{"id":"https://openalex.org/W4412107079","doi":"https://doi.org/10.1109/access.2025.3587085","title":"Multiscale Convolutional Fusion Network for Efficient Monaural Speech Separation","display_name":"Multiscale Convolutional Fusion Network for Efficient Monaural Speech Separation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412107079","doi":"https://doi.org/10.1109/access.2025.3587085"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3587085","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3587085","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3587085","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100859237","display_name":"Rui Yang","orcid":"https://orcid.org/0000-0002-7843-5114"},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Rui Yang","raw_affiliation_strings":["Faculty of Information Science and Engineering, Ningbo University, Ningbo, China"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Science and Engineering, Ningbo University, Ningbo, China","institution_ids":["https://openalex.org/I109935558"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076503603","display_name":"Shanliang Pan","orcid":null},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shanliang Pan","raw_affiliation_strings":["Faculty of Information Science and Engineering, Ningbo University, Ningbo, China"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Science and Engineering, Ningbo University, Ningbo, China","institution_ids":["https://openalex.org/I109935558"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100859237"],"corresponding_institution_ids":["https://openalex.org/I109935558"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19244288,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":null,"first_page":"127045","last_page":"127053"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech 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":0.9962000250816345,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9574000239372253,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7001002430915833},{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.6169204711914062},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5627369284629822},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.5319899320602417},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47337955236434937},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3508254885673523},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.18283849954605103}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7001002430915833},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.6169204711914062},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5627369284629822},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.5319899320602417},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47337955236434937},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3508254885673523},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.18283849954605103},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3587085","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3587085","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:5768871784d3468eac8aac9c9d07bed9","is_oa":true,"landing_page_url":"https://doaj.org/article/5768871784d3468eac8aac9c9d07bed9","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 127045-127053 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3587085","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3587085","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1520928336","display_name":null,"funder_award_id":"2022Z189","funder_id":"https://openalex.org/F4320336552","funder_display_name":"Science and Technology Innovation 2025 Major Project of Ningbo"}],"funders":[{"id":"https://openalex.org/F4320336552","display_name":"Science and Technology Innovation 2025 Major Project of Ningbo","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2127851351","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2952218014","https://openalex.org/W2962935966","https://openalex.org/W2972541922","https://openalex.org/W3015199127","https://openalex.org/W3034421924","https://openalex.org/W3096893582","https://openalex.org/W3163652268","https://openalex.org/W3191469971","https://openalex.org/W4224938485","https://openalex.org/W4281784192","https://openalex.org/W4283727958","https://openalex.org/W4286377442","https://openalex.org/W4289752563","https://openalex.org/W4372271367","https://openalex.org/W4390740505","https://openalex.org/W4392903251","https://openalex.org/W4392904741","https://openalex.org/W4396228962","https://openalex.org/W4408354310","https://openalex.org/W4409134989","https://openalex.org/W6631190155","https://openalex.org/W6777776875","https://openalex.org/W6789284391","https://openalex.org/W6803594737","https://openalex.org/W6839818334","https://openalex.org/W6844662008","https://openalex.org/W6861483607","https://openalex.org/W6863679278"],"related_works":["https://openalex.org/W2036157531","https://openalex.org/W2056406069","https://openalex.org/W1974981856","https://openalex.org/W1518859147","https://openalex.org/W2045506488","https://openalex.org/W1983045063","https://openalex.org/W4321794819","https://openalex.org/W2944394647","https://openalex.org/W2072124114","https://openalex.org/W2401567014"],"abstract_inverted_index":{"Speech":[0],"separation":[1,20,24,94,164],"is":[2],"crucial":[3],"for":[4],"robust":[5],"speech":[6,19,93,163],"processing":[7],"in":[8,15],"real-world":[9],"acoustic":[10,139,148],"environments.":[11],"To":[12,70],"enable":[13],"deployment":[14],"resource-limited":[16],"scenarios,":[17],"a":[18,76],"system":[21],"must":[22],"balance":[23],"performance,":[25],"computational":[26,61,168],"efficiency,":[27],"and":[28,130,170,189,197],"inference":[29,202],"speed.":[30],"In":[31],"time-domain":[32],"approaches,":[33],"recurrent":[34],"convolutional":[35,42,78,112],"neural":[36],"network":[37,80],"(RCNN)-based":[38],"models":[39,58],"employ":[40],"multiscale":[41,77,111,125,131],"architectures":[43],"to":[44,54,66,87,122,136],"model":[45],"the":[46,89,99,104,124,147,180,205],"long":[47],"sequences":[48],"of":[49,91,109],"encoded":[50],"mixture":[51],"signals.":[52],"Compared":[53],"dual-path":[55],"models,":[56,165],"RCNN-based":[57,84],"offer":[59],"higher":[60],"efficiency":[62],"but":[63],"often":[64],"struggle":[65],"achieve":[67],"competitive":[68],"performance.":[69],"address":[71],"this":[72],"limitation,":[73],"we":[74],"propose":[75],"fusion":[79,113],"(MSCF-Net),":[81],"an":[82],"efficient":[83],"architecture":[85],"designed":[86],"enhance":[88,123],"performance":[90,160],"lightweight":[92,162],"models.":[95],"The":[96],"MSCF-Net":[97,174],"follows":[98],"encoder-mask":[100],"estimation-decoder":[101],"pipeline,":[102],"where":[103],"mask":[105],"estimation":[106],"process":[107],"consists":[108],"parameter-shared":[110],"(MSCF)":[114],"modules.":[115],"MSCF":[116],"first":[117],"employs":[118],"dynamic":[119],"convolution-based":[120],"downsampling":[121],"feature":[126],"representation.":[127],"Adaptive":[128],"gating":[129],"convolutions":[132],"are":[133],"then":[134],"utilized":[135],"capture":[137],"complex":[138],"patterns.":[140],"Finally,":[141],"cross-scale":[142],"modulation":[143],"upsampling":[144],"efficiently":[145],"reconstructs":[146],"features.":[149],"Experiments":[150],"on":[151,179,204],"three":[152],"datasets":[153],"demonstrate":[154],"that":[155],"our":[156],"method":[157],"achieves":[158,175,198],"state-of-the-art":[159],"among":[161],"with":[166,184],"low":[167],"complexity":[169],"fast":[171],"inference.":[172],"Specifically,":[173],"19.1":[176],"dB":[177],"SI-SNRi":[178],"WSJ0-2Mix":[181],"test":[182,206],"set":[183],"only":[185],"3.4":[186],"M":[187],"parameters":[188],"6.67":[190],"G/s":[191],"multiply-accumulate":[192],"operations":[193],"(MACs)":[194],"per":[195],"second,":[196],"6":[199],"times":[200],"real-time":[201],"speed":[203],"CPU.":[207]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}