{"id":"https://openalex.org/W4375869103","doi":"https://doi.org/10.1109/icassp49357.2023.10096050","title":"Unifying Speech Enhancement and Separation with Gradient Modulation for End-to-End Noise-Robust Speech Separation","display_name":"Unifying Speech Enhancement and Separation with Gradient Modulation for End-to-End Noise-Robust Speech Separation","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869103","doi":"https://doi.org/10.1109/icassp49357.2023.10096050"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096050","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096050","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/A5074544822","display_name":"Yu\u2010Chen Hu","orcid":"https://orcid.org/0000-0002-5055-3645"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yuchen Hu","raw_affiliation_strings":["Nanyang Technological University,School of Computer Science and Engineering,Singapore","School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,School of Computer Science and Engineering,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418370","display_name":"Chen Chen","orcid":"https://orcid.org/0000-0001-7587-3314"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chen Chen","raw_affiliation_strings":["Nanyang Technological University,School of Computer Science and Engineering,Singapore","School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,School of Computer Science and Engineering,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023152132","display_name":"Heqing Zou","orcid":"https://orcid.org/0000-0003-0038-2822"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Heqing Zou","raw_affiliation_strings":["Nanyang Technological University,School of Computer Science and Engineering,Singapore","School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,School of Computer Science and Engineering,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100681425","display_name":"Xionghu Zhong","orcid":"https://orcid.org/0000-0002-7533-2347"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xionghu Zhong","raw_affiliation_strings":["Hunan University,College of Computer Science and Electronic Engineering,China","College of Computer Science and Electronic Engineering, Hunan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University,College of Computer Science and Electronic Engineering,China","institution_ids":["https://openalex.org/I16609230"]},{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070872826","display_name":"Eng Siong Chng","orcid":"https://orcid.org/0000-0001-6257-7399"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Eng Siong Chng","raw_affiliation_strings":["Nanyang Technological University,School of Computer Science and Engineering,Singapore","School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,School of Computer Science and Engineering,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":null,"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/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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/computer-science","display_name":"Computer science","score":0.7425950765609741},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6955878734588623},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6671773195266724},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6063982844352722},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5512545704841614},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5299416780471802},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5000081062316895},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.49348771572113037},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.4714577794075012},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4539676308631897},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.39212313294410706},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3314187228679657},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.24829703569412231},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.17925229668617249}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7425950765609741},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6955878734588623},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6671773195266724},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6063982844352722},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5512545704841614},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5299416780471802},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5000081062316895},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.49348771572113037},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.4714577794075012},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4539676308631897},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.39212313294410706},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3314187228679657},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.24829703569412231},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.17925229668617249},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/icassp49357.2023.10096050","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096050","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":[{"display_name":"Peace, Justice and strong institutions","score":0.6399999856948853,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W2064675550","https://openalex.org/W2227273290","https://openalex.org/W2734774145","https://openalex.org/W2952218014","https://openalex.org/W2964058413","https://openalex.org/W2972541922","https://openalex.org/W3015199127","https://openalex.org/W3027008958","https://openalex.org/W3099330747","https://openalex.org/W3142252347","https://openalex.org/W3163652268","https://openalex.org/W3185109982","https://openalex.org/W3196965931","https://openalex.org/W3206531472","https://openalex.org/W3214142715","https://openalex.org/W4283021642","https://openalex.org/W4297841258","https://openalex.org/W4300978696","https://openalex.org/W4372266968","https://openalex.org/W4372267073","https://openalex.org/W4375868977","https://openalex.org/W4375869127","https://openalex.org/W4375869189","https://openalex.org/W4382202533","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6739901393","https://openalex.org/W6777776875","https://openalex.org/W6803594737","https://openalex.org/W6844662008","https://openalex.org/W6846585435","https://openalex.org/W6846626936","https://openalex.org/W6846774901"],"related_works":["https://openalex.org/W2771275309","https://openalex.org/W2485008119","https://openalex.org/W3115290769","https://openalex.org/W2181961565","https://openalex.org/W2031585553","https://openalex.org/W2901778484","https://openalex.org/W2765976216","https://openalex.org/W2116686031","https://openalex.org/W2991037759","https://openalex.org/W3015225820"],"abstract_inverted_index":{"Recent":[0],"studies":[1],"in":[2,107],"neural":[3],"network-based":[4],"monaural":[5],"speech":[6,42,61,80,104],"separation":[7,64,84],"(SS)":[8],"have":[9],"achieved":[10],"a":[11,56,75,120],"remarkable":[12],"success":[13],"thanks":[14],"to":[15,59,68,99,109,125],"increasing":[16],"ability":[17],"of":[18,153],"long":[19],"sequence":[20],"modeling.":[21],"However,":[22],"they":[23],"would":[24],"degrade":[25],"significantly":[26],"when":[27,115],"put":[28],"under":[29],"realistic":[30],"noisy":[31],"conditions,":[32],"as":[33],"the":[34,47,127,142],"background":[35],"noise":[36,101],"could":[37],"be":[38],"mistaken":[39],"for":[40,89,102],"speaker\u2019s":[41],"and":[43,63,83,129,147,156],"thus":[44],"interfere":[45],"with":[46,65,86,150],"separated":[48],"sources.":[49],"To":[50],"alleviate":[51],"this":[52],"problem,":[53],"we":[54,72,118],"propose":[55,119],"novel":[57],"network":[58,77],"unify":[60],"enhancement":[62,81],"gradient":[66,121],"modulation":[67,122],"improve":[69],"noise-robustness.":[70],"Specifically,":[71],"first":[73],"build":[74],"unified":[76],"by":[78,95],"combining":[79],"(SE)":[82],"modules,":[85],"multi-task":[87],"learning":[88],"optimization,":[90],"where":[91],"SE":[92,128],"is":[93,162],"supervised":[94],"parallel":[96],"clean":[97],"mixture":[98],"reduce":[100],"downstream":[103],"separation.":[105],"Furthermore,":[106],"order":[108],"avoid":[110],"suppressing":[111],"valid":[112],"speaker":[113],"information":[114],"reducing":[116],"noise,":[117],"(GM)":[123],"strategy":[124],"harmonize":[126],"SS":[130],"tasks":[131],"from":[132],"optimization":[133],"view.":[134],"Experimental":[135],"results":[136,152],"show":[137],"that":[138],"our":[139],"approach":[140],"achieves":[141],"state-of-the-art":[143],"on":[144],"large-scale":[145],"Libri2Mix-":[146],"Libri3Mix-noisy":[148],"datasets,":[149],"SI-SNRi":[151],"16.0":[154],"dB":[155,158],"15.8":[157],"respectively.":[159],"Our":[160],"code":[161],"available":[163],"at":[164],"GitHub":[165],"<sup":[166],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[167],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[168],".":[169]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}