{"id":"https://openalex.org/W2102346872","doi":"https://doi.org/10.1109/icassp.2008.4517928","title":"Robust speaker identification using auditory features and computational auditory scene analysis","display_name":"Robust speaker identification using auditory features and computational auditory scene analysis","publication_year":2008,"publication_date":"2008-03-01","ids":{"openalex":"https://openalex.org/W2102346872","doi":"https://doi.org/10.1109/icassp.2008.4517928","mag":"2102346872"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2008.4517928","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4517928","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5079984408","display_name":"Yang Shao","orcid":"https://orcid.org/0000-0002-4870-7406"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yang Shao","raw_affiliation_strings":["Department of Computer Science and Engineering, Ohio State Uinversity, Columbus, OH, USA","Department of Computer Science and Engineering Ohio State University, Columbus OH"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Ohio State Uinversity, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering Ohio State University, Columbus OH","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051837453","display_name":"DeLiang Wang","orcid":"https://orcid.org/0000-0001-8195-6319"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"DeLiang Wang","raw_affiliation_strings":["Department of Computer Science and Engineering, Ohio State Uinversity, Columbus, OH, USA","Department of Computer Science and Engineering Ohio State University, Columbus OH"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Ohio State Uinversity, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering Ohio State University, Columbus OH","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5079984408"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":4.445,"has_fulltext":false,"cited_by_count":123,"citation_normalized_percentile":{"value":0.95652174,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1589","last_page":"1592"},"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":0.9997000098228455,"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/speech-recognition","display_name":"Speech recognition","score":0.8019288778305054},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7906098961830139},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7639747262001038},{"id":"https://openalex.org/keywords/computational-auditory-scene-analysis","display_name":"Computational auditory scene analysis","score":0.7068115472793579},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6572385430335999},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.5227287411689758},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.511403501033783},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4574297368526459},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4562950134277344},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4499755799770355},{"id":"https://openalex.org/keywords/auditory-scene-analysis","display_name":"Auditory scene analysis","score":0.4445541799068451},{"id":"https://openalex.org/keywords/auditory-system","display_name":"Auditory system","score":0.43114137649536133},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.2086295187473297}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8019288778305054},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7906098961830139},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7639747262001038},{"id":"https://openalex.org/C73208851","wikidata":"https://www.wikidata.org/wiki/Q5157303","display_name":"Computational auditory scene analysis","level":2,"score":0.7068115472793579},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6572385430335999},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.5227287411689758},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.511403501033783},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4574297368526459},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4562950134277344},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4499755799770355},{"id":"https://openalex.org/C38129911","wikidata":"https://www.wikidata.org/wiki/Q4820038","display_name":"Auditory scene analysis","level":3,"score":0.4445541799068451},{"id":"https://openalex.org/C2777443451","wikidata":"https://www.wikidata.org/wiki/Q821413","display_name":"Auditory system","level":2,"score":0.43114137649536133},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2086295187473297},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","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},{"id":"https://openalex.org/C548259974","wikidata":"https://www.wikidata.org/wiki/Q569965","display_name":"Audiology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2008.4517928","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4517928","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.151.4921","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.151.4921","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.ohio-state.edu/~dwang/papers/Shao-Wang.icassp08.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"},{"id":"https://openalex.org/F4320338294","display_name":"Air Force Research Laboratory","ror":"https://ror.org/02e2egq70"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W71792008","https://openalex.org/W88864901","https://openalex.org/W140549394","https://openalex.org/W202636654","https://openalex.org/W595249637","https://openalex.org/W1575829986","https://openalex.org/W1766888123","https://openalex.org/W1973746598","https://openalex.org/W1974387177","https://openalex.org/W1991112797","https://openalex.org/W2008957275","https://openalex.org/W2013020033","https://openalex.org/W2023840531","https://openalex.org/W2044894780","https://openalex.org/W2069883713","https://openalex.org/W2069976350","https://openalex.org/W2074354966","https://openalex.org/W2114851258","https://openalex.org/W2126622418","https://openalex.org/W2128202590","https://openalex.org/W2129244720","https://openalex.org/W2137075158","https://openalex.org/W2138084857","https://openalex.org/W2143855671","https://openalex.org/W2145475542","https://openalex.org/W2164432048","https://openalex.org/W2343218625","https://openalex.org/W2478884216","https://openalex.org/W2561557072","https://openalex.org/W2907162034","https://openalex.org/W4256399001","https://openalex.org/W4285719527","https://openalex.org/W4299681030","https://openalex.org/W6679445831"],"related_works":["https://openalex.org/W3199891340","https://openalex.org/W1567098080","https://openalex.org/W2051363478","https://openalex.org/W1539684593","https://openalex.org/W2539594704","https://openalex.org/W2004648780","https://openalex.org/W2061140267","https://openalex.org/W2076931986","https://openalex.org/W2474557191","https://openalex.org/W7819095"],"abstract_inverted_index":{"The":[0],"performance":[1,96],"of":[2,71,78,107],"speaker":[3,24,65,88],"recognition":[4,25,62,92],"systems":[5],"drop":[6],"significantly":[7],"under":[8],"noisy":[9,72],"conditions.":[10,73,109],"To":[11],"improve":[12],"robustness,":[13],"we":[14,39,56],"have":[15],"recently":[16],"proposed":[17],"novel":[18],"auditory":[19,33,43,80],"features":[20,44,59,81],"and":[21,50,60],"a":[22,28,64,69,86,104],"robust":[23,61],"system":[26,93],"using":[27],"front-end":[29,102],"based":[30],"on":[31],"computational":[32],"scene":[34],"analysis.":[35],"In":[36,54],"this":[37],"paper,":[38],"further":[40],"study":[41],"the":[42,58,79],"by":[45],"exploring":[46],"different":[47],"feature":[48],"dimensions":[49],"incorporating":[51],"dynamic":[52],"features.":[53],"addition,":[55],"evaluate":[57],"in":[63,68,103],"identification":[66],"task":[67],"number":[70],"We":[74],"find":[75],"that":[76],"one":[77],"performs":[82],"substantially":[83],"better":[84],"than":[85],"conventional":[87],"feature.":[89],"Furthermore,":[90],"our":[91],"achieves":[94],"significant":[95],"improvements":[97],"compared":[98],"with":[99],"an":[100],"advanced":[101],"wide":[105],"range":[106],"signal-to-noise":[108]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":20},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":10},{"year":2015,"cited_by_count":11},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":7}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
