforms":[68],"Librosa":[69],"MFCC-inversion":[70],"(by":[71],"an":[72],"increase":[73],"of":[74,93,144],"about":[75,94,99],"26%":[76],"up":[77,84],"to":[78,85],"53%":[79],"in":[80,87,96,101,103,112,127],"STOI":[81,131],"16%":[83],"78%":[86],"NISQA":[88],"score)":[89],"rise":[92],"10%":[95],"4%":[100],"naturalness":[102],"comparison":[104],"conventional":[106],"vocoder":[108],"WORLD":[109,117],"used":[111],"CycleGAN-VC":[114],"family.":[115],"However,":[116],"needs":[118],"additional":[119],"data":[120],"like":[121],"F0.":[122],"Finally,":[123],"using":[124],"perceptual":[125],"loss":[126],"discriminators":[128],"could":[132],"improve":[133],"more.":[136],"WebMUSHRA-based":[137],"subjective":[138],"tests":[139],"also":[140],"approach.":[147]},"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":1}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2023-05-10T00:00:00"}