{"id":"https://openalex.org/W3161447515","doi":"https://doi.org/10.1109/icassp39728.2021.9413522","title":"Subspectral Normalization for Neural Audio Data Processing","display_name":"Subspectral Normalization for Neural Audio Data Processing","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3161447515","doi":"https://doi.org/10.1109/icassp39728.2021.9413522","mag":"3161447515"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413522","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413522","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5112998078","display_name":"Simyung Chang","orcid":"https://orcid.org/0000-0001-7750-191X"},"institutions":[{"id":"https://openalex.org/I19268510","display_name":"Qualcomm (United Kingdom)","ror":"https://ror.org/04d3djg48","country_code":"GB","type":"company","lineage":["https://openalex.org/I19268510","https://openalex.org/I4210087596"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Simyung Chang","raw_affiliation_strings":["Qualcomm AI Research","Qualcomm Korea YH"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qualcomm AI Research","institution_ids":["https://openalex.org/I19268510"]},{"raw_affiliation_string":"Qualcomm Korea YH","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069883233","display_name":"Hyung Woo Park","orcid":"https://orcid.org/0000-0002-5341-9249"},"institutions":[{"id":"https://openalex.org/I19268510","display_name":"Qualcomm (United Kingdom)","ror":"https://ror.org/04d3djg48","country_code":"GB","type":"company","lineage":["https://openalex.org/I19268510","https://openalex.org/I4210087596"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hyoungwoo Park","raw_affiliation_strings":["Qualcomm AI Research","Qualcomm Korea YH"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qualcomm AI Research","institution_ids":["https://openalex.org/I19268510"]},{"raw_affiliation_string":"Qualcomm Korea YH","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077458889","display_name":"Janghoon Cho","orcid":null},"institutions":[{"id":"https://openalex.org/I19268510","display_name":"Qualcomm (United Kingdom)","ror":"https://ror.org/04d3djg48","country_code":"GB","type":"company","lineage":["https://openalex.org/I19268510","https://openalex.org/I4210087596"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Janghoon Cho","raw_affiliation_strings":["Qualcomm AI Research","Qualcomm Korea YH"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qualcomm AI Research","institution_ids":["https://openalex.org/I19268510"]},{"raw_affiliation_string":"Qualcomm Korea YH","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010227336","display_name":"Hyunsin Park","orcid":"https://orcid.org/0000-0003-3556-5792"},"institutions":[{"id":"https://openalex.org/I19268510","display_name":"Qualcomm (United Kingdom)","ror":"https://ror.org/04d3djg48","country_code":"GB","type":"company","lineage":["https://openalex.org/I19268510","https://openalex.org/I4210087596"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hyunsin Park","raw_affiliation_strings":["Qualcomm AI Research","Qualcomm Korea YH"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qualcomm AI Research","institution_ids":["https://openalex.org/I19268510"]},{"raw_affiliation_string":"Qualcomm Korea YH","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091430620","display_name":"Sungrack Yun","orcid":"https://orcid.org/0000-0003-2462-3854"},"institutions":[{"id":"https://openalex.org/I19268510","display_name":"Qualcomm (United Kingdom)","ror":"https://ror.org/04d3djg48","country_code":"GB","type":"company","lineage":["https://openalex.org/I19268510","https://openalex.org/I4210087596"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sungrack Yun","raw_affiliation_strings":["Qualcomm AI Research","Qualcomm Korea YH"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qualcomm AI Research","institution_ids":["https://openalex.org/I19268510"]},{"raw_affiliation_string":"Qualcomm Korea YH","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089149225","display_name":"Kyuwoong Hwang","orcid":null},"institutions":[{"id":"https://openalex.org/I19268510","display_name":"Qualcomm (United Kingdom)","ror":"https://ror.org/04d3djg48","country_code":"GB","type":"company","lineage":["https://openalex.org/I19268510","https://openalex.org/I4210087596"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Kyuwoong Hwang","raw_affiliation_strings":["Qualcomm AI Research","Qualcomm Korea YH"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qualcomm AI Research","institution_ids":["https://openalex.org/I19268510"]},{"raw_affiliation_string":"Qualcomm Korea YH","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.0884,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.92187186,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"850","last_page":"854"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9976999759674072,"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":0.9976999759674072,"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/T10860","display_name":"Speech