{"id":"https://openalex.org/W2099936868","doi":"https://doi.org/10.1109/icassp.2012.6287864","title":"On linear and mixmax interaction models for single channel source separation","display_name":"On linear and mixmax interaction models for single channel source separation","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2099936868","doi":"https://doi.org/10.1109/icassp.2012.6287864","mag":"2099936868"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6287864","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6287864","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 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/A5057485787","display_name":"Robert Peharz","orcid":"https://orcid.org/0000-0002-8644-9655"},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Robert Peharz","raw_affiliation_strings":["Signal Processing and Speech Communication Laboratory, Graz University of Technology, Austria","Signal Processing and Speech Communication Laboratory, Graz University of Technology, Austria#TAB#"],"affiliations":[{"raw_affiliation_string":"Signal Processing and Speech Communication Laboratory, Graz University of Technology, Austria","institution_ids":["https://openalex.org/I4092182"]},{"raw_affiliation_string":"Signal Processing and Speech Communication Laboratory, Graz University of Technology, Austria#TAB#","institution_ids":["https://openalex.org/I4092182"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015798259","display_name":"Franz Pernkopf","orcid":"https://orcid.org/0000-0002-6356-3367"},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Franz Pernkopf","raw_affiliation_strings":["Signal Processing and Speech Communication Laboratory, Graz University of Technology, Austria","Signal Processing and Speech Communication Laboratory, Graz University of Technology, Austria#TAB#"],"affiliations":[{"raw_affiliation_string":"Signal Processing and Speech Communication Laboratory, Graz University of Technology, Austria","institution_ids":["https://openalex.org/I4092182"]},{"raw_affiliation_string":"Signal Processing and Speech Communication Laboratory, Graz University of Technology, Austria#TAB#","institution_ids":["https://openalex.org/I4092182"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5057485787"],"corresponding_institution_ids":["https://openalex.org/I4092182"],"apc_list":null,"apc_paid":null,"fwci":0.7429,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.75067922,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"14","issue":null,"first_page":"249","last_page":"252"},"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":0.9990000128746033,"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":0.9983000159263611,"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/spectrogram","display_name":"Spectrogram","score":0.657437264919281},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.6543765664100647},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5888062119483948},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.5862542986869812},{"id":"https://openalex.org/keywords/interference","display_name":"Interference (communication)","score":0.5011460781097412},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4729052782058716},{"id":"https://openalex.org/keywords/blind-signal-separation","display_name":"Blind signal separation","score":0.4681304693222046},{"id":"https://openalex.org/keywords/factorial","display_name":"Factorial","score":0.4625474810600281},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.46106964349746704},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.45670175552368164},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4452972710132599},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.421170711517334},{"id":"https://openalex.org/keywords/white-noise","display_name":"White noise","score":0.41426998376846313},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.35558345913887024},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32304322719573975},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.2668949365615845},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24945223331451416},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11761030554771423},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.09287899732589722}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.657437264919281},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.6543765664100647},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5888062119483948},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.5862542986869812},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.5011460781097412},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4729052782058716},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.4681304693222046},{"id":"https://openalex.org/C183763347","wikidata":"https://www.wikidata.org/wiki/Q120976","display_name":"Factorial","level":2,"score":0.4625474810600281},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.46106964349746704},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.45670175552368164},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4452972710132599},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.421170711517334},{"id":"https://openalex.org/C112633086","wikidata":"https://www.wikidata.org/wiki/Q381287","display_name":"White noise","level":2,"score":0.41426998376846313},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35558345913887024},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32304322719573975},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2668949365615845},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24945223331451416},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11761030554771423},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.09287899732589722},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2012.6287864","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6287864","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:generic.eprints.org:891611","is_oa":false,"landing_page_url":"http://publications.eng.cam.ac.uk/891611/","pdf_url":null,"source":{"id":"https://openalex.org/S4406922847","display_name":"Cambridge University Engineering Department Publications Database","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W44831635","https://openalex.org/W160800111","https://openalex.org/W1500640442","https://openalex.org/W1893859273","https://openalex.org/W1989954041","https://openalex.org/W2015143272","https://openalex.org/W2035277481","https://openalex.org/W2044222806","https://openalex.org/W2059833849","https://openalex.org/W2095967949","https://openalex.org/W2127851351","https://openalex.org/W2134807719","https://openalex.org/W2168793898","https://openalex.org/W2561557072","https://openalex.org/W4233392025","https://openalex.org/W6601817925","https://openalex.org/W6684458083"],"related_works":["https://openalex.org/W3094316140","https://openalex.org/W3133205200","https://openalex.org/W2898145319","https://openalex.org/W4289363934","https://openalex.org/W2098101267","https://openalex.org/W1509813908","https://openalex.org/W2059119686","https://openalex.org/W2898606530","https://openalex.org/W4289362680","https://openalex.org/W2403380333"],"abstract_inverted_index":{"For":[0],"model-based":[1],"single":[2,68],"channel":[3,69],"source":[4,25,70,89],"separation,":[5],"one":[6,44],"typically":[7],"assumes":[8],"a":[9,128,139],"linear":[10,41,77],"interaction":[11,33],"model,":[12],"i.e.":[13],"that":[14,59],"the":[15,20,23,29,31,36,40,63,76,84,107,132],"mixture":[16],"magnitude":[17,26],"spectrogram":[18],"is":[19,35,61],"sum":[21],"of":[22,109,118,134],"individual":[24],"spectrograms.":[27],"In":[28],"log-domain,":[30],"MIXMAX":[32],"model":[34],"corresponding":[37],"approximation":[38],"for":[39,49,65,98],"model.":[42],"Hence,":[43],"would":[45],"expect":[46],"similar":[47],"performance":[48],"both":[50],"approaches.":[51],"However,":[52],"in":[53,87,106,138],"this":[54,60],"paper":[55],"we":[56,114],"empirically":[57],"show":[58],"not":[62],"case":[64],"vector-quantizer-based":[66],"(VQ)":[67],"separation.":[71],"We":[72],"propose":[73],"factorial":[74,80],"linear-VQ,":[75],"counterpart":[78],"to":[79],"max-VQ,":[81],"and":[82,102,120],"compare":[83,115],"two":[85],"methods":[86],"systematic":[88],"separation":[90],"experiments.":[91],"Linear-VQ":[92],"performs":[93],"significantly":[94],"better":[95,141],"than":[96],"max-VQ":[97],"comparable":[99],"code-book":[100],"sizes":[101],"behaves":[103],"more":[104],"robustly":[105],"presence":[108],"additive":[110],"white":[111],"noise.":[112],"Furthermore,":[113],"resynthesis":[116],"properties":[117],"binary":[119,125],"continuous":[121,135],"time-frequency":[122],"masks.":[123],"While":[124],"masks":[126,136],"achieve":[127],"higher":[129],"interference":[130],"suppression,":[131],"use":[133],"results":[137],"consistently":[140],"signal":[142],"quality.":[143]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}