{"id":"https://openalex.org/W4410771968","doi":"https://doi.org/10.1109/icasspw65056.2025.11011255","title":"TSPE: Task-Specific Prompt Ensemble for Improved Zero-Shot Audio Classification","display_name":"TSPE: Task-Specific Prompt Ensemble for Improved Zero-Shot Audio Classification","publication_year":2025,"publication_date":"2025-04-06","ids":{"openalex":"https://openalex.org/W4410771968","doi":"https://doi.org/10.1109/icasspw65056.2025.11011255"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw65056.2025.11011255","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw65056.2025.11011255","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":"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":"https://openalex.org/A5076391965","display_name":"Nishit Anand","orcid":"https://orcid.org/0000-0001-9391-1871"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nishit Anand","raw_affiliation_strings":["University of Maryland,College Park,MD,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park,MD,USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018932560","display_name":"Ashish Seth","orcid":"https://orcid.org/0000-0003-3100-9342"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashish Seth","raw_affiliation_strings":["University of Maryland,College Park,MD,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park,MD,USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013222310","display_name":"Ramani Duraiswami","orcid":"https://orcid.org/0000-0002-5596-8460"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ramani Duraiswami","raw_affiliation_strings":["University of Maryland,College Park,MD,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park,MD,USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004194238","display_name":"Dinesh Manocha","orcid":"https://orcid.org/0000-0001-7047-9801"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dinesh Manocha","raw_affiliation_strings":["University of Maryland,College Park,MD,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park,MD,USA","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I66946132"],"apc_list":null,"apc_paid":null,"fwci":3.0156,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.90105748,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":97},"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":0.9988999962806702,"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":0.9988999962806702,"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":0.9724000096321106,"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":0.9682000279426575,"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/computer-science","display_name":"Computer science","score":0.6846932172775269},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.6649127006530762},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6077020168304443},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.5918331146240234},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47721272706985474},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45057258009910583},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3535870909690857},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06693488359451294}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6846932172775269},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6649127006530762},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6077020168304443},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5918331146240234},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47721272706985474},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45057258009910583},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3535870909690857},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06693488359451294},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icasspw65056.2025.11011255","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw65056.2025.11011255","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2038484192","https://openalex.org/W2052666245","https://openalex.org/W2133824856","https://openalex.org/W2143070508","https://openalex.org/W3176445421","https://openalex.org/W3198377975","https://openalex.org/W3207493267","https://openalex.org/W4225299287","https://openalex.org/W4284898017","https://openalex.org/W4312097006","https://openalex.org/W4372266552","https://openalex.org/W4385823125","https://openalex.org/W4386071547","https://openalex.org/W4386918931","https://openalex.org/W4391094120","https://openalex.org/W4392909369","https://openalex.org/W6704098239","https://openalex.org/W6736723571","https://openalex.org/W6791353385","https://openalex.org/W6803252908","https://openalex.org/W6803864336","https://openalex.org/W6849437247","https://openalex.org/W6857657557","https://openalex.org/W6861190020","https://openalex.org/W6863470433","https://openalex.org/W6867724613","https://openalex.org/W6868057936","https://openalex.org/W6870464448"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W2325697621"],"abstract_inverted_index":{"Audio-Language":[0,109],"models":[1,11],"(ALMs)":[2,111],"excel":[3],"in":[4],"zero-shot":[5,41,150],"audio":[6,15,48,113,133],"classification,":[7],"a":[8,32,60,70,74],"task":[9],"where":[10],"classify":[12],"previously":[13],"unseen":[14],"clips":[16],"at":[17],"test":[18],"time":[19],"by":[20,43,108,141],"leveraging":[21],"descriptive":[22],"natural":[23],"language":[24],"prompts.":[25,127],"We":[26],"introduce":[27],"TSPE":[28,136],"(Task-Specific":[29],"Prompt":[30],"Ensemble),":[31],"simple,":[33],"training-free":[34],"hard":[35],"prompting":[36],"method":[37],"that":[38],"boosts":[39],"ALMs\u2019":[40],"performance":[42,138],"customizing":[44],"prompts":[45,56,106],"for":[46,112],"diverse":[47,132],"classification":[49,134],"tasks.":[50],"Rather":[51],"than":[52],"using":[53],"generic":[54],"template-based":[55],"like":[57],"\"Sound":[58,68],"of":[59,69,146],"car\"":[61],"we":[62,77,120],"generate":[63],"context-rich":[64],"prompts,":[65],"such":[66,86,95],"as":[67,87,96],"car":[71],"coming":[72],"from":[73],"tunnel\".":[75],"Specifically,":[76],"leverage":[78],"label":[79],"information":[80,103],"to":[81,116],"identify":[82],"suitable":[83],"sound":[84,93],"attributes,":[85],"\"loud\"":[88],"and":[89,91,98,100],"\"feeble\",":[90],"appropriate":[92],"sources,":[94],"\"tunnel\"":[97],"\"street\"":[99],"incorporate":[101],"this":[102],"into":[104],"the":[105],"used":[107],"Models":[110],"classification.":[114],"Further,":[115],"enhance":[117],"audio-text":[118],"alignment,":[119],"perform":[121],"prompt":[122],"ensemble":[123],"across":[124,139],"TSPE-generated":[125],"task-specific":[126],"When":[128],"evaluated":[129],"on":[130],"12":[131],"datasets,":[135],"improves":[137],"ALMs":[140],"showing":[142],"an":[143],"absolute":[144],"improvement":[145],"1.23-16.36%":[147],"over":[148],"vanilla":[149],"evaluation.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}