{"id":"https://openalex.org/W4385993937","doi":"https://doi.org/10.21437/ssw.2023-35","title":"Lightweight End-to-end Text-to-speech Synthesis for low resource on-device applications","display_name":"Lightweight End-to-end Text-to-speech Synthesis for low resource on-device applications","publication_year":2023,"publication_date":"2023-08-18","ids":{"openalex":"https://openalex.org/W4385993937","doi":"https://doi.org/10.21437/ssw.2023-35"},"language":"en","primary_location":{"id":"doi:10.21437/ssw.2023-35","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2023-35","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"12th ISCA Speech Synthesis Workshop (SSW2023)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.07701","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090303265","display_name":"Biel Tura Vecino","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Biel Tura Vecino","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031116817","display_name":"Adam Gabry\u015b","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Adam Gabrys","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092664378","display_name":"Daniel Matwicki","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel Matwicki","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092664379","display_name":"Andrzej Pomirski","orcid":"https://orcid.org/0009-0004-5526-4318"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrzej Pomirski","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092664380","display_name":"Tom Iddon","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tom Iddon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038640628","display_name":"Marius Cotescu","orcid":"https://orcid.org/0000-0001-7005-2920"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marius Cotescu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5019530089","display_name":"Jaime Lorenzo-Trueba","orcid":"https://orcid.org/0000-0003-0459-1429"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jaime Lorenzo-Trueba","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"225","last_page":"229"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12720","display_name":"Multimedia Communication and Technology","score":0.9438999891281128,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12720","display_name":"Multimedia Communication and Technology","score":0.9438999891281128,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9427000284194946,"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":0.9412000179290771,"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/computer-science","display_name":"Computer science","score":0.6670218706130981},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5477787852287292},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4397214949131012},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.2977783679962158},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.21423500776290894}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6670218706130981},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5477787852287292},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4397214949131012},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2977783679962158},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.21423500776290894}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/ssw.2023-35","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2023-35","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"12th ISCA Speech Synthesis Workshop (SSW2023)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.07701","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.07701","pdf_url":"https://arxiv.org/pdf/2505.07701","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.07701","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.07701","pdf_url":"https://arxiv.org/pdf/2505.07701","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385993937.pdf","grobid_xml":"https://content.openalex.org/works/W4385993937.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W3179968364","https://openalex.org/W2390279801","https://openalex.org/W3196421258","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2151749779","https://openalex.org/W2382290278","https://openalex.org/W2938107654"],"abstract_inverted_index":{"Recent":[0],"works":[1],"have":[2],"shown":[3],"that":[4,65,84,108,130],"modelling":[5],"raw":[6],"waveform":[7],"directly":[8],"from":[9],"text":[10],"in":[11,51,95,103,123],"an":[12,119],"end-to-end":[13],"(E2E)":[14],"fashion":[15],"produces":[16],"more":[17],"natural-sounding":[18],"speech":[19,68],"than":[20],"traditional":[21],"neural":[22],"text-to-speech":[23],"(TTS)":[24],"systems":[25],"based":[26],"on":[27,78],"a":[28,60,124,133],"cascade":[29],"or":[30],"two-stage":[31,125],"approach.":[32,126],"However,":[33],"current":[34],"E2E":[35,111],"state-of-the-art":[36,87],"models":[37],"are":[38],"computationally":[39],"complex":[40],"and":[41,82,100],"memory-consuming,":[42],"making":[43],"them":[44],"unsuitable":[45],"for":[46,136,144],"real-time":[47],"offline":[48],"on-device":[49,145],"applications":[50,143],"low-resource":[52,141],"scenarios.":[53],"To":[54],"address":[55],"this":[56],"issue,":[57],"we":[58,106],"propose":[59],"Lightweight":[61],"E2E-TTS":[62],"(LE2E)":[63],"model":[64,77,98],"generates":[66],"high-quality":[67],"requiring":[69],"minimal":[70],"computational":[71],"resources.":[72],"We":[73],"evaluate":[74],"the":[75,79,109],"proposed":[76,110],"LJSpeech":[80],"dataset":[81],"show":[83],"it":[85],"achieves":[86,114],"performance":[88],"while":[89],"being":[90],"up":[91],"to":[92,118],"$90\\%$":[93],"smaller":[94],"terms":[96],"of":[97],"parameters":[99],"$10\\times$":[101],"faster":[102],"real-time-factor.":[104],"Furthermore,":[105],"demonstrate":[107],"training":[112],"paradigm":[113],"better":[115],"quality":[116],"compared":[117],"equivalent":[120],"architecture":[121],"trained":[122],"Our":[127],"results":[128],"suggest":[129],"LE2E":[131],"is":[132],"promising":[134],"approach":[135],"developing":[137],"real-time,":[138],"high":[139],"quality,":[140],"TTS":[142],"applications.":[146]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}