{"id":"https://openalex.org/W4392903299","doi":"https://doi.org/10.1109/icassp48485.2024.10448085","title":"Audio Difference Learning for Audio Captioning","display_name":"Audio Difference Learning for Audio Captioning","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903299","doi":"https://doi.org/10.1109/icassp48485.2024.10448085"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448085","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448085","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":"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/A5113730169","display_name":"Tatsuya Komatsu","orcid":null},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]},{"id":"https://openalex.org/I4210096607","display_name":"Line Corporation (Japan)","ror":"https://ror.org/00qg8pm87","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210096607","https://openalex.org/I60922564"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Tatsuya Komatsu","raw_affiliation_strings":["LINE Corporation,Japan","LINE Corporation, Japan","Nagoya University, Japan"],"affiliations":[{"raw_affiliation_string":"LINE Corporation,Japan","institution_ids":["https://openalex.org/I4210096607"]},{"raw_affiliation_string":"LINE Corporation, Japan","institution_ids":["https://openalex.org/I4210096607"]},{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044818016","display_name":"Yusuke Fujita","orcid":"https://orcid.org/0000-0002-6523-8146"},"institutions":[{"id":"https://openalex.org/I4210096607","display_name":"Line Corporation (Japan)","ror":"https://ror.org/00qg8pm87","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210096607","https://openalex.org/I60922564"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yusuke Fujita","raw_affiliation_strings":["LINE Corporation,Japan","LINE Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"LINE Corporation,Japan","institution_ids":["https://openalex.org/I4210096607"]},{"raw_affiliation_string":"LINE Corporation, Japan","institution_ids":["https://openalex.org/I4210096607"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042118446","display_name":"Kazuya Takeda","orcid":"https://orcid.org/0000-0002-0330-1787"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuya Takeda","raw_affiliation_strings":["Nagoya University,Japan","Nagoya University, Japan"],"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Nagoya University,Japan","Nagoya University, Japan"],"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5113730169"],"corresponding_institution_ids":["https://openalex.org/I4210096607","https://openalex.org/I60134161"],"apc_list":null,"apc_paid":null,"fwci":1.1206,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.74455212,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1456","last_page":"1460"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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":0.9976999759674072,"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":0.9939000010490417,"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/computer-science","display_name":"Computer science","score":0.8160465955734253},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.7109497785568237},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.6447936296463013},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5368021130561829},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5065478086471558},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4823895990848541},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4699663817882538},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.43460893630981445},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.421779990196228},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.4182989001274109},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.40176597237586975},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3399012088775635},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.18320927023887634},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.1621944010257721},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08778861165046692}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8160465955734253},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7109497785568237},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.6447936296463013},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5368021130561829},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5065478086471558},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4823895990848541},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4699663817882538},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.43460893630981445},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.421779990196228},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.4182989001274109},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.40176597237586975},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3399012088775635},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.18320927023887634},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.1621944010257721},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08778861165046692},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/icassp48485.2024.10448085","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448085","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":[{"id":"https://metadata.un.org/sdg/4","score":0.5199999809265137,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2052666245","https://openalex.org/W2130942839","https://openalex.org/W2916103538","https://openalex.org/W2936774411","https://openalex.org/W2964213897","https://openalex.org/W3015591594","https://openalex.org/W3034999214","https://openalex.org/W3094550259","https://openalex.org/W4280567182","https://openalex.org/W4283075937","https://openalex.org/W4307933152","https://openalex.org/W4372260340","https://openalex.org/W4385245566","https://openalex.org/W4385822843","https://openalex.org/W6679436768","https://openalex.org/W6798955355","https://openalex.org/W6799494382","https://openalex.org/W6848208918","https://openalex.org/W6855847491","https://openalex.org/W6856084164"],"related_works":["https://openalex.org/W2098934641","https://openalex.org/W2494533082","https://openalex.org/W4214771044","https://openalex.org/W4382560817","https://openalex.org/W4387698063","https://openalex.org/W1975359510","https://openalex.org/W1611900921","https://openalex.org/W1969715806","https://openalex.org/W3004352674","https://openalex.org/W1620668332"],"abstract_inverted_index":{"This":[0,45,103,123],"study":[1],"introduces":[2],"a":[3,25,48,65,81,101],"novel":[4],"training":[5],"paradigm,":[6],"audio":[7,12,43,50,91,99,111,115],"difference":[8,107],"learning,":[9],"for":[10,135,141,144],"improving":[11],"captioning.":[13],"The":[14],"fundamental":[15],"concept":[16],"of":[17,38,57],"the":[18,31,36,53,89,97,106,109,113,119,125,133,139,145,148,151,156,163],"proposed":[19,85,157],"learning":[20],"method":[21,46,158],"is":[22,84],"to":[23,76,118,129,169],"create":[24],"feature":[26,62],"representation":[27],"space":[28],"that":[29,40,86],"preserves":[30],"relationship":[32],"between":[33,108],"audio,":[34,55,94],"enabling":[35],"generation":[37],"captions":[39],"detail":[41],"intricate":[42],"information.":[44],"employs":[47],"reference":[49,114],"along":[51],"with":[52,92],"input":[54,90,121],"both":[56],"which":[58],"are":[59,69],"transformed":[60],"into":[61],"representations":[63],"via":[64],"shared":[66],"encoder.":[67],"Captions":[68],"then":[70],"generated":[71],"from":[72],"these":[73],"differential":[74],"features":[75],"describe":[77],"their":[78,136],"differences.":[79,146],"Furthermore,":[80],"unique":[82],"technique":[83],"involves":[87],"mixing":[88],"additional":[93,98,142],"and":[95,112,153],"using":[96,150],"as":[100,132],"reference.":[102],"results":[104],"in":[105,162],"mixed":[110],"reverting":[116],"back":[117],"original":[120,126],"audio.":[122],"allows":[124],"input\u2019s":[127],"caption":[128,134],"be":[130],"used":[131],"difference,":[137],"eliminating":[138],"need":[140],"annotations":[143],"In":[147],"experiments":[149],"Clotho":[152],"ESC50":[154],"datasets,":[155],"demonstrated":[159],"an":[160],"improvement":[161],"SPIDEr":[164],"score":[165],"by":[166],"7%":[167],"compared":[168],"conventional":[170],"methods.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}