{"id":"https://openalex.org/W1533282361","doi":"https://doi.org/10.1109/icdsp.2015.7251849","title":"Localization based stereo speech separation using deep networks","display_name":"Localization based stereo speech separation using deep networks","publication_year":2015,"publication_date":"2015-07-01","ids":{"openalex":"https://openalex.org/W1533282361","doi":"https://doi.org/10.1109/icdsp.2015.7251849","mag":"1533282361"},"language":"en","primary_location":{"id":"doi:10.1109/icdsp.2015.7251849","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdsp.2015.7251849","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 Digital Signal Processing (DSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100458521","display_name":"Yang Yu","orcid":"https://orcid.org/0000-0002-2971-7828"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yu","raw_affiliation_strings":["Schoo1 of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, China","School of Marine Science and Technology Northwestern Polytechnical University, Xi'an, China, 710072"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Schoo1 of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Marine Science and Technology Northwestern Polytechnical University, Xi'an, China, 710072","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100676721","display_name":"Wenwu Wang","orcid":"https://orcid.org/0000-0002-8393-5703"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wenwu Wang","raw_affiliation_strings":["Centre for Vision Speech and Signal Processing, University of Surrey, UK","Centre for Vision Speech and Signal Processing, University of Surrey, UK, GU2 7XH"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Vision Speech and Signal Processing, University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"Centre for Vision Speech and Signal Processing, University of Surrey, UK, GU2 7XH","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101925640","display_name":"Luo Jian","orcid":"https://orcid.org/0000-0003-3708-4992"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Luo","raw_affiliation_strings":["Schoo1 of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, China","School of Marine Science and Technology Northwestern Polytechnical University, Xi'an, China, 710072"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Schoo1 of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Marine Science and Technology Northwestern Polytechnical University, Xi'an, China, 710072","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041045446","display_name":"Pengming Feng","orcid":"https://orcid.org/0000-0001-5853-8100"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Pengming Feng","raw_affiliation_strings":["Centre for Vision Speech and Signal Processing, University of Surrey, UK","Centre for Vision Speech and Signal Processing, University of Surrey, UK, GU2 7XH"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Vision Speech and Signal Processing, University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"Centre for Vision Speech and Signal Processing, University of Surrey, UK, GU2 7XH","institution_ids":["https://openalex.org/I28290843"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"153","last_page":"157"},"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":0.9994999766349792,"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"}},{"id":"https://openalex.org/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6723615527153015},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.6321772336959839},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5406782627105713},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4737340211868286},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.35333800315856934},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.11077222228050232}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6723615527153015},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.6321772336959839},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5406782627105713},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4737340211868286},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35333800315856934},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.11077222228050232}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdsp.2015.7251849","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdsp.2015.7251849","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 Digital Signal Processing (DSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8299999833106995,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W133022121","https://openalex.org/W1548802052","https://openalex.org/W1635512741","https://openalex.org/W1726370773","https://openalex.org/W1755563775","https://openalex.org/W1832112969","https://openalex.org/W1875231349","https://openalex.org/W1992879732","https://openalex.org/W1999841894","https://openalex.org/W2031583051","https://openalex.org/W2051434435","https://openalex.org/W2060108923","https://openalex.org/W2073612610","https://openalex.org/W2093866254","https://openalex.org/W2101616935","https://openalex.org/W2110798204","https://openalex.org/W2122982914","https://openalex.org/W2123649031","https://openalex.org/W2127851351","https://openalex.org/W2129171989","https://openalex.org/W2160815625","https://openalex.org/W2163922914","https://openalex.org/W2168231600","https://openalex.org/W2561557072","https://openalex.org/W3216401400","https://openalex.org/W4211050817","https://openalex.org/W4233392025","https://openalex.org/W6639350448","https://openalex.org/W6676481782","https://openalex.org/W6684859321"],"related_works":["https://openalex.org/W1891287906","https://openalex.org/W1969923398","https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2755342338","https://openalex.org/W2021592657","https://openalex.org/W2229312674","https://openalex.org/W3116076068","https://openalex.org/W2058170566","https://openalex.org/W2110717643"],"abstract_inverted_index":{"Time-frequency":[0],"(T-F)":[1],"masking":[2,199],"is":[3,22,64,74,107],"an":[4],"effective":[5],"method":[6,113],"for":[7,56,164,188],"stereo":[8,42],"speech":[9,43,128,190],"source":[10],"separation.":[11,57],"However,":[12],"reliable":[13],"estimation":[14],"of":[15,66,80,184],"the":[16,33,60,78,81,137,140,144,152,161,166,182,185],"T-F":[17,54,87,148,198],"mask":[18,55],"from":[19],"sound":[20],"mixtures":[21],"a":[23,40,71,110,115,195],"challenging":[24],"task,":[25],"especially":[26],"when":[27],"room":[28,122],"reverberations":[29],"are":[30,49,178],"present":[31],"in":[32,131],"mixtures.":[34],"In":[35],"this":[36],"paper,":[37],"we":[38],"proposed":[39,186,201],"new":[41],"separation":[44],"system":[45,187],"where":[46],"deep":[47,61,105,142],"networks":[48],"used":[50,75],"to":[51,76,136,151,180],"generate":[52],"soft":[53,167],"More":[58],"specifically,":[59],"network,":[62],"which":[63],"composed":[65],"two":[67],"sparse":[68],"autoencoders":[69],"and":[70,83,100,175],"softmax":[72],"classifier,":[73],"estimate":[77],"orientations":[79],"target":[82,153],"interferers":[84],"at":[85],"each":[86,147],"unit,":[88],"based":[89,159,170,197],"on":[90,160,171],"low-level":[91],"features,":[92],"such":[93],"as":[94,192],"mixing":[95],"vector":[96],"(MV),":[97],"interaural":[98],"level":[99],"phase":[101],"difference":[102],"(IPD/ILD).":[103],"The":[104],"network":[106],"trained":[108,141],"by":[109,120],"greedy":[111],"layer-wise":[112],"using":[114],"dataset":[116,177],"that":[117,146],"was":[118],"generated":[119],"convolving":[121],"impulse":[123],"responses":[124],"(RIRs)":[125],"with":[126,134,194],"clean":[127],"signals":[129],"positioned":[130],"different":[132],"angles":[133],"respect":[135],"sensors.":[138],"With":[139],"networks,":[143],"probability":[145],"unit":[149],"belongs":[150],"or":[154],"interferer":[155],"can":[156],"be":[157],"estimated":[158],"localization":[162],"cues":[163],"generating":[165],"mask.":[168],"Experiments":[169],"real":[172],"binaural":[173],"RIRs":[174],"TIMIT":[176],"provided":[179],"show":[181],"performance":[183],"reverberant":[189],"mixtures,":[191],"compared":[193],"model":[196],"technique":[200],"recently.":[202]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}