{"id":"https://openalex.org/W4416252109","doi":"https://doi.org/10.1109/waspaa66052.2025.11230979","title":"Diffused Responsibility: Analyzing the Energy Consumption of Generative Text-to-Audio Diffusion Models","display_name":"Diffused Responsibility: Analyzing the Energy Consumption of Generative Text-to-Audio Diffusion Models","publication_year":2025,"publication_date":"2025-10-12","ids":{"openalex":"https://openalex.org/W4416252109","doi":"https://doi.org/10.1109/waspaa66052.2025.11230979"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa66052.2025.11230979","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230979","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.univ-lorraine.fr/hal-05468351","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120499620","display_name":"Riccardo Passoni","orcid":null},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Riccardo Passoni","raw_affiliation_strings":["Informazione e Bioingegneria - Politecnico di Milano,Dipartimento di Elettronica,Milan,Italy"],"affiliations":[{"raw_affiliation_string":"Informazione e Bioingegneria - Politecnico di Milano,Dipartimento di Elettronica,Milan,Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056089196","display_name":"Francesca Ronchini","orcid":"https://orcid.org/0000-0001-6897-1645"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Francesca Ronchini","raw_affiliation_strings":["Informazione e Bioingegneria - Politecnico di Milano,Dipartimento di Elettronica,Milan,Italy"],"affiliations":[{"raw_affiliation_string":"Informazione e Bioingegneria - Politecnico di Milano,Dipartimento di Elettronica,Milan,Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007911573","display_name":"Luca Comanducci","orcid":"https://orcid.org/0000-0002-4167-5173"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Luca Comanducci","raw_affiliation_strings":["Informazione e Bioingegneria - Politecnico di Milano,Dipartimento di Elettronica,Milan,Italy"],"affiliations":[{"raw_affiliation_string":"Informazione e Bioingegneria - Politecnico di Milano,Dipartimento di Elettronica,Milan,Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Romain Serizel","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Romain Serizel","raw_affiliation_strings":["Universit&#x00E9; de Lorraine,CNRS, Inria, Loria,Nancy,France"],"affiliations":[{"raw_affiliation_string":"Universit&#x00E9; de Lorraine,CNRS, Inria, Loria,Nancy,France","institution_ids":["https://openalex.org/I4210121838","https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082156387","display_name":"Fabio Antonacci","orcid":"https://orcid.org/0000-0003-4545-0315"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Fabio Antonacci","raw_affiliation_strings":["Informazione e Bioingegneria - Politecnico di Milano,Dipartimento di Elettronica,Milan,Italy"],"affiliations":[{"raw_affiliation_string":"Informazione e Bioingegneria - Politecnico di Milano,Dipartimento di Elettronica,Milan,Italy","institution_ids":["https://openalex.org/I93860229"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5120499620"],"corresponding_institution_ids":["https://openalex.org/I93860229"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.4186571,"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":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.3497999906539917,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.3497999906539917,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.2190999984741211,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0640999972820282,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.7301999926567078},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6960999965667725},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5917999744415283},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.5849000215530396},{"id":"https://openalex.org/keywords/consumption","display_name":"Consumption (sociology)","score":0.5846999883651733},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.47290000319480896},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4311000108718872}],"concepts":[{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.7301999926567078},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6960999965667725},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5952000021934509},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5917999744415283},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.5849000215530396},{"id":"https://openalex.org/C30772137","wikidata":"https://www.wikidata.org/wiki/Q5164762","display_name":"Consumption (sociology)","level":2,"score":0.5846999883651733},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.47290000319480896},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4311000108718872},{"id":"https://openalex.org/C2777423268","wikidata":"https://www.wikidata.org/wiki/Q3663116","display_name":"Energy balance","level":2,"score":0.40230000019073486},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.3628000020980835},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.352400004863739},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3441999852657318},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.3287000060081482},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.3246000111103058},{"id":"https://openalex.org/C2776035688","wikidata":"https://www.wikidata.org/wiki/Q1606558","display_name":"Affect (linguistics)","level":2,"score":0.31360000371932983},{"id":"https://openalex.org/C168031717","wikidata":"https://www.wikidata.org/wiki/Q1530280","display_name":"Balance (ability)","level":2,"score":0.25699999928474426}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/waspaa66052.2025.11230979","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230979","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-05468351v1","is_oa":true,"landing_page_url":"https://hal.univ-lorraine.fr/hal-05468351","pdf_url":null,"source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, Oct 2025, Granlibakken Tahoe, United States","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-05468351v1","is_oa":true,"landing_page_url":"https://hal.univ-lorraine.fr/hal-05468351","pdf_url":null,"source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, Oct 2025, Granlibakken Tahoe, United States","raw_type":"Conference papers"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2593116425","https://openalex.org/W2931364255","https://openalex.org/W2945761034","https://openalex.org/W3015591594","https://openalex.org/W3041148953","https://openalex.org/W3081168214","https://openalex.org/W3164703200","https://openalex.org/W3214897310","https://openalex.org/W4372260244","https://openalex.org/W4372266552","https://openalex.org/W4375869067","https://openalex.org/W4387195417","https://openalex.org/W4387969125","https://openalex.org/W4392902957","https://openalex.org/W4392904573","https://openalex.org/W4396833556","https://openalex.org/W4396877837","https://openalex.org/W4399450035","https://openalex.org/W4402553617","https://openalex.org/W4405741747","https://openalex.org/W4408345930","https://openalex.org/W4413720412"],"related_works":[],"abstract_inverted_index":{"Text-to-audio":[0],"models":[1],"have":[2],"recently":[3],"emerged":[4],"as":[5],"a":[6],"powerful":[7],"technology":[8],"for":[9],"generating":[10],"sound":[11],"from":[12],"textual":[13],"descriptions.":[14],"However,":[15],"their":[16],"high":[17],"computational":[18],"demands":[19],"raise":[20],"concerns":[21],"about":[22],"energy":[23,37,55,72],"consumption":[24,56,73],"and":[25,71,91],"environmental":[26,92],"impact.":[27],"In":[28],"this":[29],"paper,":[30],"we":[31],"conduct":[32],"an":[33,65],"analysis":[34],"of":[35,39,98],"the":[36,87,96],"usage":[38],"7":[40],"state-of-the-art":[41],"text-to-audio":[42],"diffusion-based":[43],"generative":[44,101],"models,":[45],"evaluating":[46],"to":[47,63,95],"what":[48],"extent":[49],"variations":[50],"in":[51],"generation":[52],"parameters":[53],"affect":[54],"at":[57],"inference":[58],"time.":[59],"We":[60],"also":[61],"aim":[62],"identify":[64],"optimal":[66],"balance":[67],"between":[68,89],"audio":[69,102],"quality":[70],"by":[74],"considering":[75],"Pareto-optimal":[76],"solutions":[77],"across":[78],"all":[79],"selected":[80],"models.":[81,103],"Our":[82],"findings":[83],"provide":[84],"insights":[85],"into":[86],"trade-offs":[88],"performance":[90],"impact,":[93],"contributing":[94],"development":[97],"more":[99],"efficient":[100]},"counts_by_year":[],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-11-14T00:00:00"}
