{"id":"https://openalex.org/W4375869052","doi":"https://doi.org/10.1109/icassp49357.2023.10095979","title":"SEPDIFF: Speech Separation Based on Denoising Diffusion Model","display_name":"SEPDIFF: Speech Separation Based on Denoising Diffusion Model","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869052","doi":"https://doi.org/10.1109/icassp49357.2023.10095979"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095979","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095979","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":"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/A5100427261","display_name":"Bo Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bo Chen","raw_affiliation_strings":["Huawei Technologies,Hangzhou,China","Huawei Technologies, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies,Hangzhou,China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Technologies, Hangzhou, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082457935","display_name":"Chao Wu","orcid":"https://orcid.org/0000-0003-2081-4602"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Wu","raw_affiliation_strings":["Huawei Technologies,Hangzhou,China","Huawei Technologies, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies,Hangzhou,China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Technologies, Hangzhou, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044920762","display_name":"Wenbin Zhao","orcid":"https://orcid.org/0000-0001-8507-6765"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenbin Zhao","raw_affiliation_strings":["Huawei Technologies,Hangzhou,China","Huawei Technologies, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies,Hangzhou,China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Technologies, Hangzhou, China","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100427261"],"corresponding_institution_ids":["https://openalex.org/I2250955327"],"apc_list":null,"apc_paid":null,"fwci":1.2199,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.78756963,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"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":0.9990000128746033,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7932451963424683},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7169298529624939},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6696321964263916},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6238961815834045},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5863209366798401},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5720815658569336},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4603895843029022},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.4501868188381195},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43616583943367004},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4275255799293518},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42532384395599365},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.41265520453453064},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.36455994844436646}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7932451963424683},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7169298529624939},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6696321964263916},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6238961815834045},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5863209366798401},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5720815658569336},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4603895843029022},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.4501868188381195},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43616583943367004},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4275255799293518},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42532384395599365},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.41265520453453064},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.36455994844436646},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095979","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095979","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":0.6800000071525574,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2221409856","https://openalex.org/W2734774145","https://openalex.org/W2800664709","https://openalex.org/W2952218014","https://openalex.org/W2962935966","https://openalex.org/W2963816101","https://openalex.org/W3027008958","https://openalex.org/W3036167779","https://openalex.org/W3042857426","https://openalex.org/W3080135102","https://openalex.org/W3093990297","https://openalex.org/W3094607766","https://openalex.org/W3099330747","https://openalex.org/W3106955634","https://openalex.org/W3140410199","https://openalex.org/W3160077247","https://openalex.org/W3163652268","https://openalex.org/W3184410885","https://openalex.org/W3185109982","https://openalex.org/W4221144097","https://openalex.org/W4225672218","https://openalex.org/W4281736089","https://openalex.org/W4283794752","https://openalex.org/W4297841790","https://openalex.org/W4372271367","https://openalex.org/W6745149982","https://openalex.org/W6779823529","https://openalex.org/W6798721538"],"related_works":["https://openalex.org/W3094316140","https://openalex.org/W3133205200","https://openalex.org/W4289363934","https://openalex.org/W2898145319","https://openalex.org/W2898606530","https://openalex.org/W2098101267","https://openalex.org/W2059119686","https://openalex.org/W4289362680","https://openalex.org/W2403380333","https://openalex.org/W2761596192"],"abstract_inverted_index":{"Speech":[0],"separation":[1,21],"aims":[2],"to":[3,85,111,126],"extract":[4],"multiple":[5],"speech":[6,20,49,53,90],"sources":[7],"from":[8,114],"mixed":[9],"signals.":[10],"In":[11],"this":[12],"paper,":[13],"we":[14,38,55],"propose":[15,80],"SepDiff":[16,121,129],"-":[17],"a":[18,63,81,108,131],"monaural":[19],"method":[22],"based":[23],"on":[24,48,102,122],"the":[25,33,41,60,66,76,115],"denoising":[26],"diffusion":[27,34,42],"model":[28,43],"(diffusion":[29],"model).":[30],"By":[31],"modifying":[32],"and":[35,69,88,97],"reverse":[36],"process,":[37],"show":[39],"that":[40],"achieves":[44],"an":[45],"impressive":[46],"performance":[47],"separation.":[50],"To":[51],"generate":[52],"sources,":[54],"use":[56,107],"mel":[57,117],"spectrogram":[58],"of":[59,75,137],"mixture":[61],"as":[62],"condition":[64],"in":[65,72],"training":[67],"procedure":[68],"insert":[70],"it":[71],"every":[73],"step":[74],"sampling":[77],"procedure.":[78],"We":[79,106,119],"novel":[82],"DNN":[83],"structure":[84],"leverage":[86],"local":[87],"global":[89],"information":[91],"through":[92],"successive":[93],"feature":[94],"channel":[95],"attention":[96],"dilated":[98],"2-D":[99],"convolution":[100],"blocks":[101],"multi-resolution":[103],"time-frequency":[104],"features.":[105],"neural":[109],"vocoder":[110],"get":[112],"waveform":[113],"generated":[116],"spectrogram.":[118],"evaluate":[120],"LibriMix":[123],"datasets.":[124],"Compared":[125],"SepFormer":[127],"approach,":[128],"yields":[130],"higher":[132],"mean":[133],"opinion":[134],"score":[135],"(MOS)":[136],"0.11.":[138]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}