{"id":"https://openalex.org/W2963715927","doi":"https://doi.org/10.1109/icassp.2018.8462479","title":"A Light-Weight Multimodal Framework for Improved Environmental Audio Tagging","display_name":"A Light-Weight Multimodal Framework for Improved Environmental Audio Tagging","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2963715927","doi":"https://doi.org/10.1109/icassp.2018.8462479","mag":"2963715927"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462479","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462479","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/A5100648014","display_name":"Juncheng Li","orcid":"https://orcid.org/0000-0001-7314-6754"},"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":"Juncheng Li","raw_affiliation_strings":["Robert Bosch LLC, Research and Technology Center, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robert Bosch LLC, Research and Technology Center, USA","institution_ids":["https://openalex.org/I4210120115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100377624","display_name":"Yun Wang","orcid":"https://orcid.org/0000-0002-4749-2984"},"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":"Yun Wang","raw_affiliation_strings":["Language Technology Institute, Carnegie Mellon University, Pittsburgh, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technology Institute, Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072368204","display_name":"Joseph Szurley","orcid":null},"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":"Joseph Szurley","raw_affiliation_strings":["Robert Bosch LLC, Research and Technology Center, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robert Bosch LLC, Research and Technology Center, USA","institution_ids":["https://openalex.org/I4210120115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085262529","display_name":"Florian Metze","orcid":"https://orcid.org/0000-0002-6663-8600"},"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":"Florian Metze","raw_affiliation_strings":["Language Technology Institute, Carnegie Mellon University, Pittsburgh, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technology Institute, Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110454109","display_name":"Samarjit Das","orcid":null},"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":"Samarjit Das","raw_affiliation_strings":["Robert Bosch LLC, Research and Technology Center, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robert Bosch LLC, Research and Technology Center, USA","institution_ids":["https://openalex.org/I4210120115"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1804,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.45850968,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"6832","last_page":"6836"},"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":0.9937000274658203,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9671000242233276,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8368370532989502},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5810809135437012},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5731180906295776},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4996504783630371},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48568448424339294},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.4719354808330536},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4702794849872589},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4230611026287079},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4122650921344757},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33328258991241455},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.2549217641353607},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.23075538873672485},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.14909249544143677}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8368370532989502},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5810809135437012},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5731180906295776},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4996504783630371},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48568448424339294},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.4719354808330536},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4702794849872589},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4230611026287079},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4122650921344757},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33328258991241455},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2549217641353607},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.23075538873672485},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.14909249544143677},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8462479","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462479","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Life in Land","id":"https://metadata.un.org/sdg/15","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W2010792435","https://openalex.org/W2043701535","https://openalex.org/W2117539524","https://openalex.org/W2163605009","https://openalex.org/W2250539671","https://openalex.org/W2593116425","https://openalex.org/W2676925568","https://openalex.org/W2775505379","https://openalex.org/W2963877232","https://openalex.org/W2964345931","https://openalex.org/W2964350391","https://openalex.org/W3013795017","https://openalex.org/W4293665662","https://openalex.org/W6684191040","https://openalex.org/W6694260854","https://openalex.org/W6729831399","https://openalex.org/W6738607494"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W1984634519","https://openalex.org/W4245955731","https://openalex.org/W2547431347"],"abstract_inverted_index":{"The":[0,62,157],"lack":[1],"of":[2,65,89,93,132,141,155],"strong":[3,146],"labels":[4],"has":[5],"severely":[6],"limited":[7],"the":[8,66,86,99,115,128,133,139],"state-of-the-art":[9,104],"fully":[10],"supervised":[11],"audio":[12,34,60,63,87,129,148,178],"tagging":[13,130,149],"systems":[14],"to":[15,18,33,47,111,119,123,176],"be":[16,161,172],"scaled":[17],"larger":[19],"dataset.":[20],"Meanwhile,":[21],"audio-visual":[22],"learning":[23,80],"models":[24],"based":[25,76],"on":[26,77,127,166],"unlabeled":[27],"videos":[28],"have":[29],"been":[30],"successfully":[31],"applied":[32],"tagging,":[35],"but":[36],"they":[37],"are":[38],"inevitably":[39],"resource":[40],"hungry":[41],"and":[42,71,108,118,170],"require":[43],"a":[44,54,69,90,145,167],"long":[45],"time":[46],"train.":[48],"In":[49],"this":[50],"work,":[51],"we":[52],"propose":[53],"light-weight,":[55],"multimodal":[56],"framework":[57,67],"for":[58],"environmental":[59],"tagging.":[61],"branch":[64,101],"is":[68,83],"convolutional":[70],"recurrent":[72],"neural":[73],"network":[74],"(CRNN)":[75],"multiple":[78],"instance":[79],"(MIL).":[81],"It":[82],"trained":[84,162],"with":[85],"tracks":[88],"large":[91],"collection":[92],"weakly":[94],"labeled":[95],"YouTube":[96],"video":[97,100,116,142],"excerpts;":[98],"uses":[102],"pretrained":[103],"image":[105],"recognition":[106],"networks":[107],"word":[109],"embeddings":[110],"extract":[112],"information":[113,143],"from":[114],"track":[117],"map":[120],"visual":[121],"objects":[122],"sound":[124],"events.":[125],"Experiments":[126],"task":[131],"DCASE":[134],"2017":[135],"challenge":[136],"show":[137],"that":[138],"incorporation":[140],"improves":[144],"baseline":[147],"system":[150,159],"by":[151],"5.3%":[152],"in":[153],"terms":[154],"F1score.":[156],"entire":[158],"can":[160,171],"within":[163],"6":[164],"hours":[165],"single":[168],"GPU,":[169],"easily":[173],"carried":[174],"over":[175],"other":[177],"tasks":[179],"such":[180],"as":[181],"speech":[182],"sentimental":[183],"analysis.":[184]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}