{"id":"https://openalex.org/W4205984622","doi":"https://doi.org/10.1109/mmul.2022.3142752","title":"Distortion Reduction via CAE and DenseNet Mixture Network for Low Bitrate Spatial Audio Object Coding","display_name":"Distortion Reduction via CAE and DenseNet Mixture Network for Low Bitrate Spatial Audio Object Coding","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4205984622","doi":"https://doi.org/10.1109/mmul.2022.3142752"},"language":"en","primary_location":{"id":"doi:10.1109/mmul.2022.3142752","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmul.2022.3142752","pdf_url":null,"source":{"id":"https://openalex.org/S72873717","display_name":"IEEE Multimedia","issn_l":"1070-986X","issn":["1070-986X","1941-0166"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE MultiMedia","raw_type":"journal-article"},"type":"article","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/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":["National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0003-1940-2141","affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, 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/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":["National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-0290-5757","affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100401931","display_name":"Xiaochen Wang","orcid":"https://orcid.org/0000-0003-4177-7580"},"institutions":[{"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":"Xiaochen Wang","raw_affiliation_strings":["National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0003-4177-7580","affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, 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/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":["National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044380704","display_name":"Shanfa Ke","orcid":null},"institutions":[{"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":["National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I37461747"],"apc_list":null,"apc_paid":null,"fwci":0.5656,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.59873172,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"29","issue":"1","first_page":"55","last_page":"64"},"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10822","display_name":"Acoustic Wave Phenomena Research","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8008896708488464},{"id":"https://openalex.org/keywords/sub-band-coding","display_name":"Sub-band coding","score":0.6080575585365295},{"id":"https://openalex.org/keywords/audio-signal-flow","display_name":"Audio signal flow","score":0.598158597946167},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5715758204460144},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.5178883075714111},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.5148522257804871},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.49687984585762024},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.49591073393821716},{"id":"https://openalex.org/keywords/digital-audio-broadcasting","display_name":"Digital audio broadcasting","score":0.4635526239871979},{"id":"https://openalex.org/keywords/aliasing","display_name":"Aliasing","score":0.45432913303375244},{"id":"https://openalex.org/keywords/anti-aliasing","display_name":"Anti-aliasing","score":0.4489709734916687},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4183722138404846},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4152672290802002},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3699437379837036},{"id":"https://openalex.org/keywords/digital-audio","display_name":"Digital audio","score":0.3571424186229706},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.1734730303287506},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12003001570701599},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07536721229553223}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8008896708488464},{"id":"https://openalex.org/C98526533","wikidata":"https://www.wikidata.org/wiki/Q1691938","display_name":"Sub-band coding","level":3,"score":0.6080575585365295},{"id":"https://openalex.org/C167940747","wikidata":"https://www.wikidata.org/wiki/Q63727227","display_name":"Audio signal flow","level":5,"score":0.598158597946167},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5715758204460144},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.5178883075714111},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.5148522257804871},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.49687984585762024},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.49591073393821716},{"id":"https://openalex.org/C2779106878","wikidata":"https://www.wikidata.org/wiki/Q1257510","display_name":"Digital audio broadcasting","level":2,"score":0.4635526239871979},{"id":"https://openalex.org/C4069607","wikidata":"https://www.wikidata.org/wiki/Q868732","display_name":"Aliasing","level":3,"score":0.45432913303375244},{"id":"https://openalex.org/C534633266","wikidata":"https://www.wikidata.org/wiki/Q4774317","display_name":"Anti-aliasing","level":5,"score":0.4489709734916687},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4183722138404846},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4152672290802002},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3699437379837036},{"id":"https://openalex.org/C87687168","wikidata":"https://www.wikidata.org/wiki/Q173114","display_name":"Digital audio","level":4,"score":0.3571424186229706},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.1734730303287506},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12003001570701599},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07536721229553223},{"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/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"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/C136536468","wikidata":"https://www.wikidata.org/wiki/Q1225894","display_name":"Undersampling","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mmul.2022.3142752","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmul.2022.3142752","pdf_url":null,"source":{"id":"https://openalex.org/S72873717","display_name":"IEEE Multimedia","issn_l":"1070-986X","issn":["1070-986X","1941-0166"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE MultiMedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8285155503","display_name":null,"funder_award_id":"61801334","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8570679527","display_name":null,"funder_award_id":"U1803262","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"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":20,"referenced_works":["https://openalex.org/W1530838232","https://openalex.org/W1588397041","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/W2964058413","https://openalex.org/W2972838721","https://openalex.org/W3169335269","https://openalex.org/W3171685354","https://openalex.org/W4298310324","https://openalex.org/W6679997575","https://openalex.org/W6766320909","https://openalex.org/W6767933961"],"related_works":["https://openalex.org/W1983784698","https://openalex.org/W2374437886","https://openalex.org/W2076894244","https://openalex.org/W1554702895","https://openalex.org/W1568040281","https://openalex.org/W2069094726","https://openalex.org/W2119387478","https://openalex.org/W2010168868","https://openalex.org/W2918769791","https://openalex.org/W4205984622"],"abstract_inverted_index":{"Object-based":[0],"audio":[1,12,30,45,53,58,78,87,114],"content":[2],"is":[3],"becoming":[4],"popular":[5],"to":[6,107],"represent":[7],"immersive":[8],"spatial":[9,29,41,110],"sound":[10],"because":[11],"object":[13,31,59],"positions":[14],"can":[15],"be":[16],"totally":[17],"independent":[18],"of":[19,22,27,43,76,112],"the":[20,28,48,51,56,119,123,131],"locations":[21],"available":[23],"loudspeakers.":[24],"The":[25],"encoder":[26],"coding":[32,88],"(SAOC)":[33],"method":[34,89],"transmits":[35],"a":[36,85,100,141],"mono":[37],"downmix":[38],"signal":[39],"with":[40,96,140],"parameters":[42,111],"all":[44,113],"objects,":[46],"and":[47,99,137],"decoder":[49],"reconstructs":[50],"original":[52],"objects.":[54,115],"However,":[55],"decoded":[57,77],"by":[60,126],"SAOC":[61],"has":[62,129],"severe":[63],"aliasing":[64,124],"distortion,":[65],"especially":[66],"at":[67,80],"low":[68,81,142],"bitrates.":[69,82],"This":[70],"study":[71],"focuses":[72],"on":[73],"distortion":[74,125],"reduction":[75],"objects":[79],"We":[83],"present":[84],"new":[86],"via":[90],"nonuniform":[91],"fine":[92],"sub-bands":[93],"division":[94],"strategy":[95],"convolutional":[97,102],"autoencoder":[98],"dense":[101],"network":[103],"mixture":[104],"model,":[105],"aiming":[106],"effectively":[108],"compress":[109],"Evaluations":[116],"indicate":[117],"that":[118],"proposed":[120],"approach":[121],"reduces":[122],"2.02%.":[127],"It":[128],"achieved":[130],"best":[132],"performances":[133],"in":[134],"both":[135],"objective":[136],"subjective":[138],"results":[139],"bitrate":[143],"1":[144],"kb/s":[145],"per":[146],"object.":[147]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
