{"id":"https://openalex.org/W4383219073","doi":"https://doi.org/10.1109/dsp58604.2023.10167992","title":"ConSep: a Noise- and Reverberation-Robust Speech Separation Framework by Magnitude Conditioning","display_name":"ConSep: a Noise- and Reverberation-Robust Speech Separation Framework by Magnitude Conditioning","publication_year":2023,"publication_date":"2023-06-11","ids":{"openalex":"https://openalex.org/W4383219073","doi":"https://doi.org/10.1109/dsp58604.2023.10167992"},"language":"en","primary_location":{"id":"doi:10.1109/dsp58604.2023.10167992","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/dsp58604.2023.10167992","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 24th International Conference on Digital Signal Processing (DSP)","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/A5088927394","display_name":"Kuan-Hsun Ho","orcid":null},"institutions":[{"id":"https://openalex.org/I134161618","display_name":"National Taiwan Normal University","ror":"https://ror.org/059dkdx38","country_code":"TW","type":"education","lineage":["https://openalex.org/I134161618"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Kuan-Hsun Ho","raw_affiliation_strings":["National Taiwan Normal University,Department of Computer Science and Information Engineering,Taipei,Taiwan","Department of Computer Science and Information Engineering, National Taiwan Normal University, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan Normal University,Department of Computer Science and Information Engineering,Taipei,Taiwan","institution_ids":["https://openalex.org/I134161618"]},{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Taiwan Normal University, Taipei, Taiwan","institution_ids":["https://openalex.org/I134161618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019048236","display_name":"Jeih-weih Hung","orcid":"https://orcid.org/0000-0001-9366-3070"},"institutions":[{"id":"https://openalex.org/I193365169","display_name":"National Chi Nan University","ror":"https://ror.org/03ha6v181","country_code":"TW","type":"education","lineage":["https://openalex.org/I193365169"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jeih-Weih Hung","raw_affiliation_strings":["National Chi Nan University,Department of Electrical Engineering,Nantou,Taiwan","Department of Electrical Engineering, National Chi Nan University, Nantou, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Chi Nan University,Department of Electrical Engineering,Nantou,Taiwan","institution_ids":["https://openalex.org/I193365169"]},{"raw_affiliation_string":"Department of Electrical Engineering, National Chi Nan University, Nantou, Taiwan","institution_ids":["https://openalex.org/I193365169"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053222355","display_name":"Berlin Chen","orcid":"https://orcid.org/0000-0003-0693-8932"},"institutions":[{"id":"https://openalex.org/I134161618","display_name":"National Taiwan Normal University","ror":"https://ror.org/059dkdx38","country_code":"TW","type":"education","lineage":["https://openalex.org/I134161618"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Berlin Chen","raw_affiliation_strings":["National Taiwan Normal University,Department of Computer Science and Information Engineering,Taipei,Taiwan","Department of Computer Science and Information Engineering, National Taiwan Normal University, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan Normal University,Department of Computer Science and Information Engineering,Taipei,Taiwan","institution_ids":["https://openalex.org/I134161618"]},{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Taiwan Normal University, Taipei, Taiwan","institution_ids":["https://openalex.org/I134161618"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06806467,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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":1.0,"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":1.0,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9987000226974487,"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":0.9975000023841858,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.9057403206825256},{"id":"https://openalex.org/keywords/anechoic-chamber","display_name":"Anechoic chamber","score":0.8426193594932556},{"id":"https://openalex.org/keywords/short-time-fourier-transform","display_name":"Short-time Fourier transform","score":0.7390812635421753},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6957994699478149},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6576195955276489},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5647901296615601},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.5159297585487366},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.502126932144165},{"id":"https://openalex.org/keywords/magnitude","display_name":"Magnitude (astronomy)","score":0.4991471767425537},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.46422335505485535},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4262761175632477},{"id":"https://openalex.org/keywords/time-domain","display_name":"Time