{"id":"https://openalex.org/W4386764374","doi":"https://doi.org/10.1109/waspaa58266.2023.10248179","title":"Optimizing Higher-Order Directional Audio Coding with Adaptive Mixing and Energy Matching for Ambisonic Compression and Upmixing","display_name":"Optimizing Higher-Order Directional Audio Coding with Adaptive Mixing and Energy Matching for Ambisonic Compression and Upmixing","publication_year":2023,"publication_date":"2023-09-15","ids":{"openalex":"https://openalex.org/W4386764374","doi":"https://doi.org/10.1109/waspaa58266.2023.10248179"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa58266.2023.10248179","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa58266.2023.10248179","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://research.aalto.fi/en/publications/6da1d933-c832-434d-b3f8-547ba9ebc0c6","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061205893","display_name":"Christoph Hold","orcid":"https://orcid.org/0000-0001-6579-265X"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Christoph Hold","raw_affiliation_strings":["Aalto University,Department of Signal Processing and Acoustics,Espoo,Finland","Department of Signal Processing and Acoustics, Aalto University, Espoo, Finland"],"affiliations":[{"raw_affiliation_string":"Aalto University,Department of Signal Processing and Acoustics,Espoo,Finland","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"Department of Signal Processing and Acoustics, Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033768731","display_name":"Leo McCormack","orcid":"https://orcid.org/0000-0003-2448-4444"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Leo McCormack","raw_affiliation_strings":["Aalto University,Department of Signal Processing and Acoustics,Espoo,Finland","Department of Signal Processing and Acoustics, Aalto University, Espoo, Finland"],"affiliations":[{"raw_affiliation_string":"Aalto University,Department of Signal Processing and Acoustics,Espoo,Finland","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"Department of Signal Processing and Acoustics, Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010846139","display_name":"Archontis Politis","orcid":"https://orcid.org/0000-0002-0595-2356"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Archontis Politis","raw_affiliation_strings":["Tampere University,Faculty of Information Technology and Communication Sciences,Finland","Faculty of Information Technology and Communication Sciences, Tampere University, Finland"],"affiliations":[{"raw_affiliation_string":"Tampere University,Faculty of Information Technology and Communication Sciences,Finland","institution_ids":["https://openalex.org/I166825849"]},{"raw_affiliation_string":"Faculty of Information Technology and Communication Sciences, Tampere University, Finland","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033040947","display_name":"Ville Pulkki","orcid":"https://orcid.org/0000-0003-3460-9677"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Ville Pulkki","raw_affiliation_strings":["Aalto University,Department of Signal Processing and Acoustics,Espoo,Finland","Department of Signal Processing and Acoustics, Aalto University, Espoo, Finland"],"affiliations":[{"raw_affiliation_string":"Aalto University,Department of Signal Processing and Acoustics,Espoo,Finland","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"Department of Signal Processing and Acoustics, Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5061205893"],"corresponding_institution_ids":["https://openalex.org/I9927081"],"apc_list":null,"apc_paid":null,"fwci":0.3966,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.57103893,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9991999864578247,"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":0.9987999796867371,"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/ambisonics","display_name":"Ambisonics","score":0.9152179956436157},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7019108533859253},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.5894498229026794},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.4305363893508911},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3857946991920471},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.32930243015289307},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.20638170838356018},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.168462872505188},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1547519862651825},{"id":"https://openalex.org/keywords/loudspeaker","display_name":"Loudspeaker","score":0.11694788932800293}],"concepts":[{"id":"https://openalex.org/C47726159","wikidata":"https://www.wikidata.org/wiki/Q457547","display_name":"Ambisonics","level":3,"score":0.9152179956436157},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7019108533859253},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.5894498229026794},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.4305363893508911},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3857946991920471},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32930243015289307},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.20638170838356018},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.168462872505188},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1547519862651825},{"id":"https://openalex.org/C157138929","wikidata":"https://www.wikidata.org/wiki/Q570","display_name":"Loudspeaker","level":2,"score":0.11694788932800293},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/waspaa58266.2023.10248179","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa58266.2023.10248179","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/124171","is_oa":true,"landing_page_url":"https://research.aalto.fi/en/publications/6da1d933-c832-434d-b3f8-547ba9ebc0c6","pdf_url":null,"source":{"id":"https://openalex.org/S4306401662","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"acceptedVersion"},{"id":"pmh:oai:trepo.tuni.fi:10024/207365","is_oa":false,"landing_page_url":"https://trepo.tuni.fi/handle/10024/207365","pdf_url":null,"source":{"id":"https://openalex.org/S7407055260","display_name":"Trepo - Institutional Repository of Tampere University","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"conference"}],"best_oa_location":{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/124171","is_oa":true,"landing_page_url":"https://research.aalto.fi/en/publications/6da1d933-c832-434d-b3f8-547ba9ebc0c6","pdf_url":null,"source":{"id":"https://openalex.org/S4306401662","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"acceptedVersion"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.9200000166893005,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1504048097","https://openalex.org/W1552336412","https://openalex.org/W1565136158","https://openalex.org/W1583730476","https://openalex.org/W1991170630","https://openalex.org/W2028075876","https://openalex.org/W2089473323","https://openalex.org/W2164299562","https://openalex.org/W2559832253","https://openalex.org/W2761804494","https://openalex.org/W2774712265","https://openalex.org/W2936088203","https://openalex.org/W2948183496","https://openalex.org/W2951122330","https://openalex.org/W2953950894","https://openalex.org/W3180801944","https://openalex.org/W3215930811","https://openalex.org/W3217252117","https://openalex.org/W4312927510","https://openalex.org/W4366338339","https://openalex.org/W4388755861","https://openalex.org/W6630208109","https://openalex.org/W6633198442","https://openalex.org/W6633659081","https://openalex.org/W6634826758","https://openalex.org/W6730352180","https://openalex.org/W6763984898","https://openalex.org/W6798587278","https://openalex.org/W6858945797"],"related_works":["https://openalex.org/W2359734170","https://openalex.org/W2358502346","https://openalex.org/W2360518820","https://openalex.org/W2365974637","https://openalex.org/W2365437481","https://openalex.org/W1555023417","https://openalex.org/W2372102971","https://openalex.org/W2367759895","https://openalex.org/W2357328267","https://openalex.org/W3117083091"],"abstract_inverted_index":{"In":[0,90],"order":[1],"to":[2,12,19,37,60,81,85,115,210],"transmit":[3],"sound-scenes":[4,97],"encoded":[5],"into":[6],"the":[7,24,45,62,65,93,103,109,116,157,162,189,221,226,230],"higher-order":[8,26],"Ambisonics":[9],"(HOA)":[10],"format":[11],"low-bandwidth":[13],"devices,":[14],"transmission":[15],"codecs":[16],"are":[17,57,127,148,153],"needed":[18],"reduce":[20],"data":[21],"requirements.":[22],"Recently,":[23],"model-based":[25],"directional":[27],"audio":[28,48,166,237],"coding":[29,238],"(HO-DirAC)":[30],"method":[31],"was":[32],"formulated":[33,149],"for":[34,102,125],"HOA":[35,38,160],"input":[36],"output.":[39],"Compression":[40],"is":[41,176],"achieved":[42],"by":[43],"reducing":[44],"number":[46],"of":[47,119,138,159,188,225],"transport":[49,55,165,206],"channels":[50,56,207],"through":[51],"spatial":[52,71,143,236],"discretization.":[53],"These":[54,192],"then":[58],"used":[59,209],"reconstruct":[61,211],"scene":[63,75],"on":[64,69,142],"receiving":[66],"end":[67],"based":[68,141],"accompanying":[70],"metadata.":[72],"This":[73],"reconstructed":[74],"may":[76],"also":[77,195],"be":[78,113],"optionally":[79],"upmixed":[80],"a":[82,169,181,198],"higher-order;":[83],"leading":[84],"an":[86],"enhancement":[87],"in":[88,156],"spatial-resolution.":[89],"this":[91],"paper,":[92],"authors":[94,110],"analyze":[95],"certain":[96],"that":[98,151],"were":[99,194,208],"especially":[100],"challenging":[101],"previously":[104],"proposed":[105,190,227],"HO-DirAC":[106,126],"framework,":[107],"which":[108,129],"postulate":[111],"could":[112],"attributed":[114],"lower-order":[117],"reconstruction":[118,158,183],"diffuse":[120],"sound-field":[121],"components.":[122],"Three":[123],"optimizations":[124],"proposed,":[128],"all":[130],"employ":[131],"optimal":[132],"adaptive":[133],"mixing":[134],"and/or":[135],"energy":[136],"matching":[137],"Ambisonic":[139],"components":[140],"covariance":[144],"matrices.":[145],"The":[146,218],"methods":[147],"such":[150],"they":[152],"applied":[154],"directly":[155],"from":[161],"spatially":[163],"discrete":[164],"signals.":[167],"Notably,":[168],"dedicated":[170],"low-complexity":[171,231],"solution":[172],"without":[173],"additional":[174],"side-information":[175],"derived.":[177],"Instrumental":[178],"evaluations":[179],"confirm":[180],"reduced":[182],"error":[184],"when":[185],"using":[186],"either":[187],"optimizations.":[191],"improvements":[193],"demonstrated":[196],"via":[197],"perceptual":[199,223],"evaluation,":[200],"whereby":[201],"four,":[202],"six,":[203],"and":[204,239],"twelve":[205],"(and":[212],"upmix":[213],"to)":[214],"fifth-order":[215],"reference":[216],"sound-scenes.":[217],"evaluation":[219],"highlighted":[220],"high":[222],"performance":[224],"optimizations,":[228],"including":[229],"version,":[232],"thereby":[233],"improving":[234],"parametric":[235],"reproduction.":[240]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-28T08:17:26.163206","created_date":"2025-10-10T00:00:00"}
