{"id":"https://openalex.org/W2291372403","doi":"https://doi.org/10.1186/s13636-016-0085-x","title":"Localization based stereo speech source separation using probabilistic time-frequency masking and deep neural networks","display_name":"Localization based stereo speech source separation using probabilistic time-frequency masking and deep neural networks","publication_year":2016,"publication_date":"2016-03-04","ids":{"openalex":"https://openalex.org/W2291372403","doi":"https://doi.org/10.1186/s13636-016-0085-x","mag":"2291372403"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-016-0085-x","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-016-0085-x","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-016-0085-x","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-016-0085-x","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":true,"raw_author_name":"Yang Yu","raw_affiliation_strings":["School of Marine Science and Technology, Northwestern Polytechnical University, Xi\u2019an, China","School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, China","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, Guildford, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Vision Speech and Signal Processing, University of Surrey, Guildford, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101902729","display_name":"Han Peng","orcid":"https://orcid.org/0000-0001-8400-4663"},"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":"Peng Han","raw_affiliation_strings":["School of Marine Science and Technology, Northwestern Polytechnical University, Xi\u2019an, China","School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100458521"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":{"value":1115,"currency":"GBP","value_usd":1367},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1367},"fwci":6.0523,"has_fulltext":true,"cited_by_count":54,"citation_normalized_percentile":{"value":0.96945338,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"2016","issue":"1","first_page":null,"last_page":null},"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":0.9987000226974487,"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":0.9980000257492065,"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":0.7462601661682129},{"id":"https://openalex.org/keywords/binaural-recording","display_name":"Binaural recording","score":0.7299683094024658},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.6773554086685181},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.600553035736084},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5705448985099792},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5659032464027405},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5570011138916016},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5448243021965027},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5345373153686523},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.43760547041893005},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4144083559513092},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.2618439793586731}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7462601661682129},{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.7299683094024658},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.6773554086685181},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.600553035736084},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5705448985099792},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5659032464027405},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5570011138916016},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5448243021965027},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5345373153686523},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.43760547041893005},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4144083559513092},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2618439793586731}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1186/s13636-016-0085-x","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-016-0085-x","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-016-0085-x","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1186/s13636-016-0085-x","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-016-0085-x","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-016-0085-x","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.8299999833106995,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321979","display_name":"University of