{"id":"https://openalex.org/W4372259962","doi":"https://doi.org/10.1109/icassp49357.2023.10095037","title":"Dasformer: Deep Alternating Spectrogram Transformer For Multi/Single-Channel Speech Separation","display_name":"Dasformer: Deep Alternating Spectrogram Transformer For Multi/Single-Channel Speech Separation","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372259962","doi":"https://doi.org/10.1109/icassp49357.2023.10095037"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095037","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095037","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/A5100400166","display_name":"Shuo Wang","orcid":"https://orcid.org/0000-0002-6191-6608"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shuo Wang","raw_affiliation_strings":["Institute of Acoustics,Chinese Academy of Sciences,Beijing,China","Microsoft Research Asia, Beijing, China","Chinese Academy of Sciences, Institute of Acoustics, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Acoustics,Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Chinese Academy of Sciences, Institute of Acoustics, Beijing, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089038945","display_name":"Xiang\u2010Yu Kong","orcid":"https://orcid.org/0000-0002-4475-2162"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyu Kong","raw_affiliation_strings":["Microsoft Research Asia,Beijing,China","Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia,Beijing,China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024977056","display_name":"Xiulian Peng","orcid":"https://orcid.org/0000-0001-8213-4878"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiulian Peng","raw_affiliation_strings":["Microsoft Research Asia,Beijing,China","Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia,Beijing,China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102510884","display_name":"Hesam Movassagh","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hesam Movassagh","raw_affiliation_strings":["Microsoft Corporation,Redmond,WA,USA,98052"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation,Redmond,WA,USA,98052","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036981298","display_name":"Vinod Prakash","orcid":"https://orcid.org/0000-0001-8021-1729"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vinod Prakash","raw_affiliation_strings":["Microsoft Corporation,Redmond,WA,USA,98052"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation,Redmond,WA,USA,98052","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100756584","display_name":"Yan Lu","orcid":"https://orcid.org/0000-0001-5383-6424"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Lu","raw_affiliation_strings":["Microsoft Research Asia,Beijing,China","Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia,Beijing,China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100400166"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210099069","https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":2.6432,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.90705389,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.9713535308837891},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6785709857940674},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6500180959701538},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5637093782424927},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5315380692481995},{"id":"https://openalex.org/keywords/bin","display_name":"Bin","score":0.519221842288971},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.4992079734802246},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.433333158493042},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4314216077327728},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.413648784160614},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3856930136680603},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33693504333496094},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2831137180328369},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2632816731929779},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11772534251213074},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10764533281326294},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08367106318473816}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9713535308837891},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6785709857940674},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6500180959701538},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5637093782424927},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5315380692481995},{"id":"https://openalex.org/C156273044","wikidata":"https://www.wikidata.org/wiki/Q4913766","display_name":"Bin","level":2,"score":0.519221842288971},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.4992079734802246},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.433333158493042},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4314216077327728},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.413648784160614},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3856930136680603},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33693504333496094},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2831137180328369},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2632816731929779},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11772534251213074},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10764533281326294},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08367106318473816},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095037","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095037","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":0.4000000059604645,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2152728141","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2892163332","https://openalex.org/W2952218014","https://openalex.org/W2962935966","https://openalex.org/W3015191643","https://openalex.org/W3015199127","https://openalex.org/W3015372568","https://openalex.org/W3015788098","https://openalex.org/W3032514799","https://openalex.org/W3096893582","https://openalex.org/W3097777922","https://openalex.org/W3099330747","https://openalex.org/W3158779859","https://openalex.org/W3163652268","https://openalex.org/W3185109982","https://openalex.org/W3191469971","https://openalex.org/W4223583411","https://openalex.org/W4224936432","https://openalex.org/W4296070366","https://openalex.org/W4297775537","https://openalex.org/W4297841846","https://openalex.org/W6718827390"],"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":{"For":[0],"the":[1,43,54,99,111,123,130,144],"task":[2],"of":[3,40,76,80,98],"speech":[4,136],"separation,":[5,137],"previous":[6],"study":[7],"usually":[8],"treats":[9],"multi-channel":[10,135],"and":[11,28,63,138],"single-channel":[12,141],"scenarios":[13],"as":[14],"two":[15,84],"research":[16],"tracks":[17],"with":[18,58],"specialized":[19],"solutions":[20],"developed":[21],"respectively.":[22],"Instead,":[23],"we":[24],"propose":[25],"a":[26,118],"simple":[27,77],"unified":[29],"architecture":[30],"-":[31],"DasFormer":[32,69,116],"(Deep":[33],"alternating":[34],"spectrogram":[35,55,100],"transFormer)":[36],"to":[37,121],"handle":[38],"both":[39],"them":[41],"in":[42,53,134,143],"challenging":[44,146],"reverberant":[45],"environments.":[46],"Unlike":[47],"frame-wise":[48],"sequence":[49],"modeling,":[50],"each":[51,79,92,104],"TF-bin":[52],"is":[56,70],"assigned":[57],"an":[59],"embedding":[60],"encoding":[61],"spectral":[62],"spatial":[64],"information.":[65],"With":[66],"such":[67],"input,":[68],"then":[71],"formed":[72],"by":[73],"multiple":[74],"repetition":[75],"blocks":[78],"which":[81],"integrates":[82],"1)":[83],"multi-head":[85],"self-attention":[86],"(MHSA)":[87],"modules":[88],"alternately":[89],"processing":[90],"within":[91],"frequency":[93],"bin":[94],"&":[95],"temporal":[96],"frame":[97],"2)":[101],"MBConv":[102],"before":[103],"MHSA":[105],"for":[106],"modeling":[107],"local":[108],"features":[109],"on":[110],"spectrogram.":[112],"Experiments":[113],"show":[114],"that":[115],"has":[117],"powerful":[119],"ability":[120],"model":[122],"time-frequency":[124],"representation,":[125],"whose":[126],"performance":[127],"far":[128],"exceeds":[129],"current":[131],"SOTA":[132,142],"models":[133],"also":[139],"achieves":[140],"more":[145],"yet":[147],"realistic":[148],"reverberation":[149],"scenario.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}