{"id":"https://openalex.org/W4391021645","doi":"https://doi.org/10.1109/asru57964.2023.10389692","title":"Flap: Fast Language-Audio Pre-Training","display_name":"Flap: Fast Language-Audio Pre-Training","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021645","doi":"https://doi.org/10.1109/asru57964.2023.10389692"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389692","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389692","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5087421101","display_name":"Ching-Feng Yeh","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ching-Feng Yeh","raw_affiliation_strings":["FAIR, Meta"],"affiliations":[{"raw_affiliation_string":"FAIR, Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063149046","display_name":"Po-Yao Huang","orcid":"https://orcid.org/0000-0002-3319-5145"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Po-Yao Huang","raw_affiliation_strings":["FAIR, Meta"],"affiliations":[{"raw_affiliation_string":"FAIR, Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102320649","display_name":"Vasu Sharma","orcid":"https://orcid.org/0009-0005-4733-3229"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vasu Sharma","raw_affiliation_strings":["FAIR, Meta"],"affiliations":[{"raw_affiliation_string":"FAIR, Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029566548","display_name":"Shang-Wen Li","orcid":"https://orcid.org/0000-0003-0656-9874"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shang-Wen Li","raw_affiliation_strings":["FAIR, Meta"],"affiliations":[{"raw_affiliation_string":"FAIR, Meta","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5093211868","display_name":"Gargi Gosh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gargi Gosh","raw_affiliation_strings":["FAIR, Meta"],"affiliations":[{"raw_affiliation_string":"FAIR, Meta","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5087421101"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8133,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.73518182,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9987999796867371,"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":0.8412257432937622},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6298326253890991},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.6217281818389893},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5963502526283264},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4482179880142212},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44786494970321655},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4201715588569641}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8412257432937622},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6298326253890991},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.6217281818389893},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5963502526283264},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4482179880142212},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44786494970321655},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4201715588569641},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389692","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389692","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8399999737739563,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W60493759","https://openalex.org/W2138621090","https://openalex.org/W2593116425","https://openalex.org/W2842511635","https://openalex.org/W2936774411","https://openalex.org/W2963074118","https://openalex.org/W2965373594","https://openalex.org/W3005680577","https://openalex.org/W3015591594","https://openalex.org/W3035524453","https://openalex.org/W3036601975","https://openalex.org/W3114632476","https://openalex.org/W3145450063","https://openalex.org/W3166396011","https://openalex.org/W3171927989","https://openalex.org/W3203711169","https://openalex.org/W3207924272","https://openalex.org/W3209059054","https://openalex.org/W3210447534","https://openalex.org/W4210913346","https://openalex.org/W4214718130","https://openalex.org/W4221157007","https://openalex.org/W4221167396","https://openalex.org/W4280490805","https://openalex.org/W4285483774","https://openalex.org/W4297808394","https://openalex.org/W4311731188","https://openalex.org/W4313156423","https://openalex.org/W4322718191","https://openalex.org/W4372260310","https://openalex.org/W4372266552","https://openalex.org/W4380353763","https://openalex.org/W4385822467","https://openalex.org/W4386076084","https://openalex.org/W6602483677","https://openalex.org/W6631190155","https://openalex.org/W6682250724","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6766673545","https://openalex.org/W6774314701","https://openalex.org/W6780218876","https://openalex.org/W6791353385","https://openalex.org/W6810265253","https://openalex.org/W6838789689","https://openalex.org/W6840200333","https://openalex.org/W6847495150","https://openalex.org/W6850625674","https://openalex.org/W6852874933"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W3127543252","https://openalex.org/W2897924318","https://openalex.org/W2138997758"],"abstract_inverted_index":{"We":[0],"propose":[1],"Fast":[2],"Language-Audio":[3],"Pre-training":[4],"(FLAP),":[5],"a":[6,55],"self-supervised":[7],"approach":[8],"that":[9],"efficiently":[10],"and":[11,16,23,51,70,102,122],"effectively":[12],"learns":[13,46,71],"aligned":[14],"audio":[15,30,50,78],"language":[17,84],"representations":[18,53],"through":[19],"masking,":[20],"contrastive":[21,43],"learning":[22],"reconstruction.":[24],"For":[25],"efficiency,":[26],"FLAP":[27,45,60,81,107],"randomly":[28],"drops":[29],"spectrogram":[31],"tokens,":[32],"focusing":[33],"solely":[34],"on":[35,113,117],"the":[36,74,89],"remaining":[37],"ones":[38],"for":[39,67],"self-supervision.":[40],"Through":[41],"inter-modal":[42],"learning,":[44],"to":[47,72,87,93,99,108],"align":[48],"paired":[49],"text":[52,90],"in":[54],"shared":[56],"latent":[57],"space.":[58],"Notably,":[59],"leverages":[61,82],"multiple":[62],"augmented":[63],"views":[64],"via":[65],"masking":[66],"intermodal":[68],"contrast":[69],"reconstruct":[73],"masked":[75],"portion":[76],"of":[77],"tokens.":[79],"Moreover,":[80],"large":[83],"models":[85],"(LLMs)":[86],"augment":[88],"inputs,":[91],"contributing":[92],"improved":[94],"performance.":[95],"These":[96],"approaches":[97],"lead":[98],"more":[100],"robust":[101],"informative":[103],"audio-text":[104,114],"representations,":[105],"enabling":[106],"achieve":[109],"state-of-the-art":[110],"(SoTA)":[111],"performance":[112],"retrieval":[115],"tasks":[116],"AudioCaps":[118],"(achieving":[119,124],"53.0%":[120],"R@1)":[121],"Clotho":[123],"25.5%":[125],"R@1).":[126]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}