{"id":"https://openalex.org/W4414231252","doi":"https://doi.org/10.1109/ialp68296.2024.11156272","title":"Swar (Hindi): A Speaker-Aware Vocoder for Low-Resource Speech Synthesis","display_name":"Swar (Hindi): A Speaker-Aware Vocoder for Low-Resource Speech Synthesis","publication_year":2025,"publication_date":"2025-08-03","ids":{"openalex":"https://openalex.org/W4414231252","doi":"https://doi.org/10.1109/ialp68296.2024.11156272"},"language":"en","primary_location":{"id":"doi:10.1109/ialp68296.2024.11156272","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ialp68296.2024.11156272","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":0.851142,"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":"141","last_page":"146"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.996999979019165,"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":0.996999979019165,"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":0.9959999918937683,"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/T12031","display_name":"Speech and dialogue systems","score":0.9631999731063843,"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/naturalness","display_name":"Naturalness","score":0.891700029373169},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.7717999815940857},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.679099977016449},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.6359999775886536},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.49390000104904175},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4332999885082245}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.891700029373169},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.7717999815940857},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7069000005722046},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.679099977016449},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.6359999775886536},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.621399998664856},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.49390000104904175},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4332999885082245},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.38679999113082886},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3619000017642975},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.34130001068115234},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.33180001378059387},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3131999969482422},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.29919999837875366},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.2897000014781952},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.28209999203681946}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ialp68296.2024.11156272","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ialp68296.2024.11156272","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":25,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1574447377","https://openalex.org/W1761875812","https://openalex.org/W1861172732","https://openalex.org/W1975163393","https://openalex.org/W1999885698","https://openalex.org/W2075170185","https://openalex.org/W2097645910","https://openalex.org/W2107860279","https://openalex.org/W2125838338","https://openalex.org/W2128704269","https://openalex.org/W2137075158","https://openalex.org/W2141998673","https://openalex.org/W2166469361","https://openalex.org/W2181715843","https://openalex.org/W2471520273","https://openalex.org/W2963300588","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W3015338123","https://openalex.org/W3097828251","https://openalex.org/W3147984406","https://openalex.org/W3161236344","https://openalex.org/W4297841531","https://openalex.org/W4301420498"],"related_works":[],"abstract_inverted_index":{"Hindi,":[0],"one":[1],"of":[2,66,77,134,155,179,183],"the":[3,137,176],"most":[4],"widely":[5],"spoken":[6],"languages,":[7],"is":[8,64],"considered":[9],"low-resource":[10,164,191],"for":[11,38],"speech":[12,71,142,160,188],"synthesis":[13,189],"(SS)":[14],"due":[15],"to":[16,50,118],"its":[17],"complex":[18],"phonetic":[19],"structure":[20],"and":[21,47,57,97,107,116,157,175,185],"limited":[22],"annotated":[23],"datasets.":[24],"In":[25],"this":[26],"paper,":[27],"we":[28],"propose":[29],"Swar":[30,40,62,120,127,166],"(Hindi),":[31],"a":[32,43,73,91,130,145],"speaker-aware":[33,48],"neural":[34],"vocoder":[35],"designed":[36],"specifically":[37],"Hindi.":[39],"(Hindi)":[41,63,128,167],"uses":[42],"prosodic":[44],"adaptation":[45],"mechanism":[46],"conditioning":[49],"address":[51],"challenges,":[52],"such":[53,110],"as":[54,111],"poor":[55],"generalisation":[56],"context-sensitive":[58],"pronunciation":[59],"in":[60,148,159,187],"prosody.":[61],"capable":[65],"generating":[67],"high-quality":[68],"22.05":[69],"kHz":[70],"with":[72],"GPU":[74],"inference":[75,95],"speed":[76],"6.53\u00d7":[78],"real-time":[79],"factor":[80],"(RTF)":[81],"on":[82],"an":[83],"NVIDIA":[84],"GTX":[85],"1080":[86],"8GB":[87],"VRAM":[88],"by":[89,139,151],"offering":[90],"practical":[92],"balance":[93],"between":[94],"quality":[96],"performance.":[98],"Generated":[99],"samples":[100],"evaluation":[101],"using":[102],"both":[103],"subjective":[104],"(MOS,":[105],"SMOS)":[106],"objective":[108],"metrics,":[109],"PCC,":[112],"PESQ,":[113],"STOI,":[114],"MSD,":[115],"MCD":[117],"evaluate":[119],"(Hindi)s'":[121],"effectiveness":[122],"over":[123,136],"baseline":[124,138],"GAN-based":[125],"vocoders.":[126],"achieved":[129,168],"MOS":[131,169],"score":[132,150,170,178],"improvement":[133],"+0.34":[135,171],"enhancing":[140],"overall":[141],"quality.":[143],"Additionally,":[144],"+0.14":[146,180],"gain":[147],"SMOS":[149,177],"showcasing":[152],"better":[153],"preservation":[154,182],"prosody":[156,184],"naturalness":[158,186],"synthesis,":[161],"even":[162],"under":[163,190],"constraints.":[165,192],"higher":[172],"than":[173],"baseline,":[174],"showed":[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"}