{"id":"https://openalex.org/W4392909101","doi":"https://doi.org/10.1109/icassp48485.2024.10447030","title":"SPGM: Prioritizing Local Features for Enhanced Speech Separation Performance","display_name":"SPGM: Prioritizing Local Features for Enhanced Speech Separation Performance","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392909101","doi":"https://doi.org/10.1109/icassp48485.2024.10447030"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447030","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447030","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":"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/A5102941083","display_name":"Jia Qi Yip","orcid":"https://orcid.org/0000-0002-9896-9658"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]},{"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","US"],"is_corresponding":true,"raw_author_name":"Jia Qi Yip","raw_affiliation_strings":["Alibaba Group","Nanyang Technological University (NTU), Singapore"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]},{"raw_affiliation_string":"Nanyang Technological University (NTU), Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103758307","display_name":"Shengkui Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shengkui Zhao","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101568886","display_name":"Yukun Ma","orcid":"https://orcid.org/0000-0002-4419-4287"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yukun Ma","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102306089","display_name":"Chongjia Ni","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chongjia Ni","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100393899","display_name":"Chong Zhang","orcid":"https://orcid.org/0000-0002-2162-4344"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chong Zhang","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100446064","display_name":"Hao Wang","orcid":"https://orcid.org/0000-0001-9301-5989"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Wang","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101562097","display_name":"Trung Hieu Nguyen","orcid":"https://orcid.org/0000-0002-2683-253X"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Trung Hieu Nguyen","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111109271","display_name":"Kun Zhou","orcid":"https://orcid.org/0000-0003-4243-6112"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kun Zhou","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104217727","display_name":"Dianwen Ng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Dianwen Ng","raw_affiliation_strings":["Alibaba Group","Nanyang Technological University (NTU), Singapore"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]},{"raw_affiliation_string":"Nanyang Technological University (NTU), Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","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 (NTU),Singapore","Nanyang Technological University (NTU), Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University (NTU),Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Nanyang Technological University (NTU), Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100749735","display_name":"Bin Ma","orcid":"https://orcid.org/0000-0002-9223-9654"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bin Ma","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5102941083"],"corresponding_institution_ids":["https://openalex.org/I172675005","https://openalex.org/I4210095624"],"apc_list":null,"apc_paid":null,"fwci":2.2413,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.87856722,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"326","last_page":"330"},"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":0.9980999827384949,"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/pooling","display_name":"Pooling","score":0.7383692264556885},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6404098868370056},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5706491470336914},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.5512686967849731},{"id":"https://openalex.org/keywords/modulation","display_name":"Modulation (music)","score":0.5304564833641052},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5298076868057251},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4088706374168396},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4072072505950928},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3928828835487366},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31756120920181274},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17738977074623108},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.08928537368774414},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08032962679862976}],"concepts":[{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.7383692264556885},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6404098868370056},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5706491470336914},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.5512686967849731},{"id":"https://openalex.org/C123079801","wikidata":"https://www.wikidata.org/wiki/Q750240","display_name":"Modulation (music)","level":2,"score":0.5304564833641052},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5298076868057251},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4088706374168396},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4072072505950928},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3928828835487366},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31756120920181274},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17738977074623108},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.08928537368774414},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08032962679862976},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447030","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447030","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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320766","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302"},{"id":"https://openalex.org/F4320331617","display_name":"National Supercomputing Centre Singapore","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2221409856","https://openalex.org/W2734774145","https://openalex.org/W2952218014","https://openalex.org/W2998657200","https://openalex.org/W3015199127","https://openalex.org/W3027008958","https://openalex.org/W3042857426","https://openalex.org/W3094607766","https://openalex.org/W3096893582","https://openalex.org/W3096918678","https://openalex.org/W3099330747","https://openalex.org/W3167533889","https://openalex.org/W3185109982","https://openalex.org/W3214142715","https://openalex.org/W4283794752","https://openalex.org/W4296068589","https://openalex.org/W4296068774","https://openalex.org/W4300978696","https://openalex.org/W4318242507","https://openalex.org/W4372271367","https://openalex.org/W4375869129","https://openalex.org/W4375869348","https://openalex.org/W4379797396","https://openalex.org/W4385823047","https://openalex.org/W4385823354","https://openalex.org/W6777776875","https://openalex.org/W6803594737","https://openalex.org/W6844662008","https://openalex.org/W6849002408"],"related_works":["https://openalex.org/W2953234277","https://openalex.org/W2626256601","https://openalex.org/W147410782","https://openalex.org/W2900413183","https://openalex.org/W4390975304","https://openalex.org/W3022252430","https://openalex.org/W4287804464","https://openalex.org/W3103989898","https://openalex.org/W3211292372","https://openalex.org/W803346624"],"abstract_inverted_index":{"Dual-path":[0],"is":[1,64],"a":[2,43,71,78],"popular":[3],"architecture":[4],"for":[5,18],"speech":[6],"separation":[7],"models":[8,143],"(e.g.":[9],"Sepformer)":[10],"which":[11,40],"splits":[12],"long":[13],"sequences":[14],"into":[15],"overlapping":[16],"chunks":[17],"its":[19,67],"intra-":[20],"and":[21,29,118,132,136,152],"inter-blocks":[22],"that":[23,38],"separately":[24],"model":[25,98,109],"intra-chunk":[26],"local":[27,103],"features":[28],"inter-chunk":[30],"global":[31,73],"relationships.":[32],"However,":[33],"it":[34],"has":[35],"been":[36],"found":[37],"inter-blocks,":[39],"comprise":[41],"half":[42],"dual-path":[44],"model\u2019s":[45,86],"parameters,":[46],"contribute":[47],"minimally":[48],"to":[49,60,99,102,146],"performance.":[50],"Thus,":[51],"we":[52],"propose":[53],"the":[54,85,97,107,125,138],"Single-Path":[55],"Global":[56],"Modulation":[57],"(SPGM)":[58],"block":[59,91],"replace":[61],"inter-blocks.":[62],"SPGM":[63,90,111],"named":[65],"after":[66],"structure":[68],"consisting":[69],"of":[70,84,127,140],"parameter-free":[72],"pooling":[74],"module":[75,80],"followed":[76],"by":[77,129],"modulation":[79],"comprising":[81],"only":[82],"2%":[83],"total":[87],"parameters.":[88,150],"The":[89],"allows":[92],"all":[93],"transformer":[94],"layers":[95],"in":[96],"be":[100],"dedicated":[101],"feature":[104],"modelling,":[105],"making":[106],"overall":[108],"single-path.":[110],"achieves":[112],"22.1":[113],"dB":[114,120,131,134],"SI-SDRi":[115,121],"on":[116,122],"WSJ0-2Mix":[117],"20.4":[119],"Libri2Mix,":[123],"exceeding":[124],"performance":[126,139],"Sepformer":[128],"0.5":[130],"0.3":[133],"respectively":[135],"matches":[137],"recent":[141],"SOTA":[142],"with":[144],"up":[145],"8":[147],"times":[148],"fewer":[149],"Model":[151],"weights":[153],"are":[154],"available":[155],"at":[156],"huggingface.co/yipjiaqi/spgm":[157]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
