{"id":"https://openalex.org/W1570838609","doi":"https://doi.org/10.1109/icassp.2015.7178062","title":"Representation models in single channel source separation","display_name":"Representation models in single channel source separation","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1570838609","doi":"https://doi.org/10.1109/icassp.2015.7178062","mag":"1570838609"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7178062","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178062","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 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/A5028921456","display_name":"Matthias Z\u00f6hrer","orcid":"https://orcid.org/0000-0002-7406-7924"},"institutions":[{"id":"https://openalex.org/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]},{"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","US"],"is_corresponding":true,"raw_author_name":"Matthias Zohrer","raw_affiliation_strings":["Signal Processing and Speech Communication Lab, Graz University of Technology","Signal Processing & Speech Communication Lab., Graz University of Technology, Austria"],"affiliations":[{"raw_affiliation_string":"Signal Processing and Speech Communication Lab, Graz University of Technology","institution_ids":["https://openalex.org/I4092182","https://openalex.org/I4210121626"]},{"raw_affiliation_string":"Signal Processing & Speech Communication Lab., Graz University of Technology, Austria","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"]},{"id":"https://openalex.org/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]}],"countries":["AT","US"],"is_corresponding":false,"raw_author_name":"Franz Pernkopf","raw_affiliation_strings":["Signal Processing and Speech Communication Lab, Graz University of Technology","Signal Processing & Speech Communication Lab., Graz University of Technology, Austria"],"affiliations":[{"raw_affiliation_string":"Signal Processing and Speech Communication Lab, Graz University of Technology","institution_ids":["https://openalex.org/I4092182","https://openalex.org/I4210121626"]},{"raw_affiliation_string":"Signal Processing & Speech Communication Lab., Graz University of Technology, Austria","institution_ids":["https://openalex.org/I4092182"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5028921456"],"corresponding_institution_ids":["https://openalex.org/I4092182","https://openalex.org/I4210121626"],"apc_list":null,"apc_paid":null,"fwci":1.723,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.8438575,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"26","issue":null,"first_page":"713","last_page":"717"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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"}},{"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"}}],"keywords":[{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.8631656765937805},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.765106201171875},{"id":"https://openalex.org/keywords/pesq","display_name":"PESQ","score":0.7526631355285645},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6965252757072449},{"id":"https://openalex.org/keywords/boltzmann-machine","display_name":"Boltzmann machine","score":0.6461877226829529},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5641064643859863},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5613422989845276},{"id":"https://openalex.org/keywords/bernoullis-principle","display_name":"Bernoulli's principle","score":0.5021889209747314},{"id":"https://openalex.org/keywords/computational-auditory-scene-analysis","display_name":"Computational auditory scene analysis","score":0.4878816604614258},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4679504930973053},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46661797165870667},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4650503396987915},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37563779950141907},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3755982220172882},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.24413064122200012},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1428576111793518},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.12029239535331726}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8631656765937805},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.765106201171875},{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.7526631355285645},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6965252757072449},{"id":"https://openalex.org/C192576344","wikidata":"https://www.wikidata.org/wiki/Q194706","display_name":"Boltzmann machine","level":3,"score":0.6461877226829529},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5641064643859863},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5613422989845276},{"id":"https://openalex.org/C152361515","wikidata":"https://www.wikidata.org/wiki/Q181328","display_name":"Bernoulli's