{"id":"https://openalex.org/W4416799063","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249184","title":"LAPS-Diff: A Diffusion-Based Framework for Hindi Singing Voice Synthesis with Language Aware Prosody-Style Guided Learning","display_name":"LAPS-Diff: A Diffusion-Based Framework for Hindi Singing Voice Synthesis with Language Aware Prosody-Style Guided Learning","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799063","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249184"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249184","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249184","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5102798862","display_name":"Sandipan Dhar","orcid":"https://orcid.org/0000-0002-3606-6664"},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sandipan Dhar","raw_affiliation_strings":["Indian Institute of Technology Bombay,Department of Electrical Engineering,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Bombay,Department of Electrical Engineering,India","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100618536","display_name":"Mayank Gupta","orcid":"https://orcid.org/0000-0001-9035-9073"},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Mayank Gupta","raw_affiliation_strings":["Indian Institute of Technology Bombay,Department of Electrical Engineering,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Bombay,Department of Electrical Engineering,India","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084496610","display_name":"Preeti Rao","orcid":"https://orcid.org/0000-0002-2842-8450"},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Preeti Rao","raw_affiliation_strings":["Indian Institute of Technology Bombay,Department of Electrical Engineering,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Bombay,Department of Electrical Engineering,India","institution_ids":["https://openalex.org/I162827531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162827531"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17288505,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"944","last_page":"949"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.42340001463890076,"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":0.42340001463890076,"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/T11309","display_name":"Music and Audio Processing","score":0.30799999833106995,"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/T10863","display_name":"Voice and Speech Disorders","score":0.07639999687671661,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.7718999981880188},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.6545000076293945},{"id":"https://openalex.org/keywords/lyrics","display_name":"Lyrics","score":0.5558000206947327},{"id":"https://openalex.org/keywords/hindi","display_name":"Hindi","score":0.5095999836921692},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4553000032901764},{"id":"https://openalex.org/keywords/trigram","display_name":"Trigram","score":0.43939998745918274},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.42170000076293945},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.4043000042438507},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.38749998807907104}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7718999981880188},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7009000182151794},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.6545000076293945},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6535000205039978},{"id":"https://openalex.org/C2776436406","wikidata":"https://www.wikidata.org/wiki/Q602446","display_name":"Lyrics","level":2,"score":0.5558000206947327},{"id":"https://openalex.org/C519982507","wikidata":"https://www.wikidata.org/wiki/Q1568","display_name":"Hindi","level":2,"score":0.5095999836921692},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4553000032901764},{"id":"https://openalex.org/C137546455","wikidata":"https://www.wikidata.org/wiki/Q3213474","display_name":"Trigram","level":2,"score":0.43939998745918274},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.435699999332428},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.42170000076293945},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.4043000042438507},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38760000467300415},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.38749998807907104},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3303000032901764},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.31690001487731934},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.30959999561309814},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.3082999885082245},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2989000082015991},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2955999970436096},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.27549999952316284},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249184","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249184","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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":16,"referenced_works":["https://openalex.org/W2017388191","https://openalex.org/W2932319787","https://openalex.org/W3098557217","https://openalex.org/W3158762648","https://openalex.org/W3162538529","https://openalex.org/W3213618310","https://openalex.org/W4221153051","https://openalex.org/W4296068763","https://openalex.org/W4319586596","https://openalex.org/W4385570009","https://openalex.org/W4385823416","https://openalex.org/W4385823466","https://openalex.org/W4402112011","https://openalex.org/W4402112388","https://openalex.org/W4402905495","https://openalex.org/W4406794071"],"related_works":[],"abstract_inverted_index":{"The":[0],"field":[1],"of":[2,19,111,118,163,183],"Singing":[3],"Voice":[4],"Synthesis":[5],"(SVS)":[6],"has":[7],"seen":[8],"significant":[9],"advancements":[10],"in":[11,35,116],"recent":[12],"years":[13],"due":[14],"to":[15,75,97,106,131,141,168],"the":[16,107,112,143,161,164,169,184],"rapid":[17],"progress":[18],"diffusion-based":[20],"approaches.":[21],"However,":[22],"capturing":[23,103],"vocal":[24,119],"style,":[25],"genre-specific":[26],"pitch":[27,94,101,122],"inflections,":[28],"and":[29,51,70,78,92,100,109,121,128,134,152,172],"language-dependent":[30],"characteristics":[31],"remains":[32],"challenging,":[33],"particularly":[34,115],"low-resource":[36],"scenarios.":[37],"To":[38],"address":[39],"this,":[40],"we":[41,87,125,155],"propose":[42],"LAPS-Diff,":[43],"a":[44,52,66,89,93],"diffusion":[45],"model":[46,96,175],"integrated":[47],"with":[48],"language-aware":[49],"embeddings":[50,80],"vocal-style":[53],"guided":[54],"learning":[55],"mechanism,":[56],"specifically":[57],"designed":[58],"for":[59,81,176],"Bollywood":[60],"Hindi":[61,67],"singing":[62],"style.":[63],"We":[64],"curate":[65],"SVS":[68],"dataset":[69,179],"leverage":[71],"pre-trained":[72],"language":[73],"models":[74,130],"extract":[76,132],"word":[77],"phone-level":[79],"an":[82],"enriched":[83],"lyrics":[84],"representation.":[85],"Additionally,":[86],"incorporated":[88],"style":[90,99,120],"encoder":[91],"extraction":[95],"compute":[98],"losses,":[102],"features":[104],"essential":[105],"naturalness":[108],"expressiveness":[110],"synthesized":[113],"singing,":[114],"terms":[117],"variations.":[123],"Furthermore,":[124],"utilize":[126],"MERT":[127],"IndicWav2Vec":[129],"musical":[133],"contextual":[135],"embeddings,":[136],"serving":[137],"as":[138],"conditional":[139],"priors":[140],"refine":[142],"acoustic":[144],"feature":[145],"generation":[146],"process":[147],"further.":[148],"Based":[149],"on":[150],"objective":[151],"subjective":[153],"evaluations,":[154],"demonstrate":[156],"that":[157,180],"LAPS-Diff":[158],"significantly":[159],"improves":[160],"quality":[162],"generated":[165],"samples":[166],"compared":[167],"considered":[170],"baseline":[171],"state-of-the-art":[173],"(SOTA)":[174],"our":[177],"constrained":[178],"is":[181],"typical":[182],"low":[185],"resource":[186],"scenario.":[187]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-11-28T00:00:00"}