{"id":"https://openalex.org/W2916103538","doi":"https://doi.org/10.1109/icassp.2019.8682377","title":"Audio Caption: Listen and Tell","display_name":"Audio Caption: Listen and Tell","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2916103538","doi":"https://doi.org/10.1109/icassp.2019.8682377","mag":"2916103538"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682377","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682377","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1902.09254","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081865665","display_name":"Mengyue Wu","orcid":"https://orcid.org/0000-0002-5599-8707"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengyue Wu","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080154283","display_name":"Heinrich Dinkel","orcid":"https://orcid.org/0000-0003-4330-8980"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heinrich Dinkel","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043098653","display_name":"Kai Yu","orcid":"https://orcid.org/0000-0002-7102-9826"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Yu","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":53,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"830","last_page":"834"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9886999726295471,"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":0.8488262891769409},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.595759928226471},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.592144787311554},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5759313702583313},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.5436943173408508},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.5178930759429932},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5107786655426025},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5074953436851501},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4725120961666107},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.45616015791893005},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.4554034471511841},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.44065096974372864},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.3065755367279053},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.24643364548683167},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.22039535641670227},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.18132439255714417},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07209551334381104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8488262891769409},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.595759928226471},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.592144787311554},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5759313702583313},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.5436943173408508},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.5178930759429932},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5107786655426025},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5074953436851501},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4725120961666107},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.45616015791893005},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.4554034471511841},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.44065096974372864},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3065755367279053},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.24643364548683167},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.22039535641670227},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.18132439255714417},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07209551334381104},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2019.8682377","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682377","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1902.09254","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1902.09254","pdf_url":"https://arxiv.org/pdf/1902.09254","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1902.09254","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1902.09254","pdf_url":"https://arxiv.org/pdf/1902.09254","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.7200000286102295,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1573040851","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1975879668","https://openalex.org/W2038484192","https://openalex.org/W2101105183","https://openalex.org/W2123442489","https://openalex.org/W2143177362","https://openalex.org/W2414894569","https://openalex.org/W2418300416","https://openalex.org/W2481240925","https://openalex.org/W2526050071","https://openalex.org/W2566935005","https://openalex.org/W2593116425","https://openalex.org/W2607119937","https://openalex.org/W2799258971","https://openalex.org/W2903250132","https://openalex.org/W2962961016","https://openalex.org/W2963723765","https://openalex.org/W2964065937","https://openalex.org/W2964213897","https://openalex.org/W3123940584","https://openalex.org/W6630875275","https://openalex.org/W6715395060","https://openalex.org/W6745214240","https://openalex.org/W6788837655","https://openalex.org/W6898505805"],"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":{"Increasing":[0],"amount":[1],"of":[2,10,14,24,90],"research":[3,45],"has":[4,50],"shed":[5],"light":[6],"on":[7,136],"machine":[8,88],"perception":[9,23,89],"audio":[11,25,33,42,55,68,79,91],"events,":[12],"most":[13],"which":[15],"concerns":[16],"detection":[17],"and":[18,31,82,92,101,117,132],"classification":[19],"tasks.":[20],"However,":[21],"human-like":[22],"scenes":[26],"involves":[27],"not":[28],"only":[29],"detecting":[30],"classifying":[32],"sounds,":[34],"but":[35],"also":[36,103],"summarizing":[37],"the":[38,54,85,137],"relationship":[39],"between":[40,87],"different":[41],"events.":[43],"Comparable":[44],"such":[46],"as":[47],"image":[48],"caption":[49],"been":[51],"conducted,":[52],"yet":[53],"field":[56],"is":[57,72,97,112],"still":[58],"quite":[59],"barren.":[60],"This":[61],"paper":[62],"introduces":[63],"a":[64],"manually-annotated":[65],"dataset":[66,96],"for":[67,78,114,124],"caption.":[69],"The":[70,94],"purpose":[71],"to":[73,83],"automatically":[74],"generate":[75,130],"natural":[76],"sentences":[77],"scene":[80],"description":[81],"bridge":[84],"gap":[86],"image.":[93],"whole":[95],"labelled":[98],"in":[99],"Mandarin":[100],"we":[102],"include":[104],"translated":[105],"English":[106,116],"annotations.":[107],"A":[108],"baseline":[109],"encoder-decoder":[110],"model":[111,128],"provided":[113],"both":[115,125],"Mandarin.":[118],"Similar":[119],"BLEU":[120],"scores":[121],"are":[122],"derived":[123],"languages:":[126],"our":[127],"can":[129],"understandable":[131],"data-related":[133],"captions":[134],"based":[135],"dataset.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
