{"id":"https://openalex.org/W2295827011","doi":"https://doi.org/10.1109/ispacs.2015.7432750","title":"A sequential processing model for speech separation based on auditory scene analysis","display_name":"A sequential processing model for speech separation based on auditory scene analysis","publication_year":2015,"publication_date":"2015-11-01","ids":{"openalex":"https://openalex.org/W2295827011","doi":"https://doi.org/10.1109/ispacs.2015.7432750","mag":"2295827011"},"language":"en","primary_location":{"id":"doi:10.1109/ispacs.2015.7432750","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispacs.2015.7432750","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://repository.lib.tottori-u.ac.jp/record/7027/files/ISPCAS2015_124.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070464819","display_name":"Isao Nakanishi","orcid":"https://orcid.org/0000-0001-9533-9987"},"institutions":[{"id":"https://openalex.org/I4588055","display_name":"Tottori University","ror":"https://ror.org/024yc3q36","country_code":"JP","type":"education","lineage":["https://openalex.org/I4588055"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Isao Nakanishi","raw_affiliation_strings":["Graduate School of Engineering, Tottori University, 4-101 Koyama-minami, 680-8552, Japan","Graduate School of Engineering, Tottori University, Tottori, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, Tottori University, 4-101 Koyama-minami, 680-8552, Japan","institution_ids":["https://openalex.org/I4588055"]},{"raw_affiliation_string":"Graduate School of Engineering, Tottori University, Tottori, Japan","institution_ids":["https://openalex.org/I4588055"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045641503","display_name":"Hanada Junichi","orcid":null},"institutions":[{"id":"https://openalex.org/I4588055","display_name":"Tottori University","ror":"https://ror.org/024yc3q36","country_code":"JP","type":"education","lineage":["https://openalex.org/I4588055"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Junichi Hanada","raw_affiliation_strings":["Graduate School of Engineering, Tottori University, 4-101 Koyama-minami, 680-8552, Japan","Graduate School of Engineering, Tottori University, Tottori, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, Tottori University, 4-101 Koyama-minami, 680-8552, Japan","institution_ids":["https://openalex.org/I4588055"]},{"raw_affiliation_string":"Graduate School of Engineering, Tottori University, Tottori, Japan","institution_ids":["https://openalex.org/I4588055"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4588055"],"apc_list":null,"apc_paid":null,"fwci":0.243,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.4717326,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"124","last_page":"128"},"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":0.9998000264167786,"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":0.9990000128746033,"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/speech-recognition","display_name":"Speech recognition","score":0.7665526866912842},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7286370396614075},{"id":"https://openalex.org/keywords/auditory-scene-analysis","display_name":"Auditory scene analysis","score":0.6847284436225891},{"id":"https://openalex.org/keywords/computational-auditory-scene-analysis","display_name":"Computational auditory scene analysis","score":0.6444551944732666},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.6151286959648132},{"id":"https://openalex.org/keywords/time\u2013frequency-analysis","display_name":"Time\u2013frequency analysis","score":0.5682922601699829},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5590081810951233},{"id":"https://openalex.org/keywords/discrete-fourier-transform","display_name":"Discrete Fourier transform (general)","score":0.5149691700935364},{"id":"https://openalex.org/keywords/harmonic","display_name":"Harmonic","score":0.47088557481765747},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.469622403383255},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4359120726585388},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.4309830367565155},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4309409260749817},{"id":"https://openalex.org/keywords/fundamental-frequency","display_name":"Fundamental frequency","score":0.42995521426200867},{"id":"https://openalex.org/keywords/harmonic-analysis","display_name":"Harmonic analysis","score":0.42911022901535034},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.4192269444465637},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4044817090034485},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.36624613404273987},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.23588618636131287},{"id":"https://openalex.org/keywords/short-time-fourier-transform","display_name":"Short-time Fourier transform","score":0.22533637285232544},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.20519185066223145},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.1899089813232422},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.1873280107975006},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.14018777012825012},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1381097137928009},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09112757444381714},{"id":"https://openalex.org/keywords/electronic-engineering","display_name":"Electronic engineering","score":0.08574837446212769},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.07680392265319824}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7665526866912842},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7286370396614075},{"id":"https://openalex.org/C38129911","wikidata":"https://www.wikidata.org/wiki/Q4820038","display_name":"Auditory scene analysis","level":3,"score":0.6847284436225891},{"id":"https://openalex.org/C73208851","wikidata":"https://www.wikidata.org/wiki/Q5157303","display_name":"Computational auditory scene