{"id":"https://openalex.org/W3161731123","doi":"https://doi.org/10.1109/icassp39728.2021.9414018","title":"Capturing Temporal Dependencies Through Future Prediction for CNN-Based Audio Classifiers","display_name":"Capturing Temporal Dependencies Through Future Prediction for CNN-Based Audio Classifiers","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3161731123","doi":"https://doi.org/10.1109/icassp39728.2021.9414018","mag":"3161731123"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414018","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414018","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5057908066","display_name":"Hongwei Song","orcid":"https://orcid.org/0000-0003-1928-8182"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongwei Song","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101508830","display_name":"Jiqing Han","orcid":"https://orcid.org/0000-0002-4297-4300"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiqing Han","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087019132","display_name":"Shiwen Deng","orcid":"https://orcid.org/0000-0001-8964-3165"},"institutions":[{"id":"https://openalex.org/I134052481","display_name":"Harbin Normal University","ror":"https://ror.org/0270y6950","country_code":"CN","type":"education","lineage":["https://openalex.org/I134052481"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiwen Deng","raw_affiliation_strings":["School of Mathematical Science, Harbin Normal University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematical Science, Harbin Normal University, China","institution_ids":["https://openalex.org/I134052481"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001133136","display_name":"Zhihao Du","orcid":"https://orcid.org/0000-0003-3509-9322"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihao Du","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"101","last_page":"105"},"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":0.9977999925613403,"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":0.9947999715805054,"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":0.8515306711196899},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5814493298530579},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5536580085754395},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.5221410393714905},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5115271806716919},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5114259123802185},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.4915038049221039},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.48597395420074463},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.45842069387435913},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.437677264213562},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41230690479278564},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32031863927841187}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8515306711196899},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5814493298530579},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5536580085754395},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.5221410393714905},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5115271806716919},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5114259123802185},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.4915038049221039},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.48597395420074463},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.45842069387435913},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.437677264213562},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41230690479278564},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32031863927841187},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414018","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414018","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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","score":0.5799999833106995,"id":"https://metadata.un.org/sdg/15"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1819710477","https://openalex.org/W1972567154","https://openalex.org/W2038484192","https://openalex.org/W2052666245","https://openalex.org/W2133824856","https://openalex.org/W2509065397","https://openalex.org/W2563031223","https://openalex.org/W2604959036","https://openalex.org/W2768188490","https://openalex.org/W2794150026","https://openalex.org/W2842511635","https://openalex.org/W2899771611","https://openalex.org/W2908510526","https://openalex.org/W2930682606","https://openalex.org/W2948210185","https://openalex.org/W2962711843","https://openalex.org/W2962968839","https://openalex.org/W2963550089","https://openalex.org/W2964328535","https://openalex.org/W2970206392","https://openalex.org/W2972425456","https://openalex.org/W2973049979","https://openalex.org/W3008707468","https://openalex.org/W3016659311","https://openalex.org/W3045062880","https://openalex.org/W3095753917","https://openalex.org/W3098357269","https://openalex.org/W3158553615","https://openalex.org/W4297808394","https://openalex.org/W6736327223","https://openalex.org/W6745930336","https://openalex.org/W6756040250","https://openalex.org/W6757817989","https://openalex.org/W6761553608","https://openalex.org/W6775888111","https://openalex.org/W6778636332","https://openalex.org/W6780226713","https://openalex.org/W6781150751","https://openalex.org/W6844194202"],"related_works":["https://openalex.org/W2468279273","https://openalex.org/W2354198838","https://openalex.org/W1989130879","https://openalex.org/W2103419012","https://openalex.org/W2988126442","https://openalex.org/W1974414866","https://openalex.org/W2057568687","https://openalex.org/W2063982682","https://openalex.org/W2338543196","https://openalex.org/W2025953124"],"abstract_inverted_index":{"This":[0],"paper":[1],"focuses":[2],"on":[3,102,128],"the":[4,11,31,41,50,55,65,73,94,120,124],"problem":[5],"of":[6,63,106],"temporal":[7,21,38,91],"dependency":[8],"modeling":[9],"in":[10,47],"CNN-based":[12,42],"models":[13],"for":[14,88],"audio":[15,20,43,108,115],"classification":[16,51],"tasks.":[17],"To":[18],"capture":[19],"dependencies":[22,39,92],"using":[23],"CNNs,":[24],"we":[25,53],"take":[26],"a":[27,80,103,135],"different":[28],"approach":[29,122],"from":[30,139],"purely":[32],"architecture-induced":[33],"method":[34],"and":[35,112,133],"explicitly":[36],"encode":[37],"into":[40],"classifiers.":[44],"More":[45],"specifically,":[46],"addition":[48],"to":[49,58],"objective,":[52],"require":[54],"CNN":[56],"model":[57,85,99,137],"solve":[59],"an":[60],"auxiliary":[61],"task":[62],"predicting":[64],"future":[66],"features,":[67],"which":[68],"is":[69,86,100],"formulated":[70],"by":[71],"leveraging":[72],"Contrastive":[74],"Predictive":[75],"Coding":[76],"(CPC)":[77],"loss.":[78],"Furthermore,":[79],"novel":[81],"hierarchical":[82],"CPC":[83],"(HCPC)":[84],"proposed":[87,98,121],"capturing":[89],"multi-level":[90],"at":[93],"same":[95],"time.":[96],"The":[97],"evaluated":[101],"wide":[104],"range":[105],"non-speech":[107],"signals,":[109],"including":[110],"musical":[111],"in-the-wild":[113],"environmental":[114],"signals.":[116],"We":[117],"show":[118],"that":[119],"improves":[123],"backbone":[125],"CNNs":[126],"consistently":[127],"all":[129],"tested":[130],"benchmark":[131],"datasets":[132],"outperforms":[134],"DenseNet":[136],"trained":[138],"scratch.":[140]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}