{"id":"https://openalex.org/W3034398443","doi":"https://doi.org/10.24963/ijcai.2020/450","title":"Multi-Scale Group Transformer for Long Sequence Modeling in Speech Separation","display_name":"Multi-Scale Group Transformer for Long Sequence Modeling in Speech Separation","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3034398443","doi":"https://doi.org/10.24963/ijcai.2020/450","mag":"3034398443"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2020/450","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/450","pdf_url":"https://www.ijcai.org/proceedings/2020/0450.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2020/0450.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101632793","display_name":"Yucheng Zhao","orcid":"https://orcid.org/0000-0002-9610-3025"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yucheng Zhao","raw_affiliation_strings":["University of Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101437627","display_name":"Chong Luo","orcid":"https://orcid.org/0000-0003-0939-474X"},"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":"Chong Luo","raw_affiliation_strings":["Microsoft Research Asia"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003217535","display_name":"Zheng-Jun Zha","orcid":"https://orcid.org/0000-0003-2510-8993"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng-Jun Zha","raw_affiliation_strings":["University of Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049963367","display_name":"Wenjun Zeng","orcid":"https://orcid.org/0000-0003-2531-3137"},"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":"Wenjun Zeng","raw_affiliation_strings":["Microsoft Research Asia"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101632793"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.7614,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.70555119,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3251","last_page":"3257"},"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":0.9993000030517578,"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":0.9986000061035156,"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/transformer","display_name":"Transformer","score":0.7239500880241394},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6706758737564087},{"id":"https://openalex.org/keywords/quadratic-growth","display_name":"Quadratic growth","score":0.5698659420013428},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4935966730117798},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3729652166366577},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3550816774368286},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.1433860957622528},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12414529919624329},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.07649597525596619}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7239500880241394},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6706758737564087},{"id":"https://openalex.org/C195956108","wikidata":"https://www.wikidata.org/wiki/Q7268362","display_name":"Quadratic growth","level":2,"score":0.5698659420013428},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4935966730117798},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3729652166366577},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3550816774368286},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.1433860957622528},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12414529919624329},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.07649597525596619}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2020/450","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/450","pdf_url":"https://www.ijcai.org/proceedings/2020/0450.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2020/450","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/450","pdf_url":"https://www.ijcai.org/proceedings/2020/0450.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6200000047683716}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3034398443.pdf","grobid_xml":"https://content.openalex.org/works/W3034398443.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1901129140","https://openalex.org/W2221409856","https://openalex.org/W2734774145","https://openalex.org/W2792764867","https://openalex.org/W2891534142","https://openalex.org/W2916798096","https://openalex.org/W2962866211","https://openalex.org/W2962905190","https://openalex.org/W2963317762","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2964058413","https://openalex.org/W2996969697"],"related_works":["https://openalex.org/W2084086280","https://openalex.org/W2027198738","https://openalex.org/W2397767885","https://openalex.org/W2062514649","https://openalex.org/W2083114070","https://openalex.org/W237421766","https://openalex.org/W3013712002","https://openalex.org/W2004392729","https://openalex.org/W4238270958","https://openalex.org/W2057360542"],"abstract_inverted_index":{"In":[0],"this":[1,51],"paper,":[2],"we":[3,53],"introduce":[4],"Transformer":[5,14,63],"to":[6,18,46,83,99],"the":[7,16,38,74,111,139,148],"time-domain":[8,102],"methods":[9],"for":[10],"single-channel":[11],"speech":[12,20,47,103],"separation.":[13],"has":[15,41],"potential":[17],"boost":[19],"separation":[21,104],"performance":[22,140],"because":[23],"of":[24,58,91,141],"its":[25,31],"strong":[26],"sequence":[27,39],"modeling":[28],"capability.":[29],"However,":[30],"computational":[32],"complexity,":[33,75],"which":[34,71,79],"grows":[35],"quadratically":[36],"with":[37,93,117,147],"length,":[40],"made":[42],"it":[43],"largely":[44],"inapplicable":[45],"applications.":[48],"To":[49],"tackle":[50],"issue,":[52],"propose":[54],"a":[55,100,124],"novel":[56],"variation":[57],"Transformer,":[59],"named":[60],"multi-scale":[61,77],"group":[62,69],"(MSGT).":[64],"The":[65],"key":[66],"ideas":[67],"are":[68],"self-attention,":[70],"significantly":[72],"reduces":[73],"and":[76,96,132,137],"fusion,":[78],"retains":[80],"Transform's":[81],"ability":[82],"capture":[84],"long-term":[85],"dependency.":[86],"We":[87],"implement":[88],"two":[89],"versions":[90],"MSGT":[92],"different":[94],"complexities,":[95],"apply":[97],"them":[98],"well-known":[101],"method":[105],"called":[106,121],"Conv-TasNet.":[107],"By":[108],"simply":[109],"replacing":[110],"original":[112],"temporal":[113],"convolutional":[114],"network":[115],"(TCN)":[116],"MSGT,":[118],"our":[119],"approach":[120],"MSGT-TasNet":[122,142],"achieves":[123],"large":[125],"gain":[126],"over":[127],"Conv-TasNet":[128],"on":[129,145],"both":[130],"WSJ0-2mix":[131],"WHAM!":[133],"benchmarks.":[134],"Without":[135],"bells":[136],"whistles,":[138],"is":[143],"already":[144],"par":[146],"SOTA":[149],"methods.":[150]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}