principle","level":2,"score":0.5021889209747314},{"id":"https://openalex.org/C73208851","wikidata":"https://www.wikidata.org/wiki/Q5157303","display_name":"Computational auditory scene analysis","level":2,"score":0.4878816604614258},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4679504930973053},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46661797165870667},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4650503396987915},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37563779950141907},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3755982220172882},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.24413064122200012},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1428576111793518},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.12029239535331726},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2015.7178062","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178062","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W16016350","https://openalex.org/W44815768","https://openalex.org/W44831635","https://openalex.org/W1533861849","https://openalex.org/W1813659000","https://openalex.org/W1902027874","https://openalex.org/W1904365287","https://openalex.org/W1964812476","https://openalex.org/W2015143272","https://openalex.org/W2025768430","https://openalex.org/W2042492924","https://openalex.org/W2072128103","https://openalex.org/W2093866254","https://openalex.org/W2094461119","https://openalex.org/W2099904336","https://openalex.org/W2099936868","https://openalex.org/W2100495367","https://openalex.org/W2103359087","https://openalex.org/W2105288628","https://openalex.org/W2105921478","https://openalex.org/W2110798204","https://openalex.org/W2115096495","https://openalex.org/W2116825644","https://openalex.org/W2124149378","https://openalex.org/W2124173482","https://openalex.org/W2126398289","https://openalex.org/W2134842679","https://openalex.org/W2136936677","https://openalex.org/W2138939691","https://openalex.org/W2148575186","https://openalex.org/W2160815625","https://openalex.org/W2184045248","https://openalex.org/W2218318129","https://openalex.org/W2401665178","https://openalex.org/W2404000792","https://openalex.org/W2405258286","https://openalex.org/W2953267151","https://openalex.org/W2963698439","https://openalex.org/W4231109964","https://openalex.org/W6600645948","https://openalex.org/W6601785968","https://openalex.org/W6631943919","https://openalex.org/W6640036494","https://openalex.org/W6674259212","https://openalex.org/W6675321185","https://openalex.org/W6679061810","https://openalex.org/W6680066585","https://openalex.org/W6680067488","https://openalex.org/W6680324615","https://openalex.org/W6688386640","https://openalex.org/W6691534501","https://openalex.org/W6713160794","https://openalex.org/W6713676406"],"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/W2059119686","https://openalex.org/W2898606530","https://openalex.org/W4289362680","https://openalex.org/W2403380333","https://openalex.org/W2761596192"],"abstract_inverted_index":{"Model-based":[0],"single-channel":[1],"source":[2,82],"separation":[3,113],"(SCSS)":[4],"is":[5,98],"an":[6,130],"ill-posed":[7],"problem":[8],"requiring":[9],"source-specific":[10,48],"prior":[11],"knowledge.":[12,49],"In":[13,50,76],"this":[14],"paper,":[15],"we":[16,67],"use":[17],"representation":[18],"learning":[19],"and":[20,39,89,115,129,141],"compare":[21],"general":[22],"stochastic":[23],"networks":[24],"(GSNs),":[25],"Gauss":[26,33],"Bernoulli":[27,34],"restricted":[28,35],"Boltzmann":[29,36],"machines":[30,37],"(GBRBMs),":[31],"conditional":[32],"(CGBRBMs),":[38],"higher":[40],"order":[41],"contractive":[42],"autoencoders":[43],"(HCAEs)":[44],"for":[45,72,92,118,147],"modeling":[46],"the":[47,73,77,80,90,95,103,109,138],"particular,":[51],"these":[52],"models":[53,86],"learn":[54],"a":[55,119,122,125],"mapping":[56],"from":[57],"speech":[58,74,112],"mixture":[59],"spectrogram":[60,64],"representations":[61],"to":[62],"single-source":[63],"representations,":[65],"i.e.":[66],"apply":[68],"them":[69],"as":[70],"filter":[71],"mixture.":[75],"test":[78],"case,":[79],"individual":[81],"spectrograms":[83],"of":[84,94,108],"both":[85],"are":[87],"inferred":[88],"softmask":[91],"re-synthesis":[93],"time":[96],"signals":[97],"determined":[99],"thereof.":[100],"We":[101],"evaluate":[102],"deep":[104],"architectures":[105],"on":[106,145],"data":[107],"2nd":[110],"CHiME":[111],"challenge":[114],"provide":[116],"results":[117],"speaker":[120,123],"dependent,":[121],"independent,":[124],"matched":[126],"noise":[127,132],"condition":[128,133],"unmatched":[131],"task.":[134],"Our":[135],"experiments":[136],"show":[137],"best":[139],"PESQ":[140],"overall":[142],"perceptual":[143],"score":[144],"average":[146],"GSNs":[148],"in":[149],"all":[150],"four":[151],"tasks.":[152]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}