{"id":"https://openalex.org/W4206996728","doi":"https://doi.org/10.1109/ssci50451.2021.9660125","title":"Separate Sound into STFT Frames to Eliminate Sound Noise Frames in Sound Classification","display_name":"Separate Sound into STFT Frames to Eliminate Sound Noise Frames in Sound Classification","publication_year":2021,"publication_date":"2021-12-05","ids":{"openalex":"https://openalex.org/W4206996728","doi":"https://doi.org/10.1109/ssci50451.2021.9660125"},"language":"en","primary_location":{"id":"doi:10.1109/ssci50451.2021.9660125","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci50451.2021.9660125","pdf_url":null,"source":{"id":"https://openalex.org/S4363604921","display_name":"2021 IEEE Symposium Series on Computational Intelligence (SSCI)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Symposium Series on Computational Intelligence (SSCI)","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/A5032785756","display_name":"Thanh Tran","orcid":"https://orcid.org/0000-0002-8262-2414"},"institutions":[{"id":"https://openalex.org/I56475706","display_name":"Mid Sweden University","ror":"https://ror.org/019k1pd13","country_code":"SE","type":"education","lineage":["https://openalex.org/I56475706"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Thanh Tran","raw_affiliation_strings":["Mid Sweden University, Sundsvall, Sweden"],"affiliations":[{"raw_affiliation_string":"Mid Sweden University, Sundsvall, Sweden","institution_ids":["https://openalex.org/I56475706"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033594304","display_name":"Bui Huy Kien","orcid":"https://orcid.org/0000-0002-6166-2724"},"institutions":[{"id":"https://openalex.org/I27429435","display_name":"Kyoto Institute of Technology","ror":"https://ror.org/00965ax52","country_code":"JP","type":"education","lineage":["https://openalex.org/I27429435"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kien Bui Huy","raw_affiliation_strings":["Kyoto Institute of Technology, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Kyoto Institute of Technology, Kyoto, Japan","institution_ids":["https://openalex.org/I27429435"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091402542","display_name":"Nhat Truong Pham","orcid":"https://orcid.org/0000-0002-8086-6722"},"institutions":[{"id":"https://openalex.org/I141445968","display_name":"Ton Duc Thang University","ror":"https://ror.org/01drq0835","country_code":"VN","type":"education","lineage":["https://openalex.org/I141445968"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Nhat Truong Pham","raw_affiliation_strings":["Ton Due Thang University, Ho Chi Minh City, Vietnam"],"affiliations":[{"raw_affiliation_string":"Ton Due Thang University, Ho Chi Minh City, Vietnam","institution_ids":["https://openalex.org/I141445968"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014275270","display_name":"Marco Carrat\u00f9","orcid":"https://orcid.org/0000-0001-8146-6088"},"institutions":[{"id":"https://openalex.org/I131729948","display_name":"University of Salerno","ror":"https://ror.org/0192m2k53","country_code":"IT","type":"education","lineage":["https://openalex.org/I131729948"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Marco Carratu","raw_affiliation_strings":["University of Salerno, Fisciano, Italy"],"affiliations":[{"raw_affiliation_string":"University of Salerno, Fisciano, Italy","institution_ids":["https://openalex.org/I131729948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062085198","display_name":"Consolatina Liguori","orcid":"https://orcid.org/0000-0003-3254-2069"},"institutions":[{"id":"https://openalex.org/I131729948","display_name":"University of Salerno","ror":"https://ror.org/0192m2k53","country_code":"IT","type":"education","lineage":["https://openalex.org/I131729948"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Consolatina Liguori","raw_affiliation_strings":["University of Salerno, Fisciano, Italy"],"affiliations":[{"raw_affiliation_string":"University of Salerno, Fisciano, Italy","institution_ids":["https://openalex.org/I131729948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014048644","display_name":"Jan Lundgren","orcid":"https://orcid.org/0000-0003-1819-6200"},"institutions":[{"id":"https://openalex.org/I56475706","display_name":"Mid Sweden University","ror":"https://ror.org/019k1pd13","country_code":"SE","type":"education","lineage":["https://openalex.org/I56475706"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Jan Lundgren","raw_affiliation_strings":["Mid Sweden University, Sundsvall, Sweden"],"affiliations":[{"raw_affiliation_string":"Mid Sweden University, Sundsvall, Sweden","institution_ids":["https://openalex.org/I56475706"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5032785756"],"corresponding_institution_ids":["https://openalex.org/I56475706"],"apc_list":null,"apc_paid":null,"fwci":0.6881,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.74882471,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9995999932289124,"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":0.9887999892234802,"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/short-time-fourier-transform","display_name":"Short-time Fourier