{"id":"https://openalex.org/W3171685354","doi":"https://doi.org/10.1109/icme51207.2021.9428227","title":"Low Bitrates Audio Object Coding Using Convolutional Auto-Encoder and Densenet Mixture Model","display_name":"Low Bitrates Audio Object Coding Using Convolutional Auto-Encoder and Densenet Mixture Model","publication_year":2021,"publication_date":"2021-06-09","ids":{"openalex":"https://openalex.org/W3171685354","doi":"https://doi.org/10.1109/icme51207.2021.9428227","mag":"3171685354"},"language":"en","primary_location":{"id":"doi:10.1109/icme51207.2021.9428227","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme51207.2021.9428227","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Multimedia and Expo (ICME)","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/A5069771172","display_name":"Yulin Wu","orcid":"https://orcid.org/0000-0003-1940-2141"},"institutions":[{"id":"https://openalex.org/I174442536","display_name":"South Central Minzu University","ror":"https://ror.org/03d7sax13","country_code":"CN","type":"education","lineage":["https://openalex.org/I174442536"]},{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yulin Wu","raw_affiliation_strings":["Wuhan University,National Engineering Research Center for Multimedia Software, School of Computer Science,China","National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, China","Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University,National Engineering Research Center for Multimedia Software, School of Computer Science,China","institution_ids":["https://openalex.org/I174442536"]},{"raw_affiliation_string":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087726516","display_name":"Ruimin Hu","orcid":"https://orcid.org/0000-0002-0290-5757"},"institutions":[{"id":"https://openalex.org/I174442536","display_name":"South Central Minzu University","ror":"https://ror.org/03d7sax13","country_code":"CN","type":"education","lineage":["https://openalex.org/I174442536"]},{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruimin Hu","raw_affiliation_strings":["Wuhan University,National Engineering Research Center for Multimedia Software, School of Computer Science,China","Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University, China","National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University,National Engineering Research Center for Multimedia Software, School of Computer Science,China","institution_ids":["https://openalex.org/I174442536"]},{"raw_affiliation_string":"Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University, China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019900046","display_name":"Chenhao Hu","orcid":"https://orcid.org/0000-0002-0096-0488"},"institutions":[{"id":"https://openalex.org/I174442536","display_name":"South Central Minzu University","ror":"https://ror.org/03d7sax13","country_code":"CN","type":"education","lineage":["https://openalex.org/I174442536"]},{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenhao Hu","raw_affiliation_strings":["Wuhan University,National Engineering Research Center for Multimedia Software, School of Computer Science,China","National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University,National Engineering Research Center for Multimedia Software, School of Computer Science,China","institution_ids":["https://openalex.org/I174442536"]},{"raw_affiliation_string":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044380704","display_name":"Shanfa Ke","orcid":null},"institutions":[{"id":"https://openalex.org/I174442536","display_name":"South Central Minzu University","ror":"https://ror.org/03d7sax13","country_code":"CN","type":"education","lineage":["https://openalex.org/I174442536"]},{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shanfa Ke","raw_affiliation_strings":["Wuhan University,National Engineering Research Center for Multimedia Software, School of Computer Science,China","National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University,National Engineering Research Center for Multimedia Software, School of Computer Science,China","institution_ids":["https://openalex.org/I174442536"]},{"raw_affiliation_string":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100636685","display_name":"Gang Li","orcid":"https://orcid.org/0000-0001-8368-0125"},"institutions":[{"id":"https://openalex.org/I174442536","display_name":"South Central Minzu University","ror":"https://ror.org/03d7sax13","country_code":"CN","type":"education","lineage":["https://openalex.org/I174442536"]},{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Li","raw_affiliation_strings":["Wuhan University,National Engineering Research Center for Multimedia Software, School of Computer Science,China","National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University,National Engineering Research Center for Multimedia Software, School of Computer Science,China","institution_ids":["https://openalex.org/I174442536"]},{"raw_affiliation_string":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100401931","display_name":"Xiaochen Wang","orcid":"https://orcid.org/0000-0003-4177-7580"},"institutions":[{"id":"https://openalex.org/I174442536","display_name":"South Central Minzu University","ror":"https://ror.org/03d7sax13","country_code":"CN","type":"education","lineage":["https://openalex.org/I174442536"]},{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]},{"id":"https://openalex.org/I4210105229","display_name":"City University of Hong Kong, Shenzhen Research Institute","ror":"https://ror.org/00xc0ma20","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210105229"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaochen Wang","raw_affiliation_strings":["Wuhan University,National Engineering Research Center