{"id":"https://openalex.org/W4392903118","doi":"https://doi.org/10.1109/icassp48485.2024.10448214","title":"Noise-Aware Speech Separation with Contrastive Learning","display_name":"Noise-Aware Speech Separation with Contrastive Learning","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903118","doi":"https://doi.org/10.1109/icassp48485.2024.10448214"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448214","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448214","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5104118551","display_name":"Zizheng Zhang","orcid":"https://orcid.org/0009-0009-3721-0208"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zizheng Zhang","raw_affiliation_strings":["Peking University,School of Software and Microelectronics,China","School of Software and Microelectronics, Peking University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,School of Software and Microelectronics,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Software and Microelectronics, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418547","display_name":"Chen Chen","orcid":"https://orcid.org/0000-0003-1957-6432"},"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/A5001703612","display_name":"Hsin-Hung Chen","orcid":"https://orcid.org/0000-0002-3406-741X"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hsin-Hung Chen","raw_affiliation_strings":["Georgia Institute of Technology,School of Electrical and Computer Engineering,USA","School of Electrical and Computer Engineering, Georgia Institute of Technology, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,School of Electrical and Computer Engineering,USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100408604","display_name":"Xiang Liu","orcid":"https://orcid.org/0000-0002-2634-1888"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Liu","raw_affiliation_strings":["Peking University,School of Software and Microelectronics,China","School of Software and Microelectronics, Peking University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,School of Software and Microelectronics,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Software and Microelectronics, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","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":"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":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1381","last_page":"1385"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987999796867371,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.998199999332428,"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/computer-science","display_name":"Computer science","score":0.7683601379394531},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.738164484500885},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6925100088119507},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.6208420991897583},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5285141468048096},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5234915018081665},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4991579055786133},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.46283555030822754},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.44212105870246887},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4262581467628479},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.40568646788597107},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36224472522735596},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.16325998306274414},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0670042634010315},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.05455288290977478}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7683601379394531},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.738164484500885},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6925100088119507},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.6208420991897583},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5285141468048096},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5234915018081665},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4991579055786133},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.46283555030822754},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.44212105870246887},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4262581467628479},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.40568646788597107},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36224472522735596},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.16325998306274414},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0670042634010315},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.05455288290977478},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448214","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448214","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2127851351","https://openalex.org/W2170864449","https://openalex.org/W2221409856","https://openalex.org/W2734774145","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2964058413","https://openalex.org/W2972541922","https://openalex.org/W3015199127","https://openalex.org/W3027008958","https://openalex.org/W3099330747","https://openalex.org/W3108316907","https://openalex.org/W3163652268","https://openalex.org/W3167533889","https://openalex.org/W3206531472","https://openalex.org/W4221156109","https://openalex.org/W4239396298","https://openalex.org/W4372266968","https://openalex.org/W4384026591","https://openalex.org/W6752051073","https://openalex.org/W6799474351"],"related_works":["https://openalex.org/W2135485548","https://openalex.org/W2002243964","https://openalex.org/W2022538999","https://openalex.org/W3090086172","https://openalex.org/W1955763106","https://openalex.org/W2373767407","https://openalex.org/W2025188156","https://openalex.org/W2187949121","https://openalex.org/W4375869276","https://openalex.org/W1585241115"],"abstract_inverted_index":{"Recently,":[0],"speech":[1,22,54],"separation":[2],"(SS)":[3],"task":[4],"has":[5],"achieved":[6],"remarkable":[7],"progress":[8],"driven":[9],"by":[10],"deep":[11],"learning":[12,89],"technique.":[13],"However,":[14],"it":[15,73],"is":[16,30],"still":[17],"challenging":[18],"to":[19,32,36,51,106,120,135],"separate":[20],"target":[21],"from":[23,96],"noisy":[24,60,148],"mixture,":[25],"as":[26,67],"the":[27,53,97,108,122],"neural":[28],"model":[29],"vulnerable":[31],"assign":[33],"background":[34,65],"noise":[35,66,92,113,123],"each":[37],"speaker.":[38],"In":[39],"this":[40],"paper,":[41],"we":[42,85],"propose":[43],"a":[44,79],"noise-aware":[45],"SS":[46],"(NASS)":[47],"method,":[48],"which":[49],"aims":[50,105],"improve":[52],"quality":[55],"for":[56],"separated":[57,126],"signals":[58],"under":[59],"conditions.":[61],"Specifically,":[62],"NASS":[63,132],"views":[64],"an":[68],"additional":[69],"output":[70],"and":[71,93,100,114,142,146],"predicts":[72],"along":[74],"with":[75,150],"other":[76,115],"speakers":[77,116],"in":[78,125],"mask-based":[80],"manner.":[81],"To":[82],"effectively":[83],"denoise,":[84],"introduce":[86],"patch-wise":[87],"contrastive":[88],"(PCL)":[90],"between":[91,111],"speaker":[94],"representations":[95],"decoder":[98],"input":[99],"encoder":[101],"output.":[102],"PCL":[103],"loss":[104],"minimize":[107],"mutual":[109],"information":[110,124],"predicted":[112],"at":[117],"multiple-patch":[118],"level":[119],"suppress":[121],"signals.":[127],"Experimental":[128],"results":[129],"show":[130],"that":[131],"achieves":[133],"1":[134],"2dB":[136],"SI-SNRi":[137],"or":[138],"SDRi":[139],"over":[140],"DPRNN":[141],"Sepformer":[143],"on":[144],"WHAM!":[145],"LibriMix":[147],"datasets,":[149],"less":[151],"than":[152],"0.1M":[153],"parameter":[154],"increase.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}