{"id":"https://openalex.org/W4408354967","doi":"https://doi.org/10.1109/icassp49660.2025.10888129","title":"LEF-TTS: Lightweight and Efficient End-to-End Text-to-Speech Synthesis With Multi-Stream Generator","display_name":"LEF-TTS: Lightweight and Efficient End-to-End Text-to-Speech Synthesis With Multi-Stream Generator","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354967","doi":"https://doi.org/10.1109/icassp49660.2025.10888129"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888129","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888129","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5002110970","display_name":"Yan Shi","orcid":"https://orcid.org/0000-0002-6954-0537"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yan Shi","raw_affiliation_strings":["Ping An Technology,China"],"affiliations":[{"raw_affiliation_string":"Ping An Technology,China","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109693427","display_name":"Shi Jin","orcid":"https://orcid.org/0009-0002-2768-8143"},"institutions":[{"id":"https://openalex.org/I181679659","display_name":"Shanghai University of Finance and Economics","ror":"https://ror.org/00wtvfq62","country_code":"CN","type":"education","lineage":["https://openalex.org/I181679659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Shi","raw_affiliation_strings":["Shanghai University of Finance and Economics"],"affiliations":[{"raw_affiliation_string":"Shanghai University of Finance and Economics","institution_ids":["https://openalex.org/I181679659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059638789","display_name":"Minchuan Chen","orcid":"https://orcid.org/0009-0001-1512-6672"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minchuan Chen","raw_affiliation_strings":["Ping An Technology,China"],"affiliations":[{"raw_affiliation_string":"Ping An Technology,China","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093993569","display_name":"Chenfeng Miao","orcid":"https://orcid.org/0009-0006-1986-3035"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenfeng Miao","raw_affiliation_strings":["Ping An Technology,China"],"affiliations":[{"raw_affiliation_string":"Ping An Technology,China","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080919889","display_name":"Ming Fang","orcid":"https://orcid.org/0000-0003-1932-2037"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Fang","raw_affiliation_strings":["Ping An Technology,China"],"affiliations":[{"raw_affiliation_string":"Ping An Technology,China","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101977180","display_name":"Ning Cheng","orcid":"https://orcid.org/0000-0002-0988-5023"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ning Cheng","raw_affiliation_strings":["Ping An Technology,China"],"affiliations":[{"raw_affiliation_string":"Ping An Technology,China","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100702017","display_name":"Shaojun Wang","orcid":"https://orcid.org/0009-0001-8955-8566"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaojun Wang","raw_affiliation_strings":["Ping An Technology,China"],"affiliations":[{"raw_affiliation_string":"Ping An Technology,China","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016038454","display_name":"Jing Xiao","orcid":"https://orcid.org/0000-0001-9615-4749"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Xiao","raw_affiliation_strings":["Ping An Technology,China"],"affiliations":[{"raw_affiliation_string":"Ping An Technology,China","institution_ids":["https://openalex.org/I4401726822"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5002110970"],"corresponding_institution_ids":["https://openalex.org/I4401726822"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02074944,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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":0.9952999949455261,"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":0.9952999949455261,"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/T12031","display_name":"Speech and dialogue systems","score":0.9890999794006348,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9868000149726868,"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/end-to-end-principle","display_name":"End-to-end principle","score":0.7912696599960327},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7396231889724731},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.6891652941703796},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6353700160980225},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47674429416656494},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18722394108772278},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08681619167327881}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7912696599960327},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7396231889724731},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.6891652941703796},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6353700160980225},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47674429416656494},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18722394108772278},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08681619167327881},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888129","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888129","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2519091744","https://openalex.org/W2963300588","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W3095883095","https://openalex.org/W3160919572","https://openalex.org/W3162046328","https://openalex.org/W4210287297","https://openalex.org/W4319862711","https://openalex.org/W4372266896","https://openalex.org/W4372270423","https://openalex.org/W4385245566","https://openalex.org/W4386076493","https://openalex.org/W4391806982","https://openalex.org/W4392124090","https://openalex.org/W4402111690","https://openalex.org/W6610566761","https://openalex.org/W6640963894","https://openalex.org/W6731370813","https://openalex.org/W6753640285","https://openalex.org/W6757817989","https://openalex.org/W6763832098","https://openalex.org/W6767111847","https://openalex.org/W6778823374","https://openalex.org/W6783867762","https://openalex.org/W6796464841","https://openalex.org/W6796730497","https://openalex.org/W6811456798","https://openalex.org/W6838843145","https://openalex.org/W6853165267","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2151749779","https://openalex.org/W3179968364","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W2799713421","https://openalex.org/W4404782863"],"abstract_inverted_index":{"Recently,":[0],"the":[1,14,63,109,121,131],"field":[2],"of":[3,16,27,62,111,130],"Text-to-speech":[4,39],"synthesis":[5],"has":[6],"been":[7],"predominantly":[8],"characterized":[9],"by":[10,19],"end-to-end":[11,43],"models,":[12,133],"with":[13,49,57],"quality":[15,126],"speech":[17,125],"generated":[18],"these":[20],"models":[21],"becoming":[22],"increasingly":[23],"comparable":[24,127],"to":[25,81,128],"that":[26,120,129],"human":[28],"speech.":[29],"In":[30],"this":[31],"work,":[32],"we":[33,75],"propose":[34],"a":[35,41,58,77,90],"Lightweight":[36],"and":[37,71,86,103,114,140],"Efficient":[38],"model,":[40],"fast":[42],"framework":[44],"based":[45],"on":[46],"EfficientTTS":[47],"2":[48],"fully":[50],"differentiable.":[51],"We":[52],"utilize":[53],"Fast":[54],"Linear":[55],"Attention":[56],"Single":[59],"Head":[60],"instead":[61],"standard":[64],"stacked":[65],"Transformer,":[66],"which":[67],"decreases":[68],"computational":[69],"complexity":[70],"reduces":[72],"parameters.":[73],"Additionally,":[74],"improve":[76],"network":[78],"architecture":[79],"ConvWaveNet":[80],"further":[82],"decrease":[83],"model":[84,101,123,142],"parameters,":[85],"accelerate":[87],"inference":[88,105,113,138],"through":[89],"multi-stream":[91],"inverse":[92],"short-time":[93],"Fourier":[94],"Transform":[95],"generator.":[96],"These":[97],"improvements":[98],"significantly":[99],"reduce":[100],"parameters":[102],"increase":[104],"speed,":[106],"thereby":[107],"achieving":[108],"objectives":[110],"faster":[112],"lightweight":[115],"modeling.":[116],"Experimental":[117],"results":[118],"show":[119],"proposed":[122],"achieves":[124],"baseline":[132],"while":[134],"also":[135],"offering":[136],"improved":[137],"speed":[139],"reduced":[141],"size.":[143]},"counts_by_year":[],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}