{"id":"https://openalex.org/W4205888775","doi":"https://doi.org/10.23919/eusipco54536.2021.9616247","title":"A Fast and Lightweight Text-To-Speech Model with Spectrum and Waveform Alignment Algorithms","display_name":"A Fast and Lightweight Text-To-Speech Model with Spectrum and Waveform Alignment Algorithms","publication_year":2021,"publication_date":"2021-08-23","ids":{"openalex":"https://openalex.org/W4205888775","doi":"https://doi.org/10.23919/eusipco54536.2021.9616247"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco54536.2021.9616247","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616247","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","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":"2021 29th European Signal Processing Conference (EUSIPCO)","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/A5027281603","display_name":"Kihyuk Jeong","orcid":null},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Kihyuk Jeong","raw_affiliation_strings":["Dept. of EE, DSP&AI Lab., Yonsei University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Dept. of EE, DSP&AI Lab., Yonsei University, Seoul, Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036538832","display_name":"Huu-Kim Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Huu-Kim Nguyen","raw_affiliation_strings":["Dept. of EE, DSP&AI Lab., Yonsei University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Dept. of EE, DSP&AI Lab., Yonsei University, Seoul, Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056128107","display_name":"Hong-Goo Kang","orcid":"https://orcid.org/0000-0002-6554-0783"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hong-Goo Kang","raw_affiliation_strings":["Dept. of EE, DSP&AI Lab., Yonsei University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Dept. of EE, DSP&AI Lab., Yonsei University, Seoul, Korea","institution_ids":["https://openalex.org/I193775966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5027281603"],"corresponding_institution_ids":["https://openalex.org/I193775966"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19115723,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"41","last_page":"45"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10860","display_name":"Speech 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/T11309","display_name":"Music and Audio Processing","score":0.9975000023841858,"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/waveform","display_name":"Waveform","score":0.8586878180503845},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8320267200469971},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.6617098450660706},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6054589748382568},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5425934791564941},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5397430658340454},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.4957352578639984},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4617272913455963},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4254198968410492},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39451390504837036}],"concepts":[{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.8586878180503845},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8320267200469971},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.6617098450660706},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6054589748382568},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5425934791564941},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5397430658340454},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.4957352578639984},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4617272913455963},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4254198968410492},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39451390504837036},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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/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/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","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/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco54536.2021.9616247","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616247","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","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":"2021 29th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.699999988079071,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2519091744","https://openalex.org/W2531409750","https://openalex.org/W2593414223","https://openalex.org/W2767052532","https://openalex.org/W2786868129","https://openalex.org/W2903739847","https://openalex.org/W2946200149","https://openalex.org/W2963300588","https://openalex.org/W2963975282","https://openalex.org/W2964243274","https://openalex.org/W2970006822","https://openalex.org/W2996286887","https://openalex.org/W3015338123","https://openalex.org/W3033411150","https://openalex.org/W3092028330","https://openalex.org/W4287761884","https://openalex.org/W4294619240","https://openalex.org/W6753855596","https://openalex.org/W6763832098","https://openalex.org/W6767111847","https://openalex.org/W6768435317","https://openalex.org/W6778823374","https://openalex.org/W6779337556","https://openalex.org/W6783867762","https://openalex.org/W6843673214"],"related_works":["https://openalex.org/W4293202849","https://openalex.org/W1980965563","https://openalex.org/W1489300767","https://openalex.org/W2387995142","https://openalex.org/W4380714744","https://openalex.org/W4319453655","https://openalex.org/W2089959425","https://openalex.org/W2530685530","https://openalex.org/W2897924318","https://openalex.org/W2138997758"],"abstract_inverted_index":{"In":[0,133],"this":[1,153],"paper,":[2],"we":[3,27,117,140],"propose":[4,118],"a":[5,46,119],"fast":[6,64],"and":[7,65,130,172],"lightweight":[8],"text-to-speech":[9],"(TTS)":[10],"model":[11,44,184],"that":[12,123,177,188],"generates":[13],"high-quality":[14],"speech":[15],"even":[16],"in":[17,45,107],"CPU-only":[18],"environments.":[19],"By":[20],"leveraging":[21],"the":[22,42,51,66,78,82,96,101,104,108,113,128,136,164,168,178,182],"front-end":[23],"architecture":[24],"of":[25,55,68,94,103,181,189],"FastSpeech2,":[26],"adopt":[28],"an":[29,142],"effective":[30],"generative":[31],"adversarial":[32],"network":[33,69],"(GAN)":[34],"framework":[35],"for":[36,158],"waveform":[37,52,84,120,137],"synthesis,":[38],"which":[39,99],"enables":[40],"training":[41],"proposed":[43,183],"fully":[47],"end-to-end":[48],"manner.":[49],"Since":[50,152],"generator":[53],"consists":[54],"small-size":[56],"convolutional":[57],"networks,":[58],"its":[59],"inference":[60,169],"speed":[61],"is":[62,155,185],"tremendously":[63],"number":[67],"parameters":[70],"can":[71],"be":[72],"reduced":[73],"by":[74],"half":[75],"compared":[76],"to":[77,135,147,187],"FastSpeech2":[79],"model.":[80],"However,":[81],"generated":[83,131],"segments":[85],"are":[86],"often":[87],"not":[88,162],"time-aligned":[89],"with":[90],"reference":[91,129],"ones":[92],"because":[93],"utilizing":[95],"predicted":[97],"duration,":[98],"reduces":[100],"reliability":[102],"discriminator":[105],"module":[106],"GAN":[109],"framework.":[110],"To":[111],"solve":[112],"time":[114],"mis-alignment":[115],"problem,":[116],"alignment":[121],"algorithm":[122],"synchronizes":[124],"timing":[125],"information":[126],"between":[127],"waveforms.":[132],"addition":[134],"aligning":[138],"task,":[139],"include":[141],"auxiliary":[143],"mel-spectrogram":[144],"prediction":[145],"task":[146,154],"further":[148],"enhance":[149],"perceptual":[150],"quality.":[151],"only":[156],"required":[157],"training,":[159],"it":[160],"does":[161],"increase":[163],"computational":[165],"complexity":[166],"during":[167],"stage.":[170],"Objective":[171],"subjective":[173],"experimental":[174],"results":[175],"show":[176],"synthesized":[179],"quality":[180],"comparable":[186],"conventional":[190],"approaches.":[191]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}