{"id":"https://openalex.org/W4224932123","doi":"https://doi.org/10.1109/icassp43922.2022.9746601","title":"Joint Speech Recognition and Audio Captioning","display_name":"Joint Speech Recognition and Audio Captioning","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224932123","doi":"https://doi.org/10.1109/icassp43922.2022.9746601"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746601","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746601","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5015372147","display_name":"Chaitanya Narisetty","orcid":"https://orcid.org/0000-0002-9239-5534"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chaitanya Narisetty","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011937407","display_name":"Emiru Tsunoo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Emiru Tsunoo","raw_affiliation_strings":["Sony Group Corporation,Japan","Sony Group Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony Group Corporation,Japan","institution_ids":[]},{"raw_affiliation_string":"Sony Group Corporation, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050058892","display_name":"Xuankai Chang","orcid":"https://orcid.org/0000-0002-5221-5412"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuankai Chang","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109644502","display_name":"Yosuke Kashiwagi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yosuke Kashiwagi","raw_affiliation_strings":["Sony Group Corporation,Japan","Sony Group Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony Group Corporation,Japan","institution_ids":[]},{"raw_affiliation_string":"Sony Group Corporation, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010628266","display_name":"Michael Hentschel","orcid":"https://orcid.org/0000-0003-3986-5725"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Hentschel","raw_affiliation_strings":["Sony Group Corporation,Japan","Sony Group Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony Group Corporation,Japan","institution_ids":[]},{"raw_affiliation_string":"Sony Group Corporation, Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.661,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.85777166,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"7892","last_page":"7896"},"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":0.9998000264167786,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8447449207305908},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.7881392240524292},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7093459963798523},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5747061967849731},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.5488664507865906},{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.5211953520774841},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4922093451023102},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.4906860589981079},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4656292796134949},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.44228315353393555},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4254247844219208},{"id":"https://openalex.org/keywords/speech-analytics","display_name":"Speech analytics","score":0.41738951206207275},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40783679485321045},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3998086750507355},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34516263008117676}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8447449207305908},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7881392240524292},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7093459963798523},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5747061967849731},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.5488664507865906},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.5211953520774841},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4922093451023102},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.4906860589981079},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4656292796134949},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.44228315353393555},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4254247844219208},{"id":"https://openalex.org/C54953205","wikidata":"https://www.wikidata.org/wiki/Q4142201","display_name":"Speech analytics","level":4,"score":0.41738951206207275},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40783679485321045},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3998086750507355},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34516263008117676},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746601","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746601","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/16","score":0.7900000214576721,"display_name":"Peace, Justice and strong institutions"}],"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":37,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1828163288","https://openalex.org/W1956340063","https://openalex.org/W1992475611","https://openalex.org/W2024490156","https://openalex.org/W2043701535","https://openalex.org/W2058094241","https://openalex.org/W2102113734","https://openalex.org/W2193413348","https://openalex.org/W2327501763","https://openalex.org/W2506483933","https://openalex.org/W2593116425","https://openalex.org/W2627092829","https://openalex.org/W2766219058","https://openalex.org/W2949376505","https://openalex.org/W2962780374","https://openalex.org/W2963240019","https://openalex.org/W2963574857","https://openalex.org/W2964213897","https://openalex.org/W2972818416","https://openalex.org/W2981022124","https://openalex.org/W2982471419","https://openalex.org/W3007328579","https://openalex.org/W3013139777","https://openalex.org/W3094667432","https://openalex.org/W3095738461","https://openalex.org/W3103022576","https://openalex.org/W3185739472","https://openalex.org/W6623517193","https://openalex.org/W6638749077","https://openalex.org/W6675365184","https://openalex.org/W6687566353","https://openalex.org/W6725318829","https://openalex.org/W6734260513","https://openalex.org/W6755552547","https://openalex.org/W6775489429","https://openalex.org/W6798955355"],"related_works":["https://openalex.org/W2157598242","https://openalex.org/W2619911963","https://openalex.org/W2903652364","https://openalex.org/W3089379469","https://openalex.org/W4321847012","https://openalex.org/W3151376046","https://openalex.org/W1799027130","https://openalex.org/W2129389759","https://openalex.org/W3141034595","https://openalex.org/W2066339445"],"abstract_inverted_index":{"Speech":[0],"samples":[1],"recorded":[2],"in":[3,74,105],"both":[4,118],"indoor":[5],"and":[6,38,54,87,90,121,157,170],"outdoor":[7],"environments":[8],"are":[9],"often":[10],"contaminated":[11],"with":[12,117,140],"secondary":[13],"audio":[14,51,75,115,122],"sources.":[15],"Most":[16],"end-to-end":[17,82],"monaural":[18],"speech":[19,28,59,119,135],"recognition":[20,60],"systems":[21],"either":[22],"remove":[23],"these":[24,99],"background":[25,144],"sounds":[26],"using":[27],"enhancement":[29],"or":[30],"train":[31],"noise-robust":[32],"models.":[33],"For":[34],"better":[35],"model":[36,98],"interpretability":[37],"holistic":[39],"understanding,":[40],"we":[41,125],"aim":[42],"to":[43,67,166],"bring":[44],"together":[45],"the":[46,55,111,133,148],"growing":[47],"field":[48],"of":[49,64,72,85,113,143,160],"automated":[50],"captioning":[52],"(AAC)":[53],"thoroughly":[56],"studied":[57],"automatic":[58],"(ASR).":[61],"The":[62],"goal":[63],"AAC":[65,88,171],"is":[66,110],"generate":[68],"natural":[69],"language":[70],"descriptions":[71],"contents":[73],"samples.":[76],"We":[77,151],"propose":[78],"several":[79],"approaches":[80],"for":[81],"joint":[83],"modeling":[84],"ASR":[86,169],"tasks":[89,100],"demonstrate":[91],"their":[92],"advantages":[93],"over":[94],"traditional":[95],"approaches,":[96],"which":[97],"independently.":[101],"A":[102],"major":[103],"hurdle":[104],"evaluating":[106],"our":[107,161],"proposed":[108,162],"approach":[109],"lack":[112],"labeled":[114],"datasets":[116],"transcriptions":[120],"captions.":[123],"Therefore":[124],"also":[126,152],"create":[127],"a":[128],"multi-task":[129],"dataset":[130],"by":[131],"mixing":[132],"clean":[134],"Wall":[136],"Street":[137],"Journal":[138],"corpus":[139],"multiple":[141],"levels":[142],"noises":[145],"chosen":[146],"from":[147],"AudioCaps":[149],"dataset.":[150],"perform":[153],"extensive":[154],"experimental":[155],"evaluation":[156],"show":[158],"improvements":[159],"methods":[163],"as":[164],"compared":[165],"existing":[167],"state-of-the-art":[168],"methods.":[172]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}