{"id":"https://openalex.org/W4417402858","doi":"https://doi.org/10.1109/is264627.2025.11284630","title":"An Octave-based Multi-Resolution CQT Architecture for Diffusion-based Audio Generation","display_name":"An Octave-based Multi-Resolution CQT Architecture for Diffusion-based Audio Generation","publication_year":2025,"publication_date":"2025-10-29","ids":{"openalex":"https://openalex.org/W4417402858","doi":"https://doi.org/10.1109/is264627.2025.11284630"},"language":"en","primary_location":{"id":"doi:10.1109/is264627.2025.11284630","is_oa":false,"landing_page_url":"https://doi.org/10.1109/is264627.2025.11284630","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 6th International Symposium on the Internet of Sounds (IS2)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.1109/IS264627.2025.11284630","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021177130","display_name":"Maur\u00edcio do V. M. da Costa","orcid":null},"institutions":[{"id":"https://openalex.org/I170658231","display_name":"Osnabr\u00fcck University","ror":"https://ror.org/04qmmjx98","country_code":"DE","type":"education","lineage":["https://openalex.org/I170658231"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Maur\u00edcio do V. M. da Costa","raw_affiliation_strings":["University of Osnabr&#x00FC;ck,MTDML, IMM,Osnabr&#x00FC;ck,Germany"],"affiliations":[{"raw_affiliation_string":"University of Osnabr&#x00FC;ck,MTDML, IMM,Osnabr&#x00FC;ck,Germany","institution_ids":["https://openalex.org/I170658231"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030929567","display_name":"Eloi Moliner","orcid":"https://orcid.org/0000-0001-5719-326X"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Eloi Moliner","raw_affiliation_strings":["Aalto University,Acoustics Lab, DICE,Espoo,Finland"],"affiliations":[{"raw_affiliation_string":"Aalto University,Acoustics Lab, DICE,Espoo,Finland","institution_ids":["https://openalex.org/I9927081"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5021177130"],"corresponding_institution_ids":["https://openalex.org/I170658231"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.40833426,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.4018000066280365,"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"}},"topics":[{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.4018000066280365,"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":0.21889999508857727,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.05299999937415123,"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/metric","display_name":"Metric (unit)","score":0.6050999760627747},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5400000214576721},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.36959999799728394},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.3449000120162964},{"id":"https://openalex.org/keywords/digital-audio","display_name":"Digital audio","score":0.3095000088214874},{"id":"https://openalex.org/keywords/performance-metric","display_name":"Performance metric","score":0.3066999912261963}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7821000218391418},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6050999760627747},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5400000214576721},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4973999857902527},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4058000147342682},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.36959999799728394},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3449000120162964},{"id":"https://openalex.org/C87687168","wikidata":"https://www.wikidata.org/wiki/Q173114","display_name":"Digital audio","level":4,"score":0.3095000088214874},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.3066999912261963},{"id":"https://openalex.org/C98025372","wikidata":"https://www.wikidata.org/wiki/Q477538","display_name":"Systems architecture","level":3,"score":0.29170000553131104},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.2849000096321106},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.28040000796318054},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C96442724","wikidata":"https://www.wikidata.org/wiki/Q242188","display_name":"Invertible matrix","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.2515999972820282}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/is264627.2025.11284630","is_oa":false,"landing_page_url":"https://doi.org/10.1109/is264627.2025.11284630","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 6th International Symposium on the Internet of Sounds (IS2)","raw_type":"proceedings-article"},{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/141830","is_oa":true,"landing_page_url":"https://doi.org/10.1109/IS264627.2025.11284630","pdf_url":null,"source":{"id":"https://openalex.org/S4306401663","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"acceptedVersion"}],"best_oa_location":{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/141830","is_oa":true,"landing_page_url":"https://doi.org/10.1109/IS264627.2025.11284630","pdf_url":null,"source":{"id":"https://openalex.org/S4306401663","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"acceptedVersion"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320882","display_name":"Volkswagen Foundation","ror":"https://ror.org/03bsmfz84"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0,37],"paper":[1],"introduces":[2],"MR-CQTdiff,":[3],"a":[4,14],"novel":[5],"neural-network":[6],"architecture":[7,21],"for":[8],"diffusion-based":[9],"audio":[10,54,80],"generation":[11],"that":[12,28,76],"leverages":[13],"multi-resolution":[15],"Constant-Q":[16],"Transform":[17],"(CQT).":[18],"The":[19],"proposed":[20],"employs":[22],"an":[23,34,58],"efficient,":[24],"invertible":[25],"CQT":[26],"framework":[27],"adjusts":[29],"the":[30,40,61],"time-frequency":[31],"resolution":[32,45],"on":[33],"octave-by-octave":[35],"basis.":[36],"design":[38],"addresses":[39],"issue":[41],"of":[42],"low":[43],"temporal":[44],"at":[46],"lower":[47],"frequencies,":[48],"enabling":[49],"more":[50],"flexible":[51],"and":[52,70],"expressive":[53],"generation.":[55],"We":[56],"conduct":[57],"evaluation":[59],"using":[60],"Fr\u00e9chet":[62],"Audio":[63],"Distance":[64],"(FAD)":[65],"metric":[66],"across":[67],"various":[68],"architectures":[69],"two":[71],"datasets.":[72],"Experimental":[73],"results":[74],"demonstrate":[75],"MR-CQTdiff":[77],"achieves":[78],"state-of-the-art":[79],"quality,":[81],"outperforming":[82],"competing":[83],"architectures.":[84]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-12-16T00:00:00"}
