{"id":"https://openalex.org/W4410771589","doi":"https://doi.org/10.1109/icasspw65056.2025.11011113","title":"Mind the Prompt: Prompting Strategies in Audio Generations for Improving Sound Classification","display_name":"Mind the Prompt: Prompting Strategies in Audio Generations for Improving Sound Classification","publication_year":2025,"publication_date":"2025-04-06","ids":{"openalex":"https://openalex.org/W4410771589","doi":"https://doi.org/10.1109/icasspw65056.2025.11011113"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw65056.2025.11011113","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw65056.2025.11011113","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","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/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":["Politecnico di Milano,Dipartimento di Elettronica, Informazione e Bioingegneria (DEIB),Milano"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Milano,Dipartimento di Elettronica, Informazione e Bioingegneria (DEIB),Milano","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035643647","display_name":"Ho-Hsiang Wu","orcid":"https://orcid.org/0000-0002-1102-074X"},"institutions":[{"id":"https://openalex.org/I4210120115","display_name":"Robert Bosch (United States)","ror":"https://ror.org/02venad53","country_code":"US","type":"company","lineage":["https://openalex.org/I4210120115","https://openalex.org/I889804353"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ho-Hsiang Wu","raw_affiliation_strings":["Bosch Center for Artificial Intelligence,Pittsburgh,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bosch Center for Artificial Intelligence,Pittsburgh,USA","institution_ids":["https://openalex.org/I4210120115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070819601","display_name":"Wei-Cheng Lin","orcid":"https://orcid.org/0000-0003-1933-1590"},"institutions":[{"id":"https://openalex.org/I4210120115","display_name":"Robert Bosch (United States)","ror":"https://ror.org/02venad53","country_code":"US","type":"company","lineage":["https://openalex.org/I4210120115","https://openalex.org/I889804353"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei-Cheng Lin","raw_affiliation_strings":["Bosch Center for Artificial Intelligence,Pittsburgh,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bosch Center for Artificial Intelligence,Pittsburgh,USA","institution_ids":["https://openalex.org/I4210120115"]}]},{"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":["Politecnico di Milano,Dipartimento di Elettronica, Informazione e Bioingegneria (DEIB),Milano"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Milano,Dipartimento di Elettronica, Informazione e Bioingegneria (DEIB),Milano","institution_ids":["https://openalex.org/I93860229"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"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":0.11035911,"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":0.9817000031471252,"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":0.9817000031471252,"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":0.9592999815940857,"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/sound","display_name":"Sound (geography)","score":0.7651597261428833},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.605655312538147},{"id":"https://openalex.org/keywords/sound-recording-and-reproduction","display_name":"Sound recording and reproduction","score":0.5366525053977966},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4259750247001648},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4110589325428009},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3100205957889557},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.2617604732513428},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.08678579330444336},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.05261501669883728}],"concepts":[{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.7651597261428833},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.605655312538147},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.5366525053977966},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4259750247001648},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4110589325428009},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3100205957889557},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.2617604732513428},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.08678579330444336},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.05261501669883728}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icasspw65056.2025.11011113","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw65056.2025.11011113","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"},{"id":"pmh:oai:re.public.polimi.it:11311/1295746","is_oa":false,"landing_page_url":"https://hdl.handle.net/11311/1295746","pdf_url":null,"source":{"id":"https://openalex.org/S4306400312","display_name":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79189158","host_organization_name":"University of Castilla-La Mancha","host_organization_lineage":["https://openalex.org/I79189158"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2038484192","https://openalex.org/W2052666245","https://openalex.org/W2959539607","https://openalex.org/W3015591594","https://openalex.org/W3033907960","https://openalex.org/W3040266635","https://openalex.org/W3045886598","https://openalex.org/W3094550259","https://openalex.org/W3095753917","https://openalex.org/W3138333912","https://openalex.org/W3204067194","https://openalex.org/W4200337780","https://openalex.org/W4292397060","https://openalex.org/W4308507013","https://openalex.org/W4315926819","https://openalex.org/W4372260340","https://openalex.org/W4387244556","https://openalex.org/W4387969125","https://openalex.org/W4396241918","https://openalex.org/W4396877837","https://openalex.org/W4402111582","https://openalex.org/W4403653940","https://openalex.org/W4405182531","https://openalex.org/W4407130159","https://openalex.org/W4408345930","https://openalex.org/W6779961064","https://openalex.org/W6845479124","https://openalex.org/W6849109464","https://openalex.org/W6849416043","https://openalex.org/W6852971826","https://openalex.org/W6861353174","https://openalex.org/W6864798992","https://openalex.org/W6870090694","https://openalex.org/W6872964820","https://openalex.org/W6874382956"],"related_works":["https://openalex.org/W2318538434","https://openalex.org/W4404440671","https://openalex.org/W1590604789","https://openalex.org/W2088690926","https://openalex.org/W2169018375","https://openalex.org/W1595500397","https://openalex.org/W1979717040","https://openalex.org/W2511638641","https://openalex.org/W2332365212","https://openalex.org/W3000635088"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"the":[3,85,93],"design":[4],"of":[5,49,95],"effective":[6,99],"prompt":[7,50,57,62],"strategies":[8,58],"for":[9,22],"generating":[10],"realistic":[11],"datasets":[12,26,40,69],"using":[13,71,103],"Text-To-Audio":[14],"(TTA)":[15],"models.":[16],"We":[17],"also":[18],"analyze":[19],"different":[20,72],"techniques":[21,102],"efficiently":[23],"combining":[24],"these":[25,96],"to":[27,76],"enhance":[28,77],"their":[29],"utility":[30],"in":[31,64],"sound":[32,38],"classification":[33,39,78],"tasks.":[34],"By":[35],"evaluating":[36],"two":[37,42],"with":[41],"TTA":[43,73],"models,":[44],"we":[45],"apply":[46],"a":[47],"range":[48],"strategies.":[51],"Our":[52],"findings":[53],"reveal":[54],"that":[55],"task-specific":[56],"significantly":[59],"outperform":[60],"basic":[61],"approaches":[63],"data":[65,100],"generation.":[66],"Furthermore,":[67],"merging":[68],"generated":[70],"models":[74],"proves":[75],"performance":[79],"more":[80],"effectively":[81],"than":[82],"merely":[83],"increasing":[84],"training":[86],"dataset":[87],"size.":[88],"Overall,":[89],"our":[90],"results":[91],"underscore":[92],"advantages":[94],"methods":[97],"as":[98],"augmentation":[101],"synthetic":[104],"data.":[105]},"counts_by_year":[],"updated_date":"2026-06-16T09:24:06.705377","created_date":"2025-10-10T00:00:00"}
