{"id":"https://openalex.org/W1635564296","doi":"https://doi.org/10.1109/taslp.2015.2470560","title":"Representation Learning for Single-Channel Source Separation and Bandwidth Extension","display_name":"Representation Learning for Single-Channel Source Separation and Bandwidth Extension","publication_year":2015,"publication_date":"2015-08-19","ids":{"openalex":"https://openalex.org/W1635564296","doi":"https://doi.org/10.1109/taslp.2015.2470560","mag":"1635564296"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2015.2470560","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2015.2470560","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/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":"Matthias Zohrer","raw_affiliation_strings":["Intelligent Systems Group, Graz University of Technology, Graz, Austria","Intelligent Systems Group at the Signal Processing and Speech Communication Laboratory, Graz University of Technology, Graz, Austria"],"affiliations":[{"raw_affiliation_string":"Intelligent Systems Group, Graz University of Technology, Graz, Austria","institution_ids":["https://openalex.org/I4092182"]},{"raw_affiliation_string":"Intelligent Systems Group at the Signal Processing and Speech Communication Laboratory, Graz University of Technology, Graz, Austria","institution_ids":["https://openalex.org/I4092182"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057485787","display_name":"Robert Peharz","orcid":"https://orcid.org/0000-0002-8644-9655"},"institutions":[{"id":"https://openalex.org/I202276237","display_name":"Medical University of Graz","ror":"https://ror.org/02n0bts35","country_code":"AT","type":"education","lineage":["https://openalex.org/I202276237"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Robert Peharz","raw_affiliation_strings":["iDN\u2013Institute of Physiology, Medical University of Graz, Graz, Austria","Brain, Ears, and Eyes-Pattern Recognition Initiative, BioTechMed-Graz, iDN-Institute of Physiology, Medical University of Graz, Graz, Austria#TAB#"],"affiliations":[{"raw_affiliation_string":"iDN\u2013Institute of Physiology, Medical University of Graz, Graz, Austria","institution_ids":["https://openalex.org/I202276237"]},{"raw_affiliation_string":"Brain, Ears, and Eyes-Pattern Recognition Initiative, BioTechMed-Graz, iDN-Institute of Physiology, Medical University of Graz, Graz, Austria#TAB#","institution_ids":["https://openalex.org/I202276237"]}]},{"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":["Intelligent Systems Group, Graz University of Technology, Graz, Austria","Intelligent Systems Group at the Signal Processing and Speech Communication Laboratory, Graz University of Technology, Graz, Austria"],"affiliations":[{"raw_affiliation_string":"Intelligent Systems Group, Graz University of Technology, Graz, Austria","institution_ids":["https://openalex.org/I4092182"]},{"raw_affiliation_string":"Intelligent Systems Group at the Signal Processing and Speech Communication Laboratory, Graz University of Technology, Graz, Austria","institution_ids":["https://openalex.org/I4092182"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5028921456"],"corresponding_institution_ids":["https://openalex.org/I4092182"],"apc_list":null,"apc_paid":null,"fwci":3.7624,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.93883177,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"23","issue":"12","first_page":"2398","last_page":"2409"},"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/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":0.9994999766349792,"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/computer-science","display_name":"Computer science","score":0.6915925145149231},{"id":"https://openalex.org/keywords/bandwidth-extension","display_name":"Bandwidth extension","score":0.599989652633667},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5990841388702393},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5641481876373291},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5485422015190125},{"id":"https://openalex.org/keywords/pesq","display_name":"PESQ","score":0.5179023742675781},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.49919557571411133},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.49131932854652405},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.4752195477485657},{"id":"https://openalex.org/keywords/boltzmann-machine","display_name":"Boltzmann