{"id":"https://openalex.org/W4372346374","doi":"https://doi.org/10.1109/icassp49357.2023.10095021","title":"Regression to Classification: Waveform Encoding for Neural Field-Based Audio Signal Representation","display_name":"Regression to Classification: Waveform Encoding for Neural Field-Based Audio Signal Representation","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372346374","doi":"https://doi.org/10.1109/icassp49357.2023.10095021"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095021","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095021","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5100743709","display_name":"Taesoo Kim","orcid":"https://orcid.org/0000-0002-7440-2067"},"institutions":[{"id":"https://openalex.org/I4210119025","display_name":"Korea Tourism Organization","ror":"https://ror.org/02gsggh97","country_code":"KR","type":"government","lineage":["https://openalex.org/I4210119025"]},{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"TaeSoo Kim","raw_affiliation_strings":["KT,Republic of Korea","KT, Republic of Korea","Department of Electrical and Computer Engineering, Sungkyunkwan University, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KT,Republic of Korea","institution_ids":["https://openalex.org/I4210119025"]},{"raw_affiliation_string":"KT, Republic of Korea","institution_ids":[]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Sungkyunkwan University, Republic of Korea","institution_ids":["https://openalex.org/I848706"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059784120","display_name":"Daniel Rho","orcid":"https://orcid.org/0000-0002-8568-9489"},"institutions":[{"id":"https://openalex.org/I4210119025","display_name":"Korea Tourism Organization","ror":"https://ror.org/02gsggh97","country_code":"KR","type":"government","lineage":["https://openalex.org/I4210119025"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Daniel Rho","raw_affiliation_strings":["KT,Republic of Korea","KT, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KT,Republic of Korea","institution_ids":["https://openalex.org/I4210119025"]},{"raw_affiliation_string":"KT, Republic of Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063932450","display_name":"Gahui Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119025","display_name":"Korea Tourism Organization","ror":"https://ror.org/02gsggh97","country_code":"KR","type":"government","lineage":["https://openalex.org/I4210119025"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Gahui Lee","raw_affiliation_strings":["KT,Republic of Korea","KT, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KT,Republic of Korea","institution_ids":["https://openalex.org/I4210119025"]},{"raw_affiliation_string":"KT, Republic of Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072597078","display_name":"Jaehan Park","orcid":"https://orcid.org/0000-0002-6209-7595"},"institutions":[{"id":"https://openalex.org/I4210119025","display_name":"Korea Tourism Organization","ror":"https://ror.org/02gsggh97","country_code":"KR","type":"government","lineage":["https://openalex.org/I4210119025"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"JaeHan Park","raw_affiliation_strings":["KT,Republic of Korea","KT, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KT,Republic of Korea","institution_ids":["https://openalex.org/I4210119025"]},{"raw_affiliation_string":"KT, Republic of Korea","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063908850","display_name":"Jong Hwan Ko","orcid":"https://orcid.org/0000-0003-4434-4318"},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jong Hwan Ko","raw_affiliation_strings":["Sungkyunkwan University,Department of Electrical and Computer Engineering,Republic of Korea","Department of Electrical and Computer Engineering, Sungkyunkwan University, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sungkyunkwan University,Department of Electrical and Computer Engineering,Republic of Korea","institution_ids":["https://openalex.org/I848706"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Sungkyunkwan University, Republic of Korea","institution_ids":["https://openalex.org/I848706"]}]}],"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":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9954000115394592,"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"}},{"id":"https://openalex.org/T10688","display_name":"Image and Signal Denoising Methods","score":0.9908000230789185,"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/waveform","display_name":"Waveform","score":0.8475971817970276},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.7202084064483643},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6716750264167786},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6015729904174805},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5907291769981384},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5740392208099365},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.5577248334884644},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5239917635917664},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.5218873620033264},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.49578437209129333},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4645063579082489},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44042977690696716},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4247910678386688},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.31384003162384033},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20878148078918457}],"concepts":[{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.8475971817970276},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.7202084064483643},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6716750264167786},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6015729904174805},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5907291769981384},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5740392208099365},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.5577248334884644},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5239917635917664},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.5218873620033264},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49578437209129333},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4645063579082489},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44042977690696716},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4247910678386688},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.31384003162384033},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20878148078918457},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095021","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095021","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1989337816","https://openalex.org/W2052666245","https://openalex.org/W2165899180","https://openalex.org/W2519091744","https://openalex.org/W2757519008","https://openalex.org/W2953318193","https://openalex.org/W2963627347","https://openalex.org/W3036843665","https://openalex.org/W3109585842","https://openalex.org/W3170344659","https://openalex.org/W3203570626","https://openalex.org/W3210995378","https://openalex.org/W4221151978","https://openalex.org/W4287756134","https://openalex.org/W4308259687","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6774631009","https://openalex.org/W6779753539","https://openalex.org/W6780179280","https://openalex.org/W6796907879","https://openalex.org/W6803861248"],"related_works":["https://openalex.org/W2384738070","https://openalex.org/W2065633372","https://openalex.org/W2109142991","https://openalex.org/W2023208959","https://openalex.org/W2792033502","https://openalex.org/W2735200146","https://openalex.org/W2328398924","https://openalex.org/W2056404380","https://openalex.org/W4312624015","https://openalex.org/W1590604789"],"abstract_inverted_index":{"Neural":[0],"fields,":[1],"also":[2,16],"known":[3],"as":[4,60,65,73],"coordinate-based":[5],"representations,":[6],"are":[7],"an":[8],"emerging":[9],"signal":[10],"representation":[11,35,71],"framework.":[12],"This":[13],"approach":[14],"has":[15],"been":[17],"used":[18],"to":[19],"represent":[20],"audio":[21,26,92,101],"signals,":[22],"but":[23],"the":[24,43,70,91],"generated":[25],"often":[27],"contains":[28],"noise.":[29],"To":[30],"reduce":[31],"noise":[32],"and":[33,68],"improve":[34,90],"quality,":[36],"we":[37],"propose":[38],"using":[39,57],"waveform":[40,87],"encoding":[41,88],"in":[42],"neural":[44,95],"field.":[45],"Instead":[46],"of":[47,94,100],"yielding":[48],"real":[49],"numbers":[50],"for":[51],"each":[52],"temporal":[53],"coordinate,":[54],"this":[55],"involves":[56],"discrete":[58],"integers":[59,64],"outputs,":[61],"with":[62],"waveform-encoded":[63],"target":[66],"classes,":[67],"treating":[69],"problem":[72],"a":[74,79,98],"classification":[75],"task":[76],"rather":[77],"than":[78],"regression":[80],"problem.":[81],"The":[82],"experimental":[83],"results":[84],"show":[85],"that":[86],"can":[89],"quality":[93],"fields":[96],"across":[97],"variety":[99],"datasets.":[102]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
