{"id":"https://openalex.org/W4392903178","doi":"https://doi.org/10.1109/icassp48485.2024.10446736","title":"Learning Audio Concepts from Counterfactual Natural Language","display_name":"Learning Audio Concepts from Counterfactual Natural Language","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903178","doi":"https://doi.org/10.1109/icassp48485.2024.10446736"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446736","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446736","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5058314486","display_name":"Ali Vosoughi","orcid":"https://orcid.org/0000-0003-1014-2937"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ali Vosoughi","raw_affiliation_strings":["University of Rochester,Rochester,NY,USA","University of Rochester, Rochester, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rochester,Rochester,NY,USA","institution_ids":["https://openalex.org/I5388228"]},{"raw_affiliation_string":"University of Rochester, Rochester, NY, USA","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061125165","display_name":"Luca Bondi","orcid":"https://orcid.org/0000-0003-3974-7542"},"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":"Luca Bondi","raw_affiliation_strings":["USA - Bosch Center for Artificial Intelligence,Bosch Research","Bosch Research, USA - Bosch Center for Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"USA - Bosch Center for Artificial Intelligence,Bosch Research","institution_ids":["https://openalex.org/I4210120115"]},{"raw_affiliation_string":"Bosch Research, USA - Bosch Center for Artificial Intelligence","institution_ids":["https://openalex.org/I4210120115"]}]},{"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":["USA - Bosch Center for Artificial Intelligence,Bosch Research","Bosch Research, USA - Bosch Center for Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"USA - Bosch Center for Artificial Intelligence,Bosch Research","institution_ids":["https://openalex.org/I4210120115"]},{"raw_affiliation_string":"Bosch Research, USA - Bosch Center for Artificial Intelligence","institution_ids":["https://openalex.org/I4210120115"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064805926","display_name":"Chenliang Xu","orcid":"https://orcid.org/0000-0002-2183-822X"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chenliang Xu","raw_affiliation_strings":["University of Rochester,Rochester,NY,USA","University of Rochester, Rochester, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rochester,Rochester,NY,USA","institution_ids":["https://openalex.org/I5388228"]},{"raw_affiliation_string":"University of Rochester, Rochester, NY, USA","institution_ids":["https://openalex.org/I5388228"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6686,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.82978941,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"366","last_page":"370"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.972000002861023,"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/T13996","display_name":"Diverse Musicological Studies","score":0.9684000015258789,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8375945091247559},{"id":"https://openalex.org/keywords/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.8049886226654053},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.7315418720245361},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5288894176483154},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5131619572639465},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.4973202049732208},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4802042245864868},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4708675146102905},{"id":"https://openalex.org/keywords/open-domain","display_name":"Open domain","score":0.46028441190719604},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4506934583187103},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.43652260303497314},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43221646547317505},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.41677162051200867},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.41534551978111267},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.33633744716644287},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.16620901226997375},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.13319525122642517}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8375945091247559},{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.8049886226654053},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7315418720245361},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5288894176483154},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5131619572639465},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.4973202049732208},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4802042245864868},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4708675146102905},{"id":"https://openalex.org/C2993776861","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Open domain","level":3,"score":0.46028441190719604},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4506934583187103},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.43652260303497314},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43221646547317505},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.41677162051200867},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.41534551978111267},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.33633744716644287},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.16620901226997375},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.13319525122642517},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446736","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446736","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.75}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2038484192","https://openalex.org/W2052666245","https://openalex.org/W2143891888","https://openalex.org/W2883512601","https://openalex.org/W2936695845","https://openalex.org/W2945761034","https://openalex.org/W2979826702","https://openalex.org/W3015591594","https://openalex.org/W3094550259","https://openalex.org/W3162331882","https://openalex.org/W3176445421","https://openalex.org/W4221143046","https://openalex.org/W4226278401","https://openalex.org/W4284898017","https://openalex.org/W4292779060","https://openalex.org/W4301372783","https://openalex.org/W4367692219","https://openalex.org/W4372260310","https://openalex.org/W4372266552","https://openalex.org/W4377130946","https://openalex.org/W4377372369","https://openalex.org/W4386075552","https://openalex.org/W4400033239","https://openalex.org/W6761205521","https://openalex.org/W6778883912","https://openalex.org/W6783990618","https://openalex.org/W6791353385","https://openalex.org/W6809646742","https://openalex.org/W6810738896","https://openalex.org/W6852818750","https://openalex.org/W6853249747","https://openalex.org/W6855847491"],"related_works":["https://openalex.org/W2098934641","https://openalex.org/W3135871143","https://openalex.org/W3192727970","https://openalex.org/W4382560817","https://openalex.org/W2347715673","https://openalex.org/W2405875744","https://openalex.org/W2020966186","https://openalex.org/W296599067","https://openalex.org/W2119339729","https://openalex.org/W4387698063"],"abstract_inverted_index":{"Conventional":[0],"audio":[1,27,75,115,143,152],"classification":[2],"relied":[3],"on":[4],"predefined":[5],"classes,":[6],"lacking":[7],"the":[8,74,105,127,130,136,146],"ability":[9],"to":[10,41],"learn":[11],"from":[12,22,57,99],"free-form":[13],"text.":[14],"Recent":[15],"methods":[16,40],"unlock":[17],"learning":[18],"joint":[19],"audio-text":[20,24],"embeddings":[21],"raw":[23],"pairs":[25],"describing":[26],"in":[28,50,62,73,84,142,149],"natural":[29],"language.":[30],"Despite":[31],"recent":[32],"advancements,":[33],"there":[34],"is":[35],"little":[36],"exploration":[37],"of":[38,107,129,135],"systematic":[39],"train":[42],"models":[43],"for":[44],"recognizing":[45],"sound":[46,96],"events":[47,61],"and":[48,70,81,95],"sources":[49],"alternative":[51],"scenarios,":[52],"such":[53],"as":[54,133],"distinguishing":[55],"fireworks":[56],"gunshots":[58],"at":[59],"outdoor":[60],"similar":[63],"situations.":[64],"This":[65],"study":[66],"introduces":[67],"causal":[68],"reasoning":[69],"counterfactual":[71,79,140],"analysis":[72],"domain.":[76,144],"We":[77,118],"use":[78],"instances":[80],"include":[82],"them":[83],"our":[85,108],"model":[86,91],"across":[87],"different":[88],"aspects.":[89],"Our":[90],"considers":[92],"acoustic":[93],"characteristics":[94],"source":[97],"information":[98,141],"human-annotated":[100],"reference":[101],"texts.":[102],"To":[103],"validate":[104],"effectiveness":[106],"model,":[109],"we":[110],"conducted":[111],"pre-training":[112],"utilizing":[113],"multiple":[114],"captioning":[116],"datasets.":[117],"then":[119],"evaluate":[120],"with":[121],"several":[122],"common":[123],"downstream":[124],"tasks,":[125],"demonstrating":[126],"merits":[128],"proposed":[131],"method":[132],"one":[134],"first":[137],"works":[138],"leveraging":[139],"Specifically,":[145],"top-1":[147],"accuracy":[148],"open-ended":[150],"language-based":[151],"retrieval":[153],"task":[154],"increased":[155],"by":[156],"more":[157],"than":[158],"43%.":[159]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}