{"id":"https://openalex.org/W3163257865","doi":"https://doi.org/10.1109/icassp39728.2021.9414255","title":"Surrogate Source Model Learning for Determined Source Separation","display_name":"Surrogate Source Model Learning for Determined Source Separation","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3163257865","doi":"https://doi.org/10.1109/icassp39728.2021.9414255","mag":"3163257865"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414255","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414255","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5020401831","display_name":"Robin Scheibler","orcid":"https://orcid.org/0000-0002-5205-8365"},"institutions":[{"id":"https://openalex.org/I4210096607","display_name":"Line Corporation (Japan)","ror":"https://ror.org/00qg8pm87","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210096607","https://openalex.org/I60922564"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Robin Scheibler","raw_affiliation_strings":["LINE Corporation, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"LINE Corporation, Tokyo, Japan","institution_ids":["https://openalex.org/I4210096607"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021883714","display_name":"Masahito Togami","orcid":null},"institutions":[{"id":"https://openalex.org/I4210096607","display_name":"Line Corporation (Japan)","ror":"https://ror.org/00qg8pm87","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210096607","https://openalex.org/I60922564"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masahito Togami","raw_affiliation_strings":["LINE Corporation, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"LINE Corporation, Tokyo, Japan","institution_ids":["https://openalex.org/I4210096607"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5020401831"],"corresponding_institution_ids":["https://openalex.org/I4210096607"],"apc_list":null,"apc_paid":null,"fwci":2.4378,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.89709263,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"176","last_page":"180"},"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9994000196456909,"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":0.9973000288009644,"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":0.5745456218719482},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5211467742919922},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5096259117126465},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5057988166809082},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.454732745885849},{"id":"https://openalex.org/keywords/blind-signal-separation","display_name":"Blind signal separation","score":0.418049693107605},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.4123607575893402},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.3636884093284607},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3515967130661011},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3506602346897125},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3190457820892334},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.13790380954742432}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5745456218719482},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5211467742919922},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5096259117126465},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5057988166809082},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.454732745885849},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.418049693107605},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.4123607575893402},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3636884093284607},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3515967130661011},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3506602346897125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3190457820892334},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.13790380954742432},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414255","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414255","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6299999952316284}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1543386260","https://openalex.org/W1845880232","https://openalex.org/W2072548008","https://openalex.org/W2221409856","https://openalex.org/W2289394825","https://openalex.org/W2398042854","https://openalex.org/W2400339399","https://openalex.org/W2407185622","https://openalex.org/W2408629183","https://openalex.org/W2408744528","https://openalex.org/W2412956798","https://openalex.org/W2502139158","https://openalex.org/W2540419083","https://openalex.org/W2567070169","https://openalex.org/W2734774145","https://openalex.org/W2763188033","https://openalex.org/W2892163332","https://openalex.org/W2937235446","https://openalex.org/W2954049404","https://openalex.org/W2962780374","https://openalex.org/W2962935966","https://openalex.org/W2963375116","https://openalex.org/W2963970792","https://openalex.org/W2964058413","https://openalex.org/W3015678657","https://openalex.org/W3016244615","https://openalex.org/W3080684048","https://openalex.org/W3092129032","https://openalex.org/W3093964892","https://openalex.org/W3094316140","https://openalex.org/W3129864860","https://openalex.org/W6632571750","https://openalex.org/W6638690007","https://openalex.org/W6714614974","https://openalex.org/W6731370813","https://openalex.org/W6770045915","https://openalex.org/W6776228663","https://openalex.org/W6781933183","https://openalex.org/W6784417655","https://openalex.org/W6790265010"],"related_works":["https://openalex.org/W4386190339","https://openalex.org/W2968424575","https://openalex.org/W3142333283","https://openalex.org/W2580650124","https://openalex.org/W3122088529","https://openalex.org/W3041320102","https://openalex.org/W2111669074","https://openalex.org/W2085259108","https://openalex.org/W3123087812","https://openalex.org/W2071416974"],"abstract_inverted_index":{"We":[0,138,157,189],"propose":[1],"to":[2,22,89,93,119,161,174,182],"learn":[3],"surrogate":[4,44,144],"functions":[5],"of":[6,66,83,99,108,149,165],"universal":[7],"speech":[8,13,16],"priors":[9,17],"for":[10],"determined":[11],"blind":[12],"separation.":[14],"Deep":[15],"are":[18,28],"highly":[19],"desirable":[20],"due":[21,92],"their":[23],"superior":[24],"modelling":[25],"power,":[26],"but":[27],"not":[29,47],"compatible":[30],"with":[31,56,132],"state-of-the-art":[32],"independent":[33],"vector":[34],"analysis":[35],"based":[36],"on":[37,125,147],"majorization-minimization":[38],"(AuxIVA),":[39],"since":[40],"deriving":[41],"the":[42,62,75,141,166,183],"required":[43],"function":[45],"is":[46,123],"easy,":[48],"nor":[49],"always":[50],"possible.":[51],"Instead,":[52],"we":[53,72,130],"do":[54],"away":[55],"exact":[57],"majorization":[58],"and":[59,97,114,129,136,151],"directly":[60],"approximate":[61,143],"surrogate.":[63],"Taking":[64],"advantage":[65],"iterative":[67],"source":[68],"steering":[69],"(ISS)":[70],"updates,":[71],"back":[73],"propagate":[74],"permutation":[76],"invariant":[77,110],"separation":[78],"loss":[79,172],"through":[80],"multiple":[81],"iterations":[82],"AuxIVA.":[84],"ISS":[85],"lends":[86],"itself":[87],"well":[88,146],"this":[90],"task":[91],"its":[94],"lower":[95],"complexity":[96],"lack":[98],"matrix":[100],"inversion.":[101],"Experiments":[102],"show":[103],"large":[104],"improvements":[105],"in":[106,177,197],"terms":[107],"scale":[109],"signal-to-distortion":[111],"(SDR)":[112],"ratio":[113],"word":[115,185],"error":[116,186],"rate":[117,187],"compared":[118],"baseline":[120],"methods.":[121],"Training":[122],"done":[124],"two":[126,133],"speakers":[127,153],"mixtures":[128,148],"experiment":[131],"losses,":[134],"SDR":[135,171],"coherence.":[137],"find":[139],"that":[140],"learnt":[142],"generalizes":[145],"three":[150],"four":[152],"without":[154],"any":[155],"modification.":[156],"also":[158],"demonstrate":[159],"generalization":[160],"a":[162],"different":[163],"variation":[164],"AuxIVA":[167],"update":[168],"equations.":[169],"The":[170],"leads":[173,181],"fastest":[175],"convergence":[176],"iterations,":[178],"while":[179],"coherence":[180],"lowest":[184],"(WER).":[188],"obtain":[190],"as":[191,193],"much":[192],"36":[194],"%":[195],"reduction":[196],"WER.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}