{"id":"https://openalex.org/W4392902609","doi":"https://doi.org/10.1109/icassp48485.2024.10447970","title":"Enhancing Spatial Audio Generation with Source Separation and Channel Panning Loss","display_name":"Enhancing Spatial Audio Generation with Source Separation and Channel Panning Loss","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902609","doi":"https://doi.org/10.1109/icassp48485.2024.10447970"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447970","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447970","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/A5026162456","display_name":"Wootaek L\u0131m","orcid":"https://orcid.org/0000-0002-5523-6294"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]},{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Wootaek Lim","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,South Korea","Korea Advanced Institute of Science and Technology, South Korea","Electronics and Telecommunications Research Institute, South Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Electronics and Telecommunications Research Institute, South Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056437111","display_name":"Juhan Nam","orcid":"https://orcid.org/0000-0003-2664-2119"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Juhan Nam","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,South Korea","Korea Advanced Institute of Science and Technology, South Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5026162456"],"corresponding_institution_ids":["https://openalex.org/I142401562","https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":0.7321,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.64771166,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"8321","last_page":"8325"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9987999796867371,"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":0.9987999796867371,"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":0.998199999332428,"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":0.9901000261306763,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/ambisonics","display_name":"Ambisonics","score":0.9506626129150391},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8128006458282471},{"id":"https://openalex.org/keywords/spatialization","display_name":"Spatialization","score":0.6538589596748352},{"id":"https://openalex.org/keywords/panning","display_name":"Panning (audio)","score":0.5432736277580261},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5400001406669617},{"id":"https://openalex.org/keywords/transcoding","display_name":"Transcoding","score":0.47934871912002563},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.456675261259079},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45081669092178345},{"id":"https://openalex.org/keywords/loudspeaker","display_name":"Loudspeaker","score":0.41254034638404846},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10460841655731201}],"concepts":[{"id":"https://openalex.org/C47726159","wikidata":"https://www.wikidata.org/wiki/Q457547","display_name":"Ambisonics","level":3,"score":0.9506626129150391},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8128006458282471},{"id":"https://openalex.org/C2777031145","wikidata":"https://www.wikidata.org/wiki/Q4430987","display_name":"Spatialization","level":2,"score":0.6538589596748352},{"id":"https://openalex.org/C108944566","wikidata":"https://www.wikidata.org/wiki/Q1524510","display_name":"Panning (audio)","level":4,"score":0.5432736277580261},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5400001406669617},{"id":"https://openalex.org/C134535813","wikidata":"https://www.wikidata.org/wiki/Q1888734","display_name":"Transcoding","level":2,"score":0.47934871912002563},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.456675261259079},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45081669092178345},{"id":"https://openalex.org/C157138929","wikidata":"https://www.wikidata.org/wiki/Q570","display_name":"Loudspeaker","level":2,"score":0.41254034638404846},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10460841655731201},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C78762247","wikidata":"https://www.wikidata.org/wiki/Q1273174","display_name":"Petroleum engineering","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/C15336307","wikidata":"https://www.wikidata.org/wiki/Q1766051","display_name":"Lens (geology)","level":2,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C124913957","wikidata":"https://www.wikidata.org/wiki/Q1232548","display_name":"Zoom","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447970","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447970","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322093","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1993882792","https://openalex.org/W2031865865","https://openalex.org/W2108598243","https://openalex.org/W2166223512","https://openalex.org/W2171235719","https://openalex.org/W2302255633","https://openalex.org/W2560474170","https://openalex.org/W2763188033","https://openalex.org/W2950388022","https://openalex.org/W2952218014","https://openalex.org/W2962935966","https://openalex.org/W2963218389","https://openalex.org/W2963452667","https://openalex.org/W2970906079","https://openalex.org/W3034742263","https://openalex.org/W3037149862","https://openalex.org/W3098994423","https://openalex.org/W3099330747","https://openalex.org/W4236344233","https://openalex.org/W4281492411","https://openalex.org/W4287608901","https://openalex.org/W4312779270","https://openalex.org/W6746914816","https://openalex.org/W6751512325","https://openalex.org/W6754782314","https://openalex.org/W6785011006"],"related_works":["https://openalex.org/W2031865865","https://openalex.org/W852058501","https://openalex.org/W3090853884","https://openalex.org/W2971546352","https://openalex.org/W2614575298","https://openalex.org/W2556213910","https://openalex.org/W2951782199","https://openalex.org/W2923117679","https://openalex.org/W2403497458","https://openalex.org/W348798723"],"abstract_inverted_index":{"Spatial":[0],"audio":[1,21,39,49,80,91],"is":[2,11],"essential":[3],"for":[4,29],"many":[5],"immersive":[6],"content":[7],"services;":[8],"however,":[9],"it":[10,52,96],"challenging":[12],"to":[13,59,105,157],"obtain":[14],"or":[15],"create":[16],"it.":[17],"Recently,":[18],"multimodal-based":[19],"ambisonic":[20,48,70,148],"generation":[22,81],"has":[23],"emerged":[24],"as":[25,38],"a":[26,75,123,138],"promising":[27],"approach":[28],"addressing":[30],"the":[31,54,62,84,101,106,111,115,132,147,159,164,174,182],"limitation.":[32],"It":[33],"combines":[34],"multiple":[35],"modalities,":[36],"such":[37],"and":[40,42,67,77,89,162],"video,":[41],"provides":[43],"more":[44],"intuitive":[45],"control":[46],"of":[47,56,114,146,155],"generation.":[50],"Moreover,":[51],"leverages":[53],"advantages":[55],"machine-learning":[57],"methods":[58],"automatically":[60],"learn":[61],"correlation":[63],"between":[64,143],"different":[65,153],"features":[66,88],"generate":[68],"high-quality":[69],"sounds.":[71],"Herein,":[72],"we":[73,121,136],"propose":[74,137],"separation-":[76],"localization-based":[78],"spatial":[79],"model.":[82],"First,":[83],"network":[85],"extracts":[86],"visual":[87,107],"separates":[90],"into":[92],"sound":[93,103],"sources.":[94],"Then,":[95],"conducts":[97],"localization":[98,133],"by":[99],"mapping":[100],"separated":[102],"sources":[104],"features.":[108],"To":[109,130],"overcome":[110],"performance":[112,134,180],"limitation":[113],"previous":[116],"self-supervised":[117],"source":[118,125],"separation":[119],"approach,":[120],"employ":[122],"pretrained":[124],"separator":[126],"with":[127,167],"superior":[128],"performance.":[129],"improve":[131],"further,":[135],"channel":[139,145],"panning":[140],"loss":[141],"function":[142],"each":[144],"signal.":[149],"We":[150],"use":[151],"three":[152],"types":[154],"datasets":[156],"train":[158],"model":[160,176],"experimentally":[161],"evaluate":[163],"proposed":[165,175],"method":[166],"four":[168],"metrics.":[169],"The":[170],"results":[171],"show":[172],"that":[173],"achieves":[177],"better":[178],"spatialization":[179],"than":[181],"baseline":[183],"models.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}