Surrey","ror":"https://ror.org/00ks66431"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2291372403.pdf","grobid_xml":"https://content.openalex.org/works/W2291372403.grobid-xml"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W42107399","https://openalex.org/W133022121","https://openalex.org/W1504869774","https://openalex.org/W1506806321","https://openalex.org/W1548802052","https://openalex.org/W1581848821","https://openalex.org/W1601795611","https://openalex.org/W1635512741","https://openalex.org/W1663973292","https://openalex.org/W1726370773","https://openalex.org/W1755563775","https://openalex.org/W1790748249","https://openalex.org/W1832112969","https://openalex.org/W1963970749","https://openalex.org/W1984541135","https://openalex.org/W1989364685","https://openalex.org/W1992879732","https://openalex.org/W1999841894","https://openalex.org/W2006275398","https://openalex.org/W2018541726","https://openalex.org/W2021396747","https://openalex.org/W2025198378","https://openalex.org/W2031583051","https://openalex.org/W2031647436","https://openalex.org/W2036351241","https://openalex.org/W2060108923","https://openalex.org/W2072128103","https://openalex.org/W2073612610","https://openalex.org/W2076063813","https://openalex.org/W2078528584","https://openalex.org/W2084514013","https://openalex.org/W2088399049","https://openalex.org/W2093866254","https://openalex.org/W2101616935","https://openalex.org/W2110798204","https://openalex.org/W2114338548","https://openalex.org/W2122982914","https://openalex.org/W2123649031","https://openalex.org/W2127851351","https://openalex.org/W2129171989","https://openalex.org/W2139427956","https://openalex.org/W2141411743","https://openalex.org/W2160815625","https://openalex.org/W2163922914","https://openalex.org/W2168231600","https://openalex.org/W2246822104","https://openalex.org/W2561557072","https://openalex.org/W2595840341","https://openalex.org/W3146320432","https://openalex.org/W3203224907","https://openalex.org/W4231109964","https://openalex.org/W4233385860","https://openalex.org/W4233392025","https://openalex.org/W6629146343"],"related_works":["https://openalex.org/W3107204728","https://openalex.org/W4287591324","https://openalex.org/W4226420367","https://openalex.org/W2980176872","https://openalex.org/W2962876041","https://openalex.org/W3090555870","https://openalex.org/W3108503355","https://openalex.org/W2249953602","https://openalex.org/W2915887922","https://openalex.org/W2903939003"],"abstract_inverted_index":{"Time-frequency":[0],"(T-F)":[1],"masking":[2,235],"is":[3,22,66,76,195],"an":[4],"effective":[5],"method":[6],"for":[7,57,107,203,225],"stereo":[8,42],"speech":[9,43,124,227],"source":[10,85,204],"separation.":[11,58,205],"However,":[12],"reliable":[13],"estimation":[14],"of":[15,68,82,116,165,221],"the":[16,33,61,80,83,109,114,133,136,156,163,170,173,191,200,219,222],"T-F":[17,55,88,177,234],"mask":[18,56,202],"from":[19,147],"sound":[20],"mixtures":[21],"a":[23,40,73,232],"challenging":[24],"task,":[25],"especially":[26],"when":[27],"room":[28,118],"reverberations":[29],"are":[30,50,215],"present":[31],"in":[32,127],"mixtures.":[34],"In":[35],"this":[36],"paper,":[37],"we":[38,139],"propose":[39],"new":[41],"separation":[44],"system":[45,224],"where":[46],"deep":[47,62],"neural":[48,63],"networks":[49,110],"used":[51,77,197],"to":[52,78,132,143,154,180,198,217],"generate":[53,199],"soft":[54,201],"More":[59],"specifically,":[60],"network,":[64],"which":[65,194],"composed":[67],"two":[69],"sparse":[70],"autoencoders":[71],"and":[72,101,122,150,162,184,212],"softmax":[74],"regression,":[75],"estimate":[79],"orientations":[81,164],"dominant":[84,166],"at":[86],"each":[87,176],"unit,":[89],"based":[90,189,207],"on":[91,190,208],"low-level":[92,148],"features,":[93],"such":[94],"as":[95,229],"mixing":[96],"vector":[97],"(MV),":[98],"interaural":[99],"level,":[100],"phase":[102],"difference":[103],"(IPD/ILD).":[104],"The":[105],"dataset":[106,214],"training":[108,137],"was":[111],"generated":[112],"by":[113],"convolution":[115],"binaural":[117,210],"impulse":[119],"responses":[120],"(RIRs)":[121],"clean":[123],"signals":[125],"positioned":[126],"different":[128,181],"angles":[129],"with":[130,231],"respect":[131],"sensors.":[134],"With":[135],"dataset,":[138],"use":[140,151],"unsupervised":[141],"learning":[142,153],"extract":[144],"high-level":[145,160],"features":[146,149,161],"supervised":[152],"find":[155],"nonlinear":[157],"functions":[158],"between":[159],"source.":[167],"By":[168],"using":[169],"trained":[171],"networks,":[172],"probability":[174],"that":[175],"unit":[178],"belongs":[179],"sources":[182],"(target":[183],"interferers)":[185],"can":[186],"be":[187],"estimated":[188],"localization":[192],"cues":[193],"further":[196],"Experiments":[206],"real":[209],"RIRs":[211],"TIMIT":[213],"provided":[216],"show":[218],"performance":[220],"proposed":[223,237],"reverberant":[226],"mixtures,":[228],"compared":[230],"model-based":[233],"technique":[236],"recently.":[238]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}