machine","score":0.452523410320282},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4524470865726471},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.4188821613788605},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4142112135887146},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4138752520084381},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.25708675384521484},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.247639000415802},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.13438832759857178},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.13063818216323853},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.10964134335517883}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6915925145149231},{"id":"https://openalex.org/C9387945","wikidata":"https://www.wikidata.org/wiki/Q4854770","display_name":"Bandwidth extension","level":4,"score":0.599989652633667},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5990841388702393},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5641481876373291},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5485422015190125},{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.5179023742675781},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.49919557571411133},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.49131932854652405},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.4752195477485657},{"id":"https://openalex.org/C192576344","wikidata":"https://www.wikidata.org/wiki/Q194706","display_name":"Boltzmann machine","level":3,"score":0.452523410320282},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4524470865726471},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.4188821613788605},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4142112135887146},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4138752520084381},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.25708675384521484},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.247639000415802},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.13438832759857178},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.13063818216323853},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.10964134335517883},{"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/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2015.2470560","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2015.2470560","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:generic.eprints.org:891607","is_oa":false,"landing_page_url":"http://publications.eng.cam.ac.uk/891607/","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":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1540304609","display_name":null,"funder_award_id":"P25244-N15","funder_id":"https://openalex.org/F4320321181","funder_display_name":"Austrian Science Fund"},{"id":"https://openalex.org/G7381131158","display_name":null,"funder_award_id":"P27803-N15","funder_id":"https://openalex.org/F4320321181","funder_display_name":"Austrian Science Fund"}],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320321181","display_name":"Austrian Science Fund","ror":"https://ror.org/013tf3c58"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":107,"referenced_works":["https://openalex.org/W16016350","https://openalex.org/W44815768","https://openalex.org/W44831635","https://openalex.org/W164542560","https://openalex.org/W186521003","https://openalex.org/W1495679096","https://openalex.org/W1511986666","https://openalex.org/W1517841224","https://openalex.org/W1533861849","https://openalex.org/W1553145417","https://openalex.org/W1570838609","https://openalex.org/W1813659000","https://openalex.org/W1814923578","https://openalex.org/W1835282959","https://openalex.org/W1902027874","https://openalex.org/W1904365287","https://openalex.org/W1964812476","https://openalex.org/W1971868317","https://openalex.org/W2015143272","https://openalex.org/W2025768430","https://openalex.org/W2028980143","https://openalex.org/W2031647436","https://openalex.org/W2034562896","https://openalex.org/W2035277481","https://openalex.org/W2037740282","https://openalex.org/W2040370888","https://openalex.org/W2042492924","https://openalex.org/W2044893557","https://openalex.org/W2069681747","https://openalex.org/W2070450685","https://openalex.org/W2072128103","https://openalex.org/W2086725969","https://openalex.org/W2091334405","https://openalex.org/W2093866254","https://openalex.org/W2100495367","https://openalex.org/W2100969003","https://openalex.org/W2103359087","https://openalex.org/W2105288628","https://openalex.org/W2105921478","https://openalex.org/W2110798204","https://openalex.org/W2113606819