{"id":"https://openalex.org/W3015199127","doi":"https://doi.org/10.1109/icassp40776.2020.9054266","title":"Dual-Path RNN: Efficient Long Sequence Modeling for Time-Domain Single-Channel Speech Separation","display_name":"Dual-Path RNN: Efficient Long Sequence Modeling for Time-Domain Single-Channel Speech Separation","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015199127","doi":"https://doi.org/10.1109/icassp40776.2020.9054266","mag":"3015199127"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054266","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054266","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5048439332","display_name":"Yi Luo","orcid":"https://orcid.org/0000-0002-7447-3885"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yi Luo","raw_affiliation_strings":["Department of Electrical Engineering, Columbia University, NY, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Columbia University, NY, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100345092","display_name":"Zhuo Chen","orcid":"https://orcid.org/0000-0002-9011-7928"},"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":"Zhuo Chen","raw_affiliation_strings":["Microsoft, One Microsoft Way, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, One Microsoft Way, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101618071","display_name":"Takuya Yoshioka","orcid":"https://orcid.org/0009-0003-7791-3545"},"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":"Takuya Yoshioka","raw_affiliation_strings":["Microsoft, One Microsoft Way, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, One Microsoft Way, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5048439332"],"corresponding_institution_ids":["https://openalex.org/I78577930"],"apc_list":null,"apc_paid":null,"fwci":67.3981,"has_fulltext":false,"cited_by_count":740,"citation_normalized_percentile":{"value":0.99967384,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"46","last_page":"50"},"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":0.9993000030517578,"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":0.9988999962806702,"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/recurrent-neural-network","display_name":"Recurrent neural network","score":0.80543053150177},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7451419830322266},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5845743417739868},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5568020343780518},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.5443408489227295},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5271403789520264},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.5047417879104614},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46414461731910706},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44441524147987366},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.44273674488067627},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43283137679100037},{"id":"https://openalex.org/keywords/time-domain","display_name":"Time domain","score":0.43280866742134094},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4017295241355896}],"concepts":[{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.80543053150177},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7451419830322266},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5845743417739868},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5568020343780518},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.5443408489227295},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5271403789520264},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.5047417879104614},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46414461731910706},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44441524147987366},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.44273674488067627},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43283137679100037},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.43280866742134094},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4017295241355896},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054266","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054266","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W2030486566","https://openalex.org/W2064675550","https://openalex.org/W2115613106","https://openalex.org/W2117678320","https://openalex.org/W2127851351","https://openalex.org/W2221409856","https://openalex.org/W2510842514","https://openalex.org/W2584032004","https://openalex.org/W2734774145","https://openalex.org/W2735663686","https://openalex.org/W2740087922","https://openalex.org/W2792764867","https://openalex.org/W2889540509","https://openalex.org/W2943162839","https://openalex.org/W2952218014","https://openalex.org/W2962715207","https://openalex.org/W2962905190","https://openalex.org/W2962935966","https://openalex.org/W2963045393","https://openalex.org/W2963069107","https://openalex.org/W2963241221","https://openalex.org/W2963317762","https://openalex.org/W2963443859","https://openalex.org/W2963452667","https://openalex.org/W2963735467","https://openalex.org/W2964058413","https://openalex.org/W2964121744","https://openalex.org/W2964347220","https://openalex.org/W2972460025","https://openalex.org/W2972653970","https://openalex.org/W2972693890","https://openalex.org/W2996969697","https://openalex.org/W2998657200","https://openalex.org/W3004309045","https://openalex.org/W3099330747","https://openalex.org/W3124972797","https://openalex.org/W6631190155","https://openalex.org/W6725939724","https://openalex.org/W6732429163","https://openalex.org/W6743485176","https://openalex.org/W6749825310","https://openalex.org/W6751512325","https://openalex.org/W6762053788","https://openalex.org/W6780226713"],"related_works":["https://openalex.org/W4226493464","https://openalex.org/W4312417841","https://openalex.org/W3193565141","https://openalex.org/W3133861977","https://openalex.org/W3008584592","https://openalex.org/W3167935049","https://openalex.org/W3029198973","https://openalex.org/W2782295999","https://openalex.org/W1970292246","https://openalex.org/W2162306796"],"abstract_inverted_index":{"Recent":[0],"studies":[1],"in":[2,105,147,163],"deep":[3,107],"learning-based":[4],"speech":[5],"separation":[6,25,167],"have":[7],"proven":[8],"the":[9,19,23,83,116,131,139,143,164,185],"superiority":[10],"of":[11,32,36,142],"time-domain":[12,24,165],"approaches":[13],"to":[14,61,109,138],"conventional":[15],"time-frequency-based":[16],"methods.":[17],"Unlike":[18],"time-frequency":[20],"domain":[21],"approaches,":[22],"systems":[26],"often":[27],"receive":[28],"input":[29,119,132],"sequences":[30,59],"consisting":[31],"a":[33,96,106,170,179],"huge":[34],"number":[35],"time":[37],"steps,":[38],"which":[39],"introduces":[40],"challenges":[41],"for":[42,55,101],"modeling":[43,56,75,162],"extremely":[44,111],"long":[45,58,112,117],"sequences.":[46,113],"Conventional":[47],"recurrent":[48,92],"neural":[49,67,93],"networks":[50,68],"(RNNs)":[51],"are":[52],"not":[53],"effective":[54,99],"such":[57],"due":[60],"optimization":[62],"difficulties,":[63],"while":[64],"one-dimensional":[65],"convolutional":[66],"(1-D":[69],"CNNs)":[70],"cannot":[71],"perform":[72],"utterance-level":[73],"sequence":[74,84,145],"when":[76],"its":[77],"receptive":[78],"field":[79],"is":[80,176],"smaller":[81,121,182],"than":[82,184],"length.":[85],"In":[86],"this":[87],"paper,":[88],"we":[89],"propose":[90],"dual-path":[91],"network":[94,168],"(DPRNN),":[95],"simple":[97],"yet":[98],"method":[100],"organizing":[102],"RNN":[103],"layers":[104],"structure":[108],"model":[110,183],"DPRNN":[114,158],"splits":[115],"sequential":[118],"into":[120],"chunks":[122],"and":[123,126,159],"applies":[124],"intra-":[125],"inter-chunk":[127],"operations":[128],"iteratively,":[129],"where":[130],"length":[133,146],"can":[134],"be":[135],"made":[136],"proportional":[137],"square":[140],"root":[141],"original":[144],"each":[148],"operation.":[149],"Experiments":[150],"show":[151],"that":[152],"by":[153],"replacing":[154],"1-D":[155],"CNN":[156],"with":[157,178],"apply":[160],"sample-level":[161],"audio":[166],"(TasNet),":[169],"new":[171],"state-of-the-art":[172],"performance":[173],"on":[174],"WSJ0-2mix":[175],"achieved":[177],"20":[180],"times":[181],"previous":[186],"best":[187],"system.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":14},{"year":2025,"cited_by_count":149},{"year":2024,"cited_by_count":134},{"year":2023,"cited_by_count":157},{"year":2022,"cited_by_count":136},{"year":2021,"cited_by_count":109},{"year":2020,"cited_by_count":39},{"year":2019,"cited_by_count":2}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}