{"id":"https://openalex.org/W4224936432","doi":"https://doi.org/10.1109/icassp43922.2022.9747554","title":"TFPSNet: Time-Frequency Domain Path Scanning Network for Speech Separation","display_name":"TFPSNet: Time-Frequency Domain Path Scanning Network for Speech Separation","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224936432","doi":"https://doi.org/10.1109/icassp43922.2022.9747554"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747554","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747554","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5101654416","display_name":"Lei Yang","orcid":"https://orcid.org/0000-0003-1632-5910"},"institutions":[{"id":"https://openalex.org/I4210155230","display_name":"Samsung (China)","ror":"https://ror.org/04yt00889","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210155230"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lei Yang","raw_affiliation_strings":["Samsung Research China – Beijing (SRC-B)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research China – Beijing (SRC-B)","institution_ids":["https://openalex.org/I4210155230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062908102","display_name":"Wei Liu","orcid":"https://orcid.org/0000-0003-2968-2888"},"institutions":[{"id":"https://openalex.org/I4210155230","display_name":"Samsung (China)","ror":"https://ror.org/04yt00889","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210155230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Liu","raw_affiliation_strings":["Samsung Research China – Beijing (SRC-B)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research China – Beijing (SRC-B)","institution_ids":["https://openalex.org/I4210155230"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103162335","display_name":"Weiqin Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210155230","display_name":"Samsung (China)","ror":"https://ror.org/04yt00889","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210155230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiqin Wang","raw_affiliation_strings":["Samsung Research China – Beijing (SRC-B)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research China – Beijing (SRC-B)","institution_ids":["https://openalex.org/I4210155230"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101654416"],"corresponding_institution_ids":["https://openalex.org/I4210155230"],"apc_list":null,"apc_paid":null,"fwci":5.4468,"has_fulltext":false,"cited_by_count":52,"citation_normalized_percentile":{"value":0.97230091,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6842","last_page":"6846"},"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":0.9994999766349792,"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":0.9984999895095825,"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/generalizability-theory","display_name":"Generalizability theory","score":0.7491655349731445},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6633124947547913},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.6490246057510376},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.5996211171150208},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5763806104660034},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.569398820400238},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4962027668952942},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.42416203022003174},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38665783405303955},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34124135971069336},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32670366764068604},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16665947437286377},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0851832926273346},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.08303171396255493},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.08018523454666138}],"concepts":[{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.7491655349731445},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6633124947547913},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.6490246057510376},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.5996211171150208},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5763806104660034},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.569398820400238},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4962027668952942},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.42416203022003174},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38665783405303955},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34124135971069336},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32670366764068604},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16665947437286377},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0851832926273346},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.08303171396255493},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.08018523454666138},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747554","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747554","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1991139021","https://openalex.org/W2143169494","https://openalex.org/W2734774145","https://openalex.org/W2792764867","https://openalex.org/W2900212944","https://openalex.org/W2900440209","https://openalex.org/W2916979304","https://openalex.org/W2952218014","https://openalex.org/W2962935966","https://openalex.org/W2964058413","https://openalex.org/W2996969697","https://openalex.org/W3015199127","https://openalex.org/W3015843733","https://openalex.org/W3027008958","https://openalex.org/W3096893582","https://openalex.org/W3099330747","https://openalex.org/W3160903688","https://openalex.org/W3162629387","https://openalex.org/W3163652268","https://openalex.org/W3197055177","https://openalex.org/W3197445409","https://openalex.org/W6631190155","https://openalex.org/W6749825310","https://openalex.org/W6777776875"],"related_works":["https://openalex.org/W2118717649","https://openalex.org/W2413243053","https://openalex.org/W410723623","https://openalex.org/W2015341305","https://openalex.org/W2035068594","https://openalex.org/W4225593417","https://openalex.org/W2573498121","https://openalex.org/W3022298670","https://openalex.org/W3160494304","https://openalex.org/W3207796226"],"abstract_inverted_index":{"Speech":[0],"separation":[1,24],"has":[2,99],"been":[3],"very":[4],"successful":[5],"with":[6],"deep":[7],"learning":[8],"techniques.":[9],"In":[10],"this":[11],"paper,":[12],"we":[13],"propose":[14],"time-frequency":[15],"(T-F)":[16],"domain":[17],"path":[18,38,47],"scanning":[19],"network":[20],"(TFPSNet)":[21],"for":[22],"speech":[23],"task.":[25],"The":[26,55,102],"connections":[27],"between":[28],"frequency":[29,32,63],"bins":[30],"in":[31,69],"path,":[33,35],"time":[34],"and":[36,65,91],"T-F":[37,46,70],"are":[39],"modeled":[40],"by":[41],"transformer.":[42],"We":[43],"also":[44],"introduce":[45],"loss":[48],"function":[49],"to":[50],"improve":[51],"the":[52,67],"performance":[53,80],"further.":[54],"proposed":[56,75],"TFPSNet":[57],"could":[58],"learn":[59],"more":[60],"details":[61],"of":[62],"structure":[64],"separate":[66],"feature":[68],"domain.":[71],"Experiments":[72],"show":[73],"that":[74],"model":[76,103],"achieves":[77,108],"state-of-the-art":[78],"(SOTA)":[79],"on":[81,89,94,105,111,128],"public":[82],"WSJ0-2mix":[83,106],"datasets.":[84],"It":[85],"reaches":[86],"21.1dB":[87],"SI-SDRi":[88,93,110],"WSJ0-2mix,":[90],"19.7dB":[92],"Libri-2mix.":[95],"Furthermore,":[96],"our":[97],"approach":[98],"good":[100],"generalizability.":[101],"trained":[104,127],"dataset":[107],"18.6dB":[109],"Libri-2mix":[112,129],"test":[113],"set":[114],"without":[115],"any":[116],"fine-tuning":[117],"work.":[118],"This":[119],"result":[120],"is":[121],"even":[122],"0.4dB":[123],"higher":[124],"than":[125],"DPTNet":[126],"dataset.":[130]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":14}],"updated_date":"2026-06-06T09:05:17.133730","created_date":"2025-10-10T00:00:00"}