analysis","level":2,"score":0.6444551944732666},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.6151286959648132},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.5682922601699829},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5590081810951233},{"id":"https://openalex.org/C57733114","wikidata":"https://www.wikidata.org/wiki/Q1006032","display_name":"Discrete Fourier transform (general)","level":5,"score":0.5149691700935364},{"id":"https://openalex.org/C127934551","wikidata":"https://www.wikidata.org/wiki/Q1148098","display_name":"Harmonic","level":2,"score":0.47088557481765747},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.469622403383255},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4359120726585388},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.4309830367565155},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4309409260749817},{"id":"https://openalex.org/C10513763","wikidata":"https://www.wikidata.org/wiki/Q1331774","display_name":"Fundamental frequency","level":2,"score":0.42995521426200867},{"id":"https://openalex.org/C131770355","wikidata":"https://www.wikidata.org/wiki/Q876215","display_name":"Harmonic analysis","level":2,"score":0.42911022901535034},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.4192269444465637},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4044817090034485},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.36624613404273987},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.23588618636131287},{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.22533637285232544},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.20519185066223145},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.1899089813232422},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.1873280107975006},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.14018777012825012},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1381097137928009},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09112757444381714},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.08574837446212769},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.07680392265319824},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/ispacs.2015.7432750","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispacs.2015.7432750","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","raw_type":"proceedings-article"},{"id":"pmh:oai:irdb.nii.ac.jp:00874:0005883019","is_oa":true,"landing_page_url":"https://repository.lib.tottori-u.ac.jp/records/7027","pdf_url":"https://repository.lib.tottori-u.ac.jp/record/7027/files/ISPCAS2015_124.pdf","source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of International Symposium on Intelligent Signal Processing and Communication Systems 2015 (ISPACS2015)","raw_type":"conference paper"},{"id":"pmh:oai:repository.lib.tottori-u.ac.jp:5616","is_oa":false,"landing_page_url":"https://ieeexplore.ieee.org/abstract/document/7432750/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400575","display_name":"Tottori University research result repository (Tottori University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4588055","host_organization_name":"Tottori University","host_organization_lineage":["https://openalex.org/I4588055"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null}],"best_oa_location":{"id":"pmh:oai:irdb.nii.ac.jp:00874:0005883019","is_oa":true,"landing_page_url":"https://repository.lib.tottori-u.ac.jp/records/7027","pdf_url":"https://repository.lib.tottori-u.ac.jp/record/7027/files/ISPCAS2015_124.pdf","source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of International Symposium on Intelligent Signal Processing and Communication Systems 2015 (ISPACS2015)","raw_type":"conference paper"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2295827011.pdf","grobid_xml":"https://content.openalex.org/works/W2295827011.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W429587937","https://openalex.org/W1998986623","https://openalex.org/W2008592360","https://openalex.org/W2037722832","https://openalex.org/W2044222806","https://openalex.org/W2060822897","https://openalex.org/W2072184010","https://openalex.org/W2074549717","https://openalex.org/W2096178862","https://openalex.org/W2096496615","https://openalex.org/W2115129089","https://openalex.org/W2123879651","https://openalex.org/W2124539664","https://openalex.org/W2145562745","https://openalex.org/W2159202424","https://openalex.org/W2478203769","https://openalex.org/W4233392025","https://openalex.org/W6615066871","https://openalex.org/W6720756487"],"related_works":["https://openalex.org/W2362704157","https://openalex.org/W3199891340","https://openalex.org/W133022121","https://openalex.org/W1567098080","https://openalex.org/W2345846362","https://openalex.org/W2051363478","https://openalex.org/W1522062127","https://openalex.org/W2088740872","https://openalex.org/W2153297815","https://openalex.org/W614920976"],"abstract_inverted_index":{"Speech":[0],"separation":[1],"based":[2],"on":[3],"auditory":[4],"scene":[5],"analysis":[6],"(ASA)":[7],"has":[8],"been":[9],"widely":[10],"studied.":[11],"We":[12],"propose":[13],"a":[14,24,72],"sequential":[15,100],"processing":[16],"model":[17],"of":[18,90],"computational":[19],"ASA":[20,42],"(CASA),":[21],"in":[22,41,71,98],"which":[23,87],"mixed":[25],"speech":[26,63],"is":[27,64,88],"sequentially":[28],"decomposed":[29,47],"into":[30],"frequency":[31,48,51,69],"signals":[32,52,70],"using":[33,83],"modified":[34],"Discrete":[35],"Fourier":[36],"Transform":[37],"(DFT),":[38],"four":[39],"features":[40,92],"are":[43,53],"extracted":[44,58],"from":[45],"the":[46,50,57,68,84,91,96],"signals,":[49],"regrouped":[54],"by":[55,66],"examining":[56],"features,":[59],"and":[60,93],"each":[61],"separated":[62],"obtained":[65],"recomposing":[67],"group.":[73],"In":[74],"this":[75],"paper,":[76],"we":[77],"attempt":[78],"to":[79],"separate":[80],"speeches":[81],"only":[82],"harmonic":[85],"structure,":[86],"one":[89],"regarded":[94],"as":[95],"backbone":[97],"our":[99],"implementation":[101],"model.":[102]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}