{"id":"https://openalex.org/W2756050682","doi":"https://doi.org/10.1109/mmsp.2017.8122280","title":"Binaural and log-power spectra features with deep neural networks for speech-noise separation","display_name":"Binaural and log-power spectra features with deep neural networks for speech-noise separation","publication_year":2017,"publication_date":"2017-10-01","ids":{"openalex":"https://openalex.org/W2756050682","doi":"https://doi.org/10.1109/mmsp.2017.8122280","mag":"2756050682"},"language":"en","primary_location":{"id":"doi:10.1109/mmsp.2017.8122280","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp.2017.8122280","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE 19th International Workshop on Multimedia Signal Processing (MMSP)","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/A5022990754","display_name":"Alfredo Zermini","orcid":null},"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":true,"raw_author_name":"Alfredo Zermini","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, Surrey, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074138677","display_name":"Qingju Liu","orcid":"https://orcid.org/0000-0003-2288-3417"},"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":"Qingju Liu","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, Surrey, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101467338","display_name":"Yong Xu","orcid":"https://orcid.org/0000-0003-4944-6890"},"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":"Yong Xu","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, Surrey, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066967599","display_name":"Mark D. Plumbley","orcid":"https://orcid.org/0000-0002-9708-1075"},"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":"Mark D. Plumbley","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, Surrey, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067605755","display_name":"Dave Betts","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dave Betts","raw_affiliation_strings":["CEDAR Audio Ltd, Cambridge, UK"],"affiliations":[{"raw_affiliation_string":"CEDAR Audio Ltd, Cambridge, UK","institution_ids":[]}]},{"author_position":"last","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, Surrey, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5022990754"],"corresponding_institution_ids":["https://openalex.org/I28290843"],"apc_list":null,"apc_paid":null,"fwci":1.1193,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.79377511,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"23","issue":null,"first_page":"1","last_page":"6"},"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.998199999332428,"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/binaural-recording","display_name":"Binaural recording","score":0.8808682560920715},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.715280294418335},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.6412696838378906},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6327182054519653},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.6186895370483398},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5566810965538025},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5197279453277588},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.5063081979751587},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.46636900305747986},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.4451262354850769},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4338875412940979},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2689181864261627},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2572566866874695},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.13328957557678223},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.13209763169288635}],"concepts":[{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.8808682560920715},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.715280294418335},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.6412696838378906},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6327182054519653},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.6186895370483398},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5566810965538025},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5197279453277588},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.5063081979751587},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.46636900305747986},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.4451262354850769},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4338875412940979},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2689181864261627},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2572566866874695},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.13328957557678223},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.13209763169288635},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/mmsp.2017.8122280","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp.2017.8122280","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE 19th International Workshop on Multimedia Signal Processing (MMSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:alma.44SUR_INST:11138556410002346","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4210197018","display_name":"View","issn_l":"2688-268X","issn":["2688-268X","2688-3988"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:epubs.surrey.ac.uk:841892","is_oa":false,"landing_page_url":"http://epubs.surrey.ac.uk/841892/1/Binaural%20and%20Log-Power%20Spectra%20Features%20with%20Deep%20Neural%20Networks%20for%20Speech-Noise%20Separation.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400680","display_name":"Surrey Research Insight Open Access (The University of Surrey)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28290843","host_organization_name":"University of Surrey","host_organization_lineage":["https://openalex.org/I28290843"],"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":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.550000011920929}],"awards":[{"id":"https://openalex.org/G6513227722","display_name":null,"funder_award_id":"EP/L027119/2","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1635512741","https://openalex.org/W1755563775","https://openalex.org/W1790748249","https://openalex.org/W1832112969","https://openalex.org/W1992879732","https://openalex.org/W2044893557","https://openalex.org/W2067295501","https://openalex.org/W2078528584","https://openalex.org/W2100495367","https://openalex.org/W2101616935","https://openalex.org/W2129171989","https://openalex.org/W2135029798","https://openalex.org/W2291372403","https://openalex.org/W2397226255","https://openalex.org/W2561557072","https://openalex.org/W2597052513","https://openalex.org/W3124794156","https://openalex.org/W3143596294","https://openalex.org/W4233392025","https://openalex.org/W6680012447","https://openalex.org/W6712317276","https://openalex.org/W6734974674","https://openalex.org/W7065181925"],"related_works":["https://openalex.org/W1982169876","https://openalex.org/W2005888073","https://openalex.org/W1986772939","https://openalex.org/W2037635165","https://openalex.org/W2738829087","https://openalex.org/W2542062716","https://openalex.org/W1505346162","https://openalex.org/W4200562864","https://openalex.org/W4256175191","https://openalex.org/W2770624987"],"abstract_inverted_index":{"Binaural":[0],"features":[1,37,65,94,125],"of":[2,35,63,128],"interaural":[3,7],"level":[4],"difference":[5,9,83],"and":[6,66,86,89,134],"phase":[8],"have":[10],"proved":[11],"to":[12,22,70,95,109,130],"be":[13],"very":[14],"effective":[15],"in":[16,30,40,52,126],"training":[17],"deep":[18],"neural":[19],"networks":[20],"(DNNs),":[21],"generate":[23],"time-frequency":[24],"masks":[25],"for":[26],"target":[27],"speech":[28,51,85],"extraction":[29],"speech-speech":[31],"mixtures.":[32],"However,":[33],"effectiveness":[34],"binaural":[36,64,124],"is":[38],"reduced":[39],"more":[41],"common":[42],"speech-noise":[43],"scenarios,":[44],"since":[45],"the":[46,50,57,61,71,76,81,91,97,119],"noise":[47,87,110],"may":[48],"over-shadow":[49],"adverse":[53],"conditions.":[54],"In":[55],"addition,":[56],"reverberation":[58],"also":[59],"decreases":[60],"sparsity":[62],"therefore":[67],"adds":[68],"difficulties":[69],"separation":[72],"task.":[73],"To":[74],"address":[75],"above":[77],"limitations,":[78],"we":[79],"highlight":[80],"spectral":[82],"between":[84],"spectra":[88,93],"incorporate":[90],"log-power":[92],"extend":[96],"DNN":[98],"input.":[99],"Tested":[100],"on":[101],"two":[102],"different":[103,107],"reverberant":[104],"rooms":[105],"at":[106],"signal":[108,129],"ratios":[111],"(SNR),":[112],"our":[113],"proposed":[114],"method":[115,121],"shows":[116],"advantages":[117],"over":[118],"baseline":[120],"using":[122],"only":[123],"terms":[127],"distortion":[131],"ratio":[132],"(SDR)":[133],"Short-Time":[135],"Perceptual":[136],"Intelligibility":[137],"(STOI).":[138]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}