transform","score":0.8276265859603882},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.733063280582428},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6449218392372131},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6169899106025696},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6137263774871826},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5301937460899353},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5037056803703308},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.4962790608406067},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.4402598738670349},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.4313663840293884},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.4226319193840027},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2514860928058624},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.142035573720932},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11629647016525269},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07455229759216309}],"concepts":[{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.8276265859603882},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.733063280582428},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6449218392372131},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6169899106025696},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6137263774871826},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5301937460899353},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5037056803703308},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.4962790608406067},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.4402598738670349},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.4313663840293884},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.4226319193840027},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2514860928058624},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.142035573720932},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11629647016525269},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07455229759216309},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ssci50451.2021.9660125","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci50451.2021.9660125","pdf_url":null,"source":{"id":"https://openalex.org/S4363604921","display_name":"2021 IEEE Symposium Series on Computational Intelligence (SSCI)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Symposium Series on Computational Intelligence (SSCI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1618108441","https://openalex.org/W1686810756","https://openalex.org/W2097117768","https://openalex.org/W2164207156","https://openalex.org/W2167752533","https://openalex.org/W2168515119","https://openalex.org/W2509065397","https://openalex.org/W2632052911","https://openalex.org/W2798158991","https://openalex.org/W2799388264","https://openalex.org/W2899829828","https://openalex.org/W2955425717","https://openalex.org/W2963125010","https://openalex.org/W2963859210","https://openalex.org/W3008335638","https://openalex.org/W3014419348","https://openalex.org/W3014593905","https://openalex.org/W3039519447","https://openalex.org/W3082319384","https://openalex.org/W3086539361","https://openalex.org/W3097470552","https://openalex.org/W3098270842","https://openalex.org/W3098357269","https://openalex.org/W3123940584","https://openalex.org/W3139373250","https://openalex.org/W4294087448","https://openalex.org/W6637373629","https://openalex.org/W6746059548"],"related_works":["https://openalex.org/W2120540196","https://openalex.org/W3095343173","https://openalex.org/W2381036744","https://openalex.org/W2288135719","https://openalex.org/W2323749021","https://openalex.org/W2533590149","https://openalex.org/W2901989338","https://openalex.org/W82005754","https://openalex.org/W3094316140","https://openalex.org/W2059119686"],"abstract_inverted_index":{"Sounds":[0],"always":[1],"contain":[2],"acoustic":[3],"noise":[4,7,20,152],"and":[5,90,103,109,153,168,179],"background":[6],"that":[8,40,94,131,145],"affects":[9],"the":[10,13,22,26,29,42,58,74,88,124,139,146,176],"accuracy":[11,83],"of":[12,19,28,158,165,175],"sound":[14,23,30,37,44,66,75,166],"classification":[15,31,125],"system.":[16],"Hence,":[17],"suppression":[18],"in":[21,87,156],"can":[24],"improve":[25],"robustness":[27],"model.":[32],"This":[33],"paper":[34],"investigated":[35],"a":[36,68,169],"separation":[38],"technique":[39],"separates":[41],"input":[43],"into":[45,67,76,116],"many":[46,77],"overlapped-content":[47],"Short-Time":[48],"Fourier":[49],"Transform":[50],"(STFT)":[51],"frames.":[52],"Our":[53],"approach":[54,148],"is":[55,149,181],"different":[56],"from":[57,93,133],"traditional":[59],"STFT":[60,70,78],"conversion":[61],"method,":[62],"which":[63,112],"converts":[64],"each":[65],"single":[69],"image.":[71],"Contradictory,":[72],"separating":[73],"frames":[79,98,111,135],"improves":[80],"model":[81],"prediction":[82],"by":[84],"increasing":[85],"variability":[86],"data":[89],"therefore":[91],"learning":[92,118],"variability.":[95],"These":[96],"separated":[97],"are":[99,113],"saved":[100],"as":[101,107],"images":[102],"then":[104,114],"labeled":[105],"manually":[106],"clean":[108],"noisy":[110,170],"fed":[115],"transfer":[117],"convolutional":[119],"neural":[120],"networks":[121],"(CNNs)":[122],"for":[123],"task.":[126],"The":[127,141],"pre-trained":[128],"CNN":[129],"architectures":[130],"learn":[132],"these":[134],"become":[136],"robust":[137,150],"against":[138,151],"noise.":[140],"experimental":[142],"results":[143,180],"show":[144],"proposed":[147,177],"achieves":[154],"94.14%":[155],"terms":[157],"classifying":[159],"21":[160],"classes":[161,164],"including":[162],"20":[163],"events":[167],"class.":[171],"An":[172],"open-source":[173],"repository":[174],"method":[178],"available":[182],"at":[183],"https://github.com/nhattruongpham/soundSepsound.":[184]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}