for Multimedia Software, School of Computer Science,China","Research Institute of Wuhan University in Shenzhen, China","National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University,National Engineering Research Center for Multimedia Software, School of Computer Science,China","institution_ids":["https://openalex.org/I174442536"]},{"raw_affiliation_string":"Research Institute of Wuhan University in Shenzhen, China","institution_ids":["https://openalex.org/I4210105229","https://openalex.org/I37461747"]},{"raw_affiliation_string":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, China","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"11","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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/T11309","display_name":"Music and Audio Processing","score":0.9984999895095825,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9957000017166138,"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":0.8326734304428101},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6386757493019104},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.5936341285705566},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.5426152348518372},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.5216432213783264},{"id":"https://openalex.org/keywords/convolutional-code","display_name":"Convolutional code","score":0.5037981867790222},{"id":"https://openalex.org/keywords/sub-band-coding","display_name":"Sub-band coding","score":0.45139169692993164},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44801634550094604},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4005109965801239},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.38446927070617676},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34804201126098633},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.23102262616157532}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8326734304428101},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6386757493019104},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.5936341285705566},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.5426152348518372},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5216432213783264},{"id":"https://openalex.org/C157899210","wikidata":"https://www.wikidata.org/wiki/Q1395022","display_name":"Convolutional code","level":3,"score":0.5037981867790222},{"id":"https://openalex.org/C98526533","wikidata":"https://www.wikidata.org/wiki/Q1691938","display_name":"Sub-band coding","level":3,"score":0.45139169692993164},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44801634550094604},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4005109965801239},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.38446927070617676},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34804201126098633},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23102262616157532},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme51207.2021.9428227","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme51207.2021.9428227","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1485861648","https://openalex.org/W1920010643","https://openalex.org/W2070145845","https://openalex.org/W2104907433","https://openalex.org/W2126675686","https://openalex.org/W2127851351","https://openalex.org/W2136655611","https://openalex.org/W2166223512","https://openalex.org/W2687790454","https://openalex.org/W2762718569","https://openalex.org/W2918769791","https://openalex.org/W2963446712","https://openalex.org/W2972838721","https://openalex.org/W2997035796","https://openalex.org/W4298310324","https://openalex.org/W6766320909","https://openalex.org/W6767933961","https://openalex.org/W7030363128"],"related_works":["https://openalex.org/W2132373020","https://openalex.org/W2096049278","https://openalex.org/W2158434271","https://openalex.org/W2118305611","https://openalex.org/W1901617521","https://openalex.org/W1857623347","https://openalex.org/W2744599249","https://openalex.org/W2354332708","https://openalex.org/W2109142991","https://openalex.org/W2350061705"],"abstract_inverted_index":{"The":[0],"efficient":[1],"transmission":[2,38],"of":[3,39,66,70,91,101,116,120],"the":[4,33,37,64,81,88,99,110,126],"audio":[5,12,40,49,71,127],"objects":[6,41],"can":[7,86,96],"be":[8],"achieved":[9],"by":[10],"spatial":[11],"object":[13,30],"coding":[14,50],"(SAOC)":[15],"method":[16,51,136],"that":[17,28,134],"conveys":[18],"a":[19,47],"mono":[20],"downmix":[21],"signal":[22],"together":[23],"with":[24,52],"side":[25,67,92,102,121],"information":[26,68,93,103,122],"parameters":[27,69,94],"enable":[29],"reconstruction":[31],"in":[32,109],"decoder.":[34],"To":[35],"allow":[36],"at":[42,129],"low":[43,117,130,143],"bitrates,":[44],"we":[45],"present":[46],"new":[48],"convolutional":[53,58],"auto-encoder":[54],"(CAE)":[55],"and":[56,95],"dense":[57],"network":[59],"(DenseNet)":[60],"mixture":[61],"model,":[62],"optimizing":[63],"compression":[65],"objects.":[72],"It":[73],"has":[74],"two":[75],"main":[76],"advantages:":[77],"1)":[78],"Different":[79],"from":[80],"linear":[82],"transform":[83],"methods,":[84],"CAE":[85],"dig":[87],"nonlinear":[89],"relationship":[90],"effectively":[97],"reduce":[98],"dimension":[100],"parameters;":[104],"2)":[105],"DenseNet":[106],"is":[107],"adding":[108],"decoder":[111],"to":[112],"make":[113],"full":[114],"use":[115],"dimensional":[118],"features":[119],"parameters,":[123],"which":[124],"improves":[125],"quality":[128],"bitrate.":[131],"Experiments":[132],"show":[133],"our":[135],"outperforms":[137],"base-line":[138],"methods":[139],"permitting":[140],"bitrates":[141],"as":[142,144],"1":[145],"kbps":[146],"per":[147],"object.":[148]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}