and Audio Processing","score":0.9954000115394592,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9937000274658203,"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/normalization","display_name":"Normalization (sociology)","score":0.8008514642715454},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7766859531402588},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5126346945762634},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5076440572738647},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4304543137550354},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4209926426410675},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32878825068473816},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.1978936493396759},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.13816818594932556}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.8008514642715454},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7766859531402588},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5126346945762634},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5076440572738647},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4304543137550354},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4209926426410675},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32878825068473816},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.1978936493396759},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.13816818594932556},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413522","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413522","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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":31,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1836465849","https://openalex.org/W1995562189","https://openalex.org/W2194775991","https://openalex.org/W2284050935","https://openalex.org/W2407023693","https://openalex.org/W2502312327","https://openalex.org/W2509065397","https://openalex.org/W2526050071","https://openalex.org/W2627092829","https://openalex.org/W2883935097","https://openalex.org/W2897557658","https://openalex.org/W2930364467","https://openalex.org/W2962711843","https://openalex.org/W2963685250","https://openalex.org/W2964187693","https://openalex.org/W2972951785","https://openalex.org/W2973226577","https://openalex.org/W2987999870","https://openalex.org/W3015530480","https://openalex.org/W3098357269","https://openalex.org/W4250482878","https://openalex.org/W4295723153","https://openalex.org/W6637373629","https://openalex.org/W6638667902","https://openalex.org/W6695676441","https://openalex.org/W6714171909","https://openalex.org/W6724804524","https://openalex.org/W6752516136","https://openalex.org/W6755978804","https://openalex.org/W6780226713"],"related_works":["https://openalex.org/W2591697403","https://openalex.org/W2944728705","https://openalex.org/W2904022177","https://openalex.org/W2359348847","https://openalex.org/W3011538607","https://openalex.org/W4294432981","https://openalex.org/W4321441197","https://openalex.org/W2953716828","https://openalex.org/W2469820710","https://openalex.org/W4321276295"],"abstract_inverted_index":{"Convolutional":[0],"Neural":[1],"Networks":[2],"are":[3],"widely":[4],"used":[5],"in":[6,31,45],"various":[7],"machine":[8],"learning":[9],"domains.":[10],"In":[11,69,121],"image":[12],"processing,":[13],"the":[14,28,32,46,59,65,79,111,115,122,134],"features":[15],"can":[16,102,131],"be":[17,103],"obtained":[18],"by":[19],"applying":[20],"2D":[21,60],"convolution":[22,61],"to":[23,63,105],"all":[24],"spatial":[25],"dimensions":[26],"of":[27],"input.":[29],"However,":[30],"audio":[33,125],"case,":[34],"frequency":[35,47,66,81],"domain":[36],"input":[37,80],"like":[38],"Mel-Spectrogram":[39],"has":[40],"different":[41,90],"and":[42,87],"unique":[43],"characteristics":[44],"dimension.":[48],"Thus,":[49],"there":[50],"is":[51],"a":[52,55,89,118],"need":[53],"for":[54,92],"method":[56,109],"that":[57,101,129],"allows":[58],"layer":[62],"handle":[64],"dimension":[67,82],"differently.":[68],"this":[70],"work,":[71],"we":[72,127],"introduce":[73],"SubSpectral":[74],"Normalization":[75],"(SSN),":[76],"which":[77],"splits":[78],"into":[83],"several":[84],"groups":[85],"(sub-bands)":[86],"performs":[88],"normalization":[91],"each":[93,106],"group.":[94,107],"SSN":[95,130],"also":[96],"includes":[97],"an":[98],"affine":[99],"transformation":[100],"applied":[104],"Our":[108],"removes":[110],"inter-frequency":[112],"deflection":[113],"while":[114],"network":[116],"learns":[117],"frequency-aware":[119],"characteristic.":[120],"experiments":[123],"with":[124],"data,":[126],"observed":[128],"efficiently":[132],"improve":[133],"network\u2019s":[135],"performance.":[136]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
