{"id":"https://openalex.org/W2800022361","doi":"https://doi.org/10.1109/icassp.2018.8462471","title":"Single Channel Speech Separation with Constrained Utterance Level Permutation Invariant Training Using Grid LSTM","display_name":"Single Channel Speech Separation with Constrained Utterance Level Permutation Invariant Training Using Grid LSTM","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2800022361","doi":"https://doi.org/10.1109/icassp.2018.8462471","mag":"2800022361"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462471","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462471","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://dr.ntu.edu.sg/bitstream/10356/137336/2/SINGLE%20CHANNEL%20SPEECH%20SEPARATION%20WITH%20CONSTRAINED%20UTTERANCE%20LEVEL%20PERMUTATION%20INVARIANT%20TRAINING%20USING%20GRID%20LSTM.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103210439","display_name":"Chenglin Xu","orcid":"https://orcid.org/0000-0002-1584-6282"},"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":"Chenglin Xu","raw_affiliation_strings":["Temasek Laboratories@NTU, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Temasek Laboratories@NTU, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035226758","display_name":"Wei Rao","orcid":"https://orcid.org/0000-0002-7237-0874"},"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":"Wei Rao","raw_affiliation_strings":["Temasek Laboratories@NTU, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Temasek Laboratories@NTU, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101602536","display_name":"Xiong Xiao","orcid":"https://orcid.org/0009-0001-5128-6518"},"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":"Xiong Xiao","raw_affiliation_strings":["Microsoft Corporation, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, United States","institution_ids":["https://openalex.org/I1290206253"]}]},{"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":["Temasek Laboratories@NTU, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Temasek Laboratories@NTU, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"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":"Haizhou Li","raw_affiliation_strings":["Temasek Laboratories@NTU, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Temasek Laboratories@NTU, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":12.1378,"has_fulltext":true,"cited_by_count":89,"citation_normalized_percentile":{"value":0.99074497,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"2018","issue":null,"first_page":"6","last_page":"10"},"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":0.9995999932289124,"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":0.9994999766349792,"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/computer-science","display_name":"Computer science","score":0.7105367183685303},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.6371449828147888},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5756704807281494},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.5634438991546631},{"id":"https://openalex.org/keywords/permutation","display_name":"Permutation (music)","score":0.5140060186386108},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.48430076241493225},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4819331169128418},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.4420672059059143},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.4288976192474365},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.42666101455688477},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3875020146369934},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3792721629142761},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20965594053268433}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7105367183685303},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.6371449828147888},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5756704807281494},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.5634438991546631},{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.5140060186386108},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.48430076241493225},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4819331169128418},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.4420672059059143},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.4288976192474365},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.42666101455688477},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3875020146369934},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3792721629142761},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20965594053268433},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2018.8462471","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462471","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:dr.ntu.edu.sg:10356/137336","is_oa":true,"landing_page_url":"https://hdl.handle.net/10356/137336","pdf_url":"https://dr.ntu.edu.sg/bitstream/10356/137336/2/SINGLE%20CHANNEL%20SPEECH%20SEPARATION%20WITH%20CONSTRAINED%20UTTERANCE%20LEVEL%20PERMUTATION%20INVARIANT%20TRAINING%20USING%20GRID%20LSTM.pdf","source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Paper"},{"id":"mag:3203885292","is_oa":false,"landing_page_url":"https://jglobal.jst.go.jp/en/detail?JGLOBAL_ID=201802257340662446","pdf_url":null,"source":{"id":"https://openalex.org/S4306512817","display_name":"IEEE