{"id":"https://openalex.org/W7140720424","doi":"https://doi.org/10.1109/iciis69028.2026.11450741","title":"Feature Conditioned Diffusion for Audio Generation","display_name":"Feature Conditioned Diffusion for Audio Generation","publication_year":2026,"publication_date":"2026-01-16","ids":{"openalex":"https://openalex.org/W7140720424","doi":"https://doi.org/10.1109/iciis69028.2026.11450741"},"language":null,"primary_location":{"id":"doi:10.1109/iciis69028.2026.11450741","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iciis69028.2026.11450741","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 19th International Conference on Industrial and Information Systems (ICIIS)","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":null,"display_name":"Shakthi Perera","orcid":null},"institutions":[{"id":"https://openalex.org/I111199411","display_name":"University of Peradeniya","ror":"https://ror.org/025h79t26","country_code":"LK","type":"education","lineage":["https://openalex.org/I111199411"]}],"countries":["LK"],"is_corresponding":true,"raw_author_name":"Shakthi Perera","raw_affiliation_strings":["University of Peradeniya,Dept. of Electrical and Electronic Eng.,Peradeniya,Sri Lanka"],"affiliations":[{"raw_affiliation_string":"University of Peradeniya,Dept. of Electrical and Electronic Eng.,Peradeniya,Sri Lanka","institution_ids":["https://openalex.org/I111199411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022774555","display_name":"Subhani Ranasinghe","orcid":"https://orcid.org/0000-0001-7420-8929"},"institutions":[{"id":"https://openalex.org/I111199411","display_name":"University of Peradeniya","ror":"https://ror.org/025h79t26","country_code":"LK","type":"education","lineage":["https://openalex.org/I111199411"]}],"countries":["LK"],"is_corresponding":false,"raw_author_name":"Sandunika Ranasinghe","raw_affiliation_strings":["University of Peradeniya,Dept. of Electrical and Electronic Eng.,Peradeniya,Sri Lanka"],"affiliations":[{"raw_affiliation_string":"University of Peradeniya,Dept. of Electrical and Electronic Eng.,Peradeniya,Sri Lanka","institution_ids":["https://openalex.org/I111199411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076732661","display_name":"Shiran Jayakody","orcid":"https://orcid.org/0000-0003-0077-3962"},"institutions":[{"id":"https://openalex.org/I111199411","display_name":"University of Peradeniya","ror":"https://ror.org/025h79t26","country_code":"LK","type":"education","lineage":["https://openalex.org/I111199411"]}],"countries":["LK"],"is_corresponding":false,"raw_author_name":"Senith Jayakody","raw_affiliation_strings":["University of Peradeniya,Dept. of Electrical and Electronic Eng.,Peradeniya,Sri Lanka"],"affiliations":[{"raw_affiliation_string":"University of Peradeniya,Dept. of Electrical and Electronic Eng.,Peradeniya,Sri Lanka","institution_ids":["https://openalex.org/I111199411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130718169","display_name":"Buwaneka Epakanda","orcid":null},"institutions":[{"id":"https://openalex.org/I111199411","display_name":"University of Peradeniya","ror":"https://ror.org/025h79t26","country_code":"LK","type":"education","lineage":["https://openalex.org/I111199411"]}],"countries":["LK"],"is_corresponding":false,"raw_author_name":"Buwaneka Epakanda","raw_affiliation_strings":["University of Peradeniya,Dept. of Electrical and Electronic Eng.,Peradeniya,Sri Lanka"],"affiliations":[{"raw_affiliation_string":"University of Peradeniya,Dept. of Electrical and Electronic Eng.,Peradeniya,Sri Lanka","institution_ids":["https://openalex.org/I111199411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122286365","display_name":"Roshan Godaliyadda","orcid":null},"institutions":[{"id":"https://openalex.org/I111199411","display_name":"University of Peradeniya","ror":"https://ror.org/025h79t26","country_code":"LK","type":"education","lineage":["https://openalex.org/I111199411"]}],"countries":["LK"],"is_corresponding":false,"raw_author_name":"Roshan Godaliyadda","raw_affiliation_strings":["University of Peradeniya,Dept. of Electrical and Electronic Eng.,Peradeniya,Sri Lanka"],"affiliations":[{"raw_affiliation_string":"University of Peradeniya,Dept. of Electrical and Electronic Eng.,Peradeniya,Sri Lanka","institution_ids":["https://openalex.org/I111199411"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108555949","display_name":"M. P. B. Ekanayake","orcid":null},"institutions":[{"id":"https://openalex.org/I111199411","display_name":"University of Peradeniya","ror":"https://ror.org/025h79t26","country_code":"LK","type":"education","lineage":["https://openalex.org/I111199411"]}],"countries":["LK"],"is_corresponding":false,"raw_author_name":"Mervyn Parakrama Ekanayake","raw_affiliation_strings":["University of Peradeniya,Dept. of Electrical and Electronic Eng.,Peradeniya,Sri Lanka"],"affiliations":[{"raw_affiliation_string":"University of Peradeniya,Dept. of