domain","score":0.4259132444858551},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.41602978110313416},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40692827105522156},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.39447885751724243},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3872596025466919},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2485913634300232},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.17154884338378906},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1523650884628296},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.14937704801559448},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09641635417938232},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09562316536903381},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07872915267944336}],"concepts":[{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.9057403206825256},{"id":"https://openalex.org/C149712133","wikidata":"https://www.wikidata.org/wiki/Q332774","display_name":"Anechoic chamber","level":2,"score":0.8426193594932556},{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.7390812635421753},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6957994699478149},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6576195955276489},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5647901296615601},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.5159297585487366},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.502126932144165},{"id":"https://openalex.org/C126691448","wikidata":"https://www.wikidata.org/wiki/Q2028919","display_name":"Magnitude (astronomy)","level":2,"score":0.4991471767425537},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.46422335505485535},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4262761175632477},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.4259132444858551},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.41602978110313416},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40692827105522156},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.39447885751724243},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3872596025466919},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2485913634300232},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.17154884338378906},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1523650884628296},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.14937704801559448},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09641635417938232},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09562316536903381},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07872915267944336},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dsp58604.2023.10167992","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/dsp58604.2023.10167992","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 24th International Conference on Digital Signal Processing (DSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.550000011920929}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2048142341","https://openalex.org/W2050551142","https://openalex.org/W2734774145","https://openalex.org/W2760103357","https://openalex.org/W2952218014","https://openalex.org/W2962715207","https://openalex.org/W2963750251","https://openalex.org/W2964058413","https://openalex.org/W2972541922","https://openalex.org/W2981976899","https://openalex.org/W3015191643","https://openalex.org/W3015199127","https://openalex.org/W3015843733","https://openalex.org/W3027637851","https://openalex.org/W3034772996","https://openalex.org/W3093839391","https://openalex.org/W3096893582","https://openalex.org/W3099330747","https://openalex.org/W3163652268","https://openalex.org/W3170088519","https://openalex.org/W3185109982","https://openalex.org/W3201698955","https://openalex.org/W3213661887","https://openalex.org/W4221149546","https://openalex.org/W4296069339","https://openalex.org/W4296069347","https://openalex.org/W4307199125","https://openalex.org/W4312257080","https://openalex.org/W4319862661","https://openalex.org/W4323645825","https://openalex.org/W6772381481","https://openalex.org/W6777701575","https://openalex.org/W6784499681","https://openalex.org/W6848979688"],"related_works":["https://openalex.org/W2289848901","https://openalex.org/W2001172292","https://openalex.org/W2169567031","https://openalex.org/W1849802015","https://openalex.org/W2354873283","https://openalex.org/W2023041720","https://openalex.org/W3097766872","https://openalex.org/W2353977479","https://openalex.org/W2732511158","https://openalex.org/W2402466562"],"abstract_inverted_index":{"Speech":[0],"separation":[1],"has":[2],"recently":[3],"made":[4],"significant":[5],"progress":[6],"thanks":[7],"to":[8,50,69,83],"the":[9,52,79,85,90],"fine-grained":[10],"vision":[11],"used":[12],"in":[13,62,95],"time-domain":[14,47],"methods.":[15],"However,":[16],"several":[17],"studies":[18],"have":[19,93],"shown":[20],"that":[21,58],"adopting":[22],"Short-Time":[23],"Fourier":[24],"Transform":[25],"(STFT)":[26],"for":[27],"feature":[28],"extraction":[29],"could":[30],"be":[31],"beneficial":[32,53],"when":[33],"encountering":[34],"harsher":[35],"conditions,":[36],"such":[37],"as":[38],"noise":[39],"or":[40],"reverberation.":[41],"Therefore,":[42],"we":[43,77,92],"propose":[44],"a":[45],"magnitude-conditioned":[46],"framework,":[48],"ConSep,":[49],"inherit":[51],"characteristics.":[54],"The":[55],"experiment":[56],"shows":[57],"ConSep":[59,82],"promotes":[60],"performance":[61],"anechoic,":[63],"noisy,":[64],"and":[65,74,87],"reverberant":[66],"settings":[67],"compared":[68],"two":[70],"celebrated":[71],"methods,":[72],"SepFormer":[73],"BiSep.":[75],"Furthermore,":[76],"visualize":[78],"components":[80],"of":[81],"strengthen":[84],"advantages":[86],"cohere":[88],"with":[89],"actualities":[91],"found":[94],"preliminary":[96],"studies.":[97]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}