{"id":"https://openalex.org/W4416799503","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249114","title":"An Enhanced Probabilistic Approach for Singfake Generation","display_name":"An Enhanced Probabilistic Approach for Singfake Generation","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799503","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249114"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249114","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249114","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":"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":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":["Dhirubhai Ambani University (DAU),Speech Research Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dhirubhai Ambani University (DAU),Speech Research Lab","institution_ids":["https://openalex.org/I98389781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088207165","display_name":"A.K. Pandey","orcid":"https://orcid.org/0000-0001-6033-2822"},"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":"Aniket Pandey","raw_affiliation_strings":["Dhirubhai Ambani University (DAU),Speech Research Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dhirubhai Ambani University (DAU),Speech Research Lab","institution_ids":["https://openalex.org/I98389781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110351238","display_name":"S. Tiwari","orcid":null},"institutions":[{"id":"https://openalex.org/I172427033","display_name":"Sarah Cannon Research Institute","ror":"https://ror.org/03cp5cj42","country_code":"GB","type":"education","lineage":["https://openalex.org/I172427033"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Satyam R. Tiwari","raw_affiliation_strings":["Sarvajanik College of Engineering and Technology (SCET)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sarvajanik College of Engineering and Technology (SCET)","institution_ids":["https://openalex.org/I172427033"]}]},{"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dhirubhai Ambani University (DAU),Speech Research Lab","institution_ids":["https://openalex.org/I98389781"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.3454139,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2086","last_page":"2091"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.37779998779296875,"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":0.37779998779296875,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.11540000140666962,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.11320000141859055,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.5785999894142151},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.5785999894142151},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.559499979019165},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.476500004529953},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.4618000090122223},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.4577000141143799},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4205000102519989},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.4072999954223633},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.4016000032424927},{"id":"https://openalex.org/keywords/wavelet","display_name":"Wavelet","score":0.36570000648498535}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.5785999894142151},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.5785999894142151},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5605999827384949},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.559499979019165},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4977000057697296},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.476500004529953},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.4618000090122223},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.4577000141143799},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45750001072883606},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4205000102519989},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.4072999954223633},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.4016000032424927},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.36570000648498535},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.36070001125335693},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.32739999890327454},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.32170000672340393},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.319599986076355},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.31380000710487366},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.31189998984336853},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.310699999332428},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.30320000648498535},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.29660001397132874},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2867000102996826},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.2822999954223633},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2773999869823456},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.2732999920845032},{"id":"https://openalex.org/C178009071","wikidata":"https://www.wikidata.org/wiki/Q93344","display_name":"Trigonometric functions","level":2,"score":0.2732999920845032},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.2685999870300293},{"id":"https://openalex.org/C174576160","wikidata":"https://www.wikidata.org/wiki/Q1183700","display_name":"Deconvolution","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.2542000114917755},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.25360000133514404},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249114","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249114","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":12,"referenced_works":["https://openalex.org/W1965555277","https://openalex.org/W2042970394","https://openalex.org/W2407508591","https://openalex.org/W3096831136","https://openalex.org/W3158762648","https://openalex.org/W3207340675","https://openalex.org/W4385728838","https://openalex.org/W4392908976","https://openalex.org/W4398159307","https://openalex.org/W4402112070","https://openalex.org/W4406859898","https://openalex.org/W4409852345"],"related_works":[],"abstract_inverted_index":{"This":[0],"work":[1],"proposes":[2],"an":[3,141],"enhanced":[4],"probabilistic":[5],"framework":[6],"for":[7,178],"singing":[8,30,80,180],"voice":[9],"deepfake":[10,181],"generation":[11,126],"using":[12],"Variational":[13],"Autoencoders":[14],"(VAEs)":[15],"augmented":[16],"with":[17,89,130,140],"Kolmogorov-Arnold":[18],"Network":[19],"(KAN)":[20],"variants.":[21],"The":[22,133],"goal":[23],"is":[24],"to":[25,65,116],"generate":[26],"highfidelity":[27],"and":[28,36,55,57,100,108,128,145,157,166,175,183],"controllable":[29],"voices":[31],"by":[32],"disentangling":[33],"singer":[34],"identity":[35],"acoustic":[37],"content":[38],"in":[39,160],"the":[40,67,70,86,117,161],"latent":[41,71,173],"space.":[42],"We":[43],"explore":[44],"multiple":[45],"KAN-based":[46],"bottleneck":[47,162],"architectures\u2014B-Spline":[48],"Radial":[49],"Basis":[50],"Function":[51],"(BSRBF)":[52],"KAN,":[53],"Chebyshev-KAN,":[54],"WaveletKAN(WavKAN)\u2014with":[56],"without":[58],"Gaussian":[59],"Error":[60],"Linear":[61],"Unit":[62],"(GELU)":[63],"activation,":[64],"improve":[66,163],"expressiveness":[68],"of":[69,79,143],"representation.":[72],"Experiments":[73],"conducted":[74],"on":[75],"Mel":[76,92],"spectrogram":[77],"representations":[78],"audio":[81],"reveals":[82],"that":[83,155],"WavKANGELU":[84],"achieves":[85],"best":[87],"performance,":[88],"relatively":[90],"lowest":[91],"Cepstral":[93],"Distortion":[94,98],"(15.25),":[95],"Mean":[96],"Spectral":[97],"(0.065),":[99],"high":[101],"correlation":[102,120,146],"($\\mathbf{0.":[103,111],"9":[104,112,113,148,150],"4":[105],"3":[106,149],"6}$)":[107],"cosine":[109],"similarity":[110],"3}$).":[114],"Compared":[115],"baseline$\\text{VAE}(\\text{MCD}=21.75,":[118],"\\text{MSD}=0.108$,":[119],"=":[121],"0.846),":[122],"WavKAN-GELU":[123],"significantly":[124],"enhances":[125],"quality":[127],"alignment":[129],"real":[131],"data.":[132],"BSRBF-KAN-GELU":[134],"variant":[135],"also":[136],"shows":[137],"competitive":[138],"results":[139,153],"MCD":[142],"17.91,":[144],"of$\\mathbf{0.":[147],"9}$.":[151],"These":[152],"demonstrate":[154],"wavelet":[156],"polynomial-based":[158],"nonlinearities":[159],"both":[164],"reconstruction":[165],"generative":[167],"capabilities.":[168],"Our":[169],"model":[170],"supports":[171],"interpretable":[172],"control":[174],"opens":[176],"avenues":[177],"robust":[179],"synthesis":[182],"detection.":[184]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-28T00:00:00"}