Electrical and Electronic Eng.,Peradeniya,Sri Lanka","institution_ids":["https://openalex.org/I111199411"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I111199411"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.70282272,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"162","last_page":"167"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.29649999737739563,"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":0.29649999737739563,"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":0.2583000063896179,"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/T11309","display_name":"Music and Audio Processing","score":0.19499999284744263,"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/spectrogram","display_name":"Spectrogram","score":0.8913999795913696},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.7189000248908997},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6335999965667725},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5271000266075134},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.4909999966621399},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.4810999929904938},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.38909998536109924}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8913999795913696},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.7189000248908997},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6628999710083008},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6335999965667725},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5957000255584717},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5859000086784363},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5271000266075134},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.4909999966621399},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4810999929904938},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.38909998536109924},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.3634999990463257},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.3628000020980835},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3571000099182129},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.35109999775886536},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3409000039100647},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.32850000262260437},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27469998598098755},{"id":"https://openalex.org/C54926389","wikidata":"https://www.wikidata.org/wiki/Q7575188","display_name":"Spectral envelope","level":2,"score":0.2644999921321869}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iciis69028.2026.11450741","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iciis69028.2026.11450741","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 19th International Conference on Industrial and Information Systems (ICIIS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2042105302","https://openalex.org/W2076608692","https://openalex.org/W2103869314","https://openalex.org/W2164538846","https://openalex.org/W2964243274","https://openalex.org/W3158762648","https://openalex.org/W4210663539","https://openalex.org/W4313178214","https://openalex.org/W4372341905","https://openalex.org/W4396877837"],"related_works":[],"abstract_inverted_index":{"Audio":[0,91],"generation":[1,22],"has":[2],"taken":[3],"a":[4,35,122],"leap":[5],"forward":[6],"with":[7,23,42],"tools":[8],"that":[9,113],"recreate":[10],"sounds":[11],"using":[12,38],"spectral":[13],"data,":[14],"like":[15],"spectrograms.":[16,32],"State":[17],"of":[18,81],"the":[19,39,76,79,88],"art":[20],"audio":[21,127],"diffusion":[24],"models":[25],"is":[26],"typically":[27],"conditioned":[28],"only":[29],"on":[30,63,96,99,102],"Mel":[31,47,82],"We":[33],"explored":[34],"new":[36,124],"approach":[37,125],"DiffWave":[40],"model":[41],"conditioning":[43,119],"features":[44],"such":[45],"as":[46],"Frequency":[48],"Cepstral":[49],"Coefficients":[50],"(MFCCs),":[51],"Constant":[52],"Q":[53],"Transform":[54,57],"(CQT),":[55],"Karhunen-Lo\u00e8ve":[56],"(KLT),":[58],"and":[59,66,72,84,108],"their":[60],"combinations,":[61],"tested":[62,77],"LJSpeech,":[64,97],"ESC-50,":[65,100],"IRMAS":[67],"datasets":[68],"for":[69,126],"speech,":[70],"environmental,":[71],"music":[73],"synthesis.":[74],"Among":[75],"methods,":[78,120],"combination":[80],"spectrogram":[83,86],"CQT":[85],"achieved":[87],"lowest":[89],"Fr\u00e9chet":[90],"Distance":[92],"(FAD)":[93],"scores":[94],"(5.45":[95],"6.71":[98],"4.60":[101],"IRMAS)":[103],"while":[104],"maintaining":[105],"strong":[106],"precision":[107],"coverage.":[109],"Our":[110],"results":[111],"demonstrate":[112],"this":[114],"technique":[115],"significantly":[116],"outperforms":[117],"conventional":[118],"offering":[121],"promising":[123],"generation.":[128]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2026-03-27T00:00:00"}