{"id":"https://openalex.org/W4406858817","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10848687","title":"PPHiFi-TTS: Phonetic Preserved High-Fidelity Text-to-Speech for Long-Term Speech Dependencies","display_name":"PPHiFi-TTS: Phonetic Preserved High-Fidelity Text-to-Speech for Long-Term Speech Dependencies","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4406858817","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10848687"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc63619.2025.10848687","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10848687","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5114974321","display_name":"Ravindrakumar M. Purohit","orcid":null},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani University","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ravindrakumar M. Purohit","raw_affiliation_strings":["Research Lab,DAIICT,Gandhinagar,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Lab,DAIICT,Gandhinagar,India","institution_ids":["https://openalex.org/I98389781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116046393","display_name":"Dharmendra H. Vaghera","orcid":null},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani University","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Dharmendra H. Vaghera","raw_affiliation_strings":["Research Lab,DAIICT,Gandhinagar,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Lab,DAIICT,Gandhinagar,India","institution_ids":["https://openalex.org/I98389781"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Arth J. Shah","orcid":null},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani University","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Arth J. Shah","raw_affiliation_strings":["Research Lab,DAIICT,Gandhinagar,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Lab,DAIICT,Gandhinagar,India","institution_ids":["https://openalex.org/I98389781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113880393","display_name":"Hemant A. Patil","orcid":null},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani University","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Hemant A. Patil","raw_affiliation_strings":["Research Lab,DAIICT,Gandhinagar,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Lab,DAIICT,Gandhinagar,India","institution_ids":["https://openalex.org/I98389781"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98389781"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29365339,"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":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.988099992275238,"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/T12031","display_name":"Speech and dialogue systems","score":0.988099992275238,"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":0.9839000105857849,"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":0.9682000279426575,"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":0.782913327217102},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.7325880527496338},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.729308545589447},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.5775081515312195},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5378984212875366},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.48781684041023254},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4557002782821655},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43771928548812866},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4195539057254791},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.08600282669067383},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.04462301731109619}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.782913327217102},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.7325880527496338},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.729308545589447},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.5775081515312195},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5378984212875366},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.48781684041023254},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4557002782821655},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43771928548812866},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4195539057254791},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.08600282669067383},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.04462301731109619},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc63619.2025.10848687","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10848687","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":15,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1975163393","https://openalex.org/W2903739847","https://openalex.org/W2963300588","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W3015338123","https://openalex.org/W4200300291","https://openalex.org/W4224612669","https://openalex.org/W6765987481","https://openalex.org/W6767111847","https://openalex.org/W6767273955","https://openalex.org/W6772349387","https://openalex.org/W6778823374","https://openalex.org/W6783867762"],"related_works":["https://openalex.org/W4313443006","https://openalex.org/W2945374968","https://openalex.org/W4293777179","https://openalex.org/W4385452045","https://openalex.org/W2164070813","https://openalex.org/W2135608140","https://openalex.org/W2895525995","https://openalex.org/W2332512904","https://openalex.org/W4224231624","https://openalex.org/W2319626700"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"TTS":[3,64,140],"models":[4],"have":[5,37],"significantly":[6],"improved":[7],"the":[8,21,28,32,39,43,48,52,63,67,72,81,86,95,101,117,123,127],"quality":[9,83],"of":[10,23,47,114,129],"synthesized":[11,134],"speech,":[12],"making":[13],"it":[14],"more":[15],"natural-sounding":[16],"and":[17,75,84,99,120],"intelligible,":[18],"particularly":[19],"with":[20,66,116,122],"interaction":[22],"neural":[24,29],"network-based":[25],"models.":[26],"Further,":[27],"vocoders-based":[30],"on":[31],"Generative":[33],"Adversarial":[34],"Networks":[35],"(GANs)":[36],"shown":[38],"potential":[40],"to":[41,79,137],"generate":[42],"raw":[44],"speech":[45,103,135],"waveform":[46],"unseen":[49],"speaker":[50],"in":[51,131],"natural":[53],"style.":[54],"We":[55],"introduce":[56],"a":[57,109],"novel":[58],"architecture":[59],"PPHiFiGAN,":[60],"by":[61],"combining":[62],"model":[65,130],"HiFi-GAN":[68],"phoneme":[69],"vocoder,":[70],"where":[71],"Generator":[73],"(G),":[74],"Discriminator":[76],"(D)":[77],"aim":[78],"enhance":[80],"synthesis":[82],"capture":[85],"in-depth":[87],"phonetic":[88],"nuances":[89],"from":[90],"thedictionary.":[91],"This":[92],"approach":[93],"preserves":[94],"fine":[96],"gradient":[97],"details":[98],"captures":[100],"long-term":[102],"characteristics.":[104],"Our":[105],"proposed":[106,138],"method":[107],"attained":[108],"Mean":[110],"Opinion":[111],"Score":[112],"(MOS)":[113],"4.23":[115],"LJSpeech":[118],"recipe":[119],"4.05":[121],"VCTK":[124],"recipe,":[125],"demonstrating":[126],"effectiveness":[128],"generating":[132],"high-quality":[133],"relative":[136],"existing":[139],"architectures.":[141]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}