","https://openalex.org/W2115096495","https://openalex.org/W2116825644","https://openalex.org/W2119900738","https://openalex.org/W2120847449","https://openalex.org/W2124149378","https://openalex.org/W2124173482","https://openalex.org/W2125838338","https://openalex.org/W2126398289","https://openalex.org/W2128744540","https://openalex.org/W2130322773","https://openalex.org/W2134383396","https://openalex.org/W2134842679","https://openalex.org/W2136922672","https://openalex.org/W2136936677","https://openalex.org/W2138084857","https://openalex.org/W2138939691","https://openalex.org/W2144792281","https://openalex.org/W2146871184","https://openalex.org/W2148575186","https://openalex.org/W2153074847","https://openalex.org/W2159687189","https://openalex.org/W2160815625","https://openalex.org/W2163922914","https://openalex.org/W2165108269","https://openalex.org/W2168013545","https://openalex.org/W2168906135","https://openalex.org/W2172174689","https://openalex.org/W2184045248","https://openalex.org/W2218318129","https://openalex.org/W2249616250","https://openalex.org/W2394932179","https://openalex.org/W2399803916","https://openalex.org/W2400295372","https://openalex.org/W2401665178","https://openalex.org/W2404000792","https://openalex.org/W2945373127","https://openalex.org/W2951446714","https://openalex.org/W2953267151","https://openalex.org/W2956476286","https://openalex.org/W2963698439","https://openalex.org/W2964191424","https://openalex.org/W3159808927","https://openalex.org/W4231109964","https://openalex.org/W4253928870","https://openalex.org/W4285719527","https://openalex.org/W6600645948","https://openalex.org/W6631943919","https://openalex.org/W6638458773","https://openalex.org/W6640036494","https://openalex.org/W6675321185","https://openalex.org/W6676481782","https://openalex.org/W6676903177","https://openalex.org/W6677915450","https://openalex.org/W6679061810","https://openalex.org/W6679233511","https://openalex.org/W6680066585","https://openalex.org/W6680067488","https://openalex.org/W6680324615","https://openalex.org/W6683309385","https://openalex.org/W6684753728","https://openalex.org/W6684905728","https://openalex.org/W6688386640","https://openalex.org/W6691534501","https://openalex.org/W6713160794","https://openalex.org/W6762367593","https://openalex.org/W6765212771"],"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/W2972653970","https://openalex.org/W2059119686","https://openalex.org/W2898606530","https://openalex.org/W4289362680","https://openalex.org/W2403380333"],"abstract_inverted_index":{"In":[0,29],"this":[1],"paper,":[2],"we":[3,67],"use":[4],"deep":[5,48,70],"representation":[6,149],"learning":[7,62],"for":[8,61,87],"model-based":[9],"single-channel":[10],"source":[11],"separation":[12,82],"(SCSS)":[13],"and":[14,23,40,55,84,98,109,146],"artificial":[15],"bandwidth":[16],"extension":[17],"(ABE).":[18],"Both":[19],"tasks":[20],"are":[21,59,122],"ill-posed":[22],"source-specific":[24],"prior":[25],"knowledge":[26],"is":[27],"required.":[28],"addition":[30],"to":[31,124],"well-known":[32],"generative":[33,51],"models":[34,145,150],"such":[35],"as":[36],"restricted":[37],"Boltzmann":[38],"machines":[39],"higher":[41],"order":[42],"contractive":[43],"autoencoders":[44],"two":[45],"recently":[46],"introduced":[47],"models,":[49],"namely":[50],"stochastic":[52],"networks":[53,57],"(GSNs)":[54],"sum-product":[56],"(SPNs),":[58],"used":[60],"spectrogram":[63],"representations.":[64],"For":[65],"SCSS":[66],"evaluate":[68],"the":[69,75,106,126,147],"architectures":[71],"on":[72,113],"data":[73],"of":[74],"2":[76],"<sup":[77],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[78],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">nd</sup>":[79],"CHiME":[80],"speech":[81],"challenge":[83],"provide":[85],"results":[86],"a":[88,91,94],"speaker":[89,92],"dependent,":[90],"independent,":[93],"matched":[95],"noise":[96,101],"condition":[97,102],"an":[99],"unmatched":[100],"task.":[103],"GSNs":[104,121],"obtain":[105],"best":[107],"PESQ":[108],"overall":[110],"perceptual":[111],"score":[112],"average":[114],"in":[115,130,134,142],"all":[116],"four":[117],"tasks.":[118],"Similarly,":[119],"frame-wise":[120],"able":[123],"reconstruct":[125],"missing":[127],"frequency":[128],"bands":[129],"ABE":[131],"best,":[132],"measured":[133],"frequency-domain":[135],"segmental":[136],"SNR.":[137],"They":[138],"outperform":[139],"SPNs":[140],"embedded":[141],"hidden":[143],"Markov":[144],"other":[148],"significantly.":[151]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}