{"id":"https://openalex.org/W4414231080","doi":"https://doi.org/10.1109/ialp68296.2024.11156270","title":"Whether to Use Pretrain Neural Vocoders or Not?: An Empirical Analysis for Indic Speech Synthesis","display_name":"Whether to Use Pretrain Neural Vocoders or Not?: An Empirical Analysis for Indic Speech Synthesis","publication_year":2025,"publication_date":"2025-08-03","ids":{"openalex":"https://openalex.org/W4414231080","doi":"https://doi.org/10.1109/ialp68296.2024.11156270"},"language":"en","primary_location":{"id":"doi:10.1109/ialp68296.2024.11156270","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ialp68296.2024.11156270","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Asian Language Processing (IALP)","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":["Dhirubhai Ambani University (DAU),Speech Research Lab,Gandhinagar,GJ,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dhirubhai Ambani University (DAU),Speech Research Lab,Gandhinagar,GJ,India","institution_ids":["https://openalex.org/I98389781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043002276","display_name":"Hemant A. Patil","orcid":"https://orcid.org/0000-0002-4068-2005"},"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":["Dhirubhai Ambani University (DAU),Speech Research Lab,Gandhinagar,GJ,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dhirubhai Ambani University (DAU),Speech Research Lab,Gandhinagar,GJ,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":1.673,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85109025,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"123","last_page":"128"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9632999897003174,"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":0.9632999897003174,"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":0.9415000081062317,"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":0.9290000200271606,"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/intelligibility","display_name":"Intelligibility (philosophy)","score":0.7656999826431274},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4839000105857849},{"id":"https://openalex.org/keywords/pearson-product-moment-correlation-coefficient","display_name":"Pearson product-moment correlation coefficient","score":0.4659999907016754},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4537999927997589},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4043000042438507},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.4041999876499176},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.3889999985694885},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.35920000076293945}],"concepts":[{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7656999826431274},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7473000288009644},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6119999885559082},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4839000105857849},{"id":"https://openalex.org/C55078378","wikidata":"https://www.wikidata.org/wiki/Q1136628","display_name":"Pearson product-moment correlation coefficient","level":2,"score":0.4659999907016754},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46389999985694885},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4537999927997589},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4059999883174896},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4043000042438507},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.4041999876499176},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.3889999985694885},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.35920000076293945},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.3546999990940094},{"id":"https://openalex.org/C2780092901","wikidata":"https://www.wikidata.org/wiki/Q3433612","display_name":"Correlation coefficient","level":2,"score":0.335099995136261},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.3163999915122986},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.299699991941452},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.275299996137619},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.2639000117778778},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C3020001037","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assessment","level":3,"score":0.2549000084400177},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.25290000438690186}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ialp68296.2024.11156270","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ialp68296.2024.11156270","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Asian Language Processing (IALP)","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":23,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1574447377","https://openalex.org/W1761875812","https://openalex.org/W2049686551","https://openalex.org/W2107860279","https://openalex.org/W2137075158","https://openalex.org/W2141998673","https://openalex.org/W2152205330","https://openalex.org/W2318810473","https://openalex.org/W2471520273","https://openalex.org/W2519091744","https://openalex.org/W2798685342","https://openalex.org/W2963300588","https://openalex.org/W2972359262","https://openalex.org/W3015338123","https://openalex.org/W3095790275","https://openalex.org/W3097828251","https://openalex.org/W3144035034","https://openalex.org/W3196475561","https://openalex.org/W3197273793","https://openalex.org/W3205012673","https://openalex.org/W4240592325","https://openalex.org/W4319347033"],"related_works":[],"abstract_inverted_index":{"Existing":[0],"speech":[1,24,146],"synthesis":[2,25],"systems":[3,26],"are":[4],"developed":[5],"in":[6,21,62,119],"German,":[7],"Mandarin,":[8],"or":[9],"Japanese.":[10],"However,":[11],"languages,":[12],"such":[13,19,129],"as":[14,130],"Indic":[15,64,120,149],"and":[16,46,53,66,98,114,134,141,155,160,179],"African":[17],"lack":[18],"progress":[20],"building":[22],"robust":[23],"due":[27],"to":[28,33,109],"limited":[29],"low-resource":[30],"constraints":[31],"(compared":[32],"language":[34],"diversity).":[35],"Manually":[36],"creating":[37],"a":[38],"dataset":[39],"specifically":[40],"for":[41],"these":[42],"languages":[43,65],"is":[44],"time-consuming":[45],"costly.":[47],"This":[48],"paper":[49],"conducts":[50],"comprehensive":[51],"experiments":[52],"evaluations":[54],"of":[55,80,116,143],"eight":[56],"non-Indic":[57],"pre-trained":[58],"neural":[59],"vocoders":[60,153],"(PTNV)":[61],"six":[63],"four":[67],"dialects.":[68],"We":[69],"used":[70],"subjective":[71],"(NISQA":[72],"Mean":[73],"Opinion":[74],"Score":[75],"(MOS)),":[76],"objective":[77],"(Perceptual":[78],"Evaluation":[79],"Speech":[81],"Quality":[82],"(PESQ),":[83],"Mel-Cepstral":[84],"Distortion":[85],"(MCD),":[86],"Mel-Spectra":[87],"Distance":[88],"(MSD),":[89],"Short-Time":[90],"Objective":[91],"Intelligibility":[92],"(STOI),":[93],"Pearson":[94],"Correlation":[95],"Coefficient":[96],"(PCC))":[97],"quantitative":[99],"(Word":[100],"Error":[101,105],"Rate":[102,106],"(WER),":[103],"Character":[104],"(CER))":[107],"measures":[108],"assess":[110],"the":[111,139,144],"generalization":[112,159],"capabilities":[113,173],"performance":[115],"PTV":[117],"models":[118],"languages.":[121,150],"During":[122],"analysis,":[123],"we":[124],"noticed":[125],"that":[126],"architectural":[127,180],"features,":[128],"Multi-Receptive":[131],"Fields":[132],"(MRFs)":[133],"residual":[135],"blocks,":[136],"significantly":[137],"improved":[138],"quality":[140],"intelligibility":[142],"synthesized":[145],"across":[147],"diverse":[148],"In":[151],"particular,":[152],"HiFi-GAN":[154],"UnivNet":[156],"gave":[157],"superior":[158],"perceptual":[161],"quality,":[162],"despite":[163],"being":[164],"trained":[165],"on":[166],"non-indic":[167],"datasets.":[168],"Which":[169],"suggests":[170],"strong":[171],"cross-lingual":[172],"when":[174],"combined":[175],"with":[176],"proper":[177],"conditioning":[178],"robustness.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}