Conference Proceedings","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":null,"is_accepted":false,"is_published":null,"raw_source_name":"IEEE Conference Proceedings","raw_type":null}],"best_oa_location":{"id":"pmh:oai:dr.ntu.edu.sg:10356/137336","is_oa":true,"landing_page_url":"https://hdl.handle.net/10356/137336","pdf_url":"https://dr.ntu.edu.sg/bitstream/10356/137336/2/SINGLE%20CHANNEL%20SPEECH%20SEPARATION%20WITH%20CONSTRAINED%20UTTERANCE%20LEVEL%20PERMUTATION%20INVARIANT%20TRAINING%20USING%20GRID%20LSTM.pdf","source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Paper"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2800022361.pdf","grobid_xml":"https://content.openalex.org/works/W2800022361.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W185399533","https://openalex.org/W1482149378","https://openalex.org/W1522301498","https://openalex.org/W1790748249","https://openalex.org/W1994396704","https://openalex.org/W2069681747","https://openalex.org/W2118718620","https://openalex.org/W2124149378","https://openalex.org/W2127851351","https://openalex.org/W2147174722","https://openalex.org/W2221409856","https://openalex.org/W2233657726","https://openalex.org/W2460742184","https://openalex.org/W2475988411","https://openalex.org/W2558649592","https://openalex.org/W2734774145","https://openalex.org/W2742061524","https://openalex.org/W2962715207","https://openalex.org/W2962965465","https://openalex.org/W3124666641","https://openalex.org/W3124794156","https://openalex.org/W6677759377","https://openalex.org/W6688843265","https://openalex.org/W6789284391"],"related_works":["https://openalex.org/W270557224","https://openalex.org/W1883264250","https://openalex.org/W2499922657","https://openalex.org/W115323076","https://openalex.org/W2025991752","https://openalex.org/W1839403150","https://openalex.org/W2687193347","https://openalex.org/W1542472901","https://openalex.org/W4244859097","https://openalex.org/W2073779666"],"abstract_inverted_index":{"Utterance":[0],"level":[1,45],"permutation":[2],"invariant":[3],"training":[4],"(uPIT)":[5],"technique":[6],"is":[7,49],"a":[8,61,71,116],"state-of-the-art":[9],"deep":[10],"learning":[11],"architecture":[12],"for":[13],"speaker":[14],"independent":[15],"multi-talker":[16],"separation.":[17],"uPIT":[18,39,63,162],"solves":[19],"the":[20,26,47,53,86,93,98,112,136,161],"label":[21],"ambiguity":[22],"problem":[23,68],"by":[24,69,97,114],"minimizing":[25],"mean":[27],"square":[28],"error":[29],"(MSE)":[30],"over":[31,52,135],"all":[32],"permutations":[33],"between":[34],"outputs":[35],"and":[36,80,132,146,156],"targets.":[37],"However,":[38],"may":[40],"be":[41],"sub-optimal":[42],"at":[43],"segmental":[44],"because":[46],"optimization":[48],"not":[50],"calculated":[51],"individual":[54],"frames.":[55],"In":[56],"this":[57,67],"paper,":[58],"we":[59,109,121],"propose":[60],"constrained":[62],"(cuPIT)":[64],"to":[65,127],"solve":[66],"computing":[70],"weighted":[72,83],"MSE":[73],"loss":[74,84],"using":[75],"dynamic":[76],"information":[77],"(i.e.,":[78,100],"delta":[79],"acceleration).":[81],"The":[82,141],"ensures":[85],"temporal":[87,131],"continuity":[88],"of":[89],"output":[90],"frames":[91],"with":[92,160],"same":[94],"speaker.":[95],"Inspired":[96],"heuristics":[99],"vocal":[101],"tract":[102],"continuity)":[103],"in":[104],"computational":[105],"auditory":[106],"scene":[107],"analysis,":[108],"then":[110],"extend":[111],"model":[113],"adding":[115],"Grid":[117],"LSTM":[118],"layer,":[119],"that":[120],"name":[122],"it":[123],"as":[124],"cuPIT-Grid":[125],"LSTM,":[126],"automatically":[128],"learn":[129],"both":[130,154],"spectral":[133],"patterns":[134],"input":[137],"magnitude":[138],"spectrum":[139],"simultaneously.":[140],"experimental":[142],"results":[143],"show":[144],"9.6%":[145],"8.5%":[147],"relative":[148],"improvements":[149],"on":[150],"WSJ0-2mix":[151],"dataset":[152],"under":[153],"closed":[155],"open":[157],"conditions":[158],"comparing":[159],"baseline.":[163]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":19},{"year":2020,"cited_by_count":23},{"year":2019,"cited_by_count":29},{"year":2018,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}