{"id":"https://openalex.org/W2536751011","doi":"https://doi.org/10.1109/fskd.2016.7603472","title":"Perception auditory factor for speaker recognition in noisy environment","display_name":"Perception auditory factor for speaker recognition in noisy environment","publication_year":2016,"publication_date":"2016-08-01","ids":{"openalex":"https://openalex.org/W2536751011","doi":"https://doi.org/10.1109/fskd.2016.7603472","mag":"2536751011"},"language":"en","primary_location":{"id":"doi:10.1109/fskd.2016.7603472","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fskd.2016.7603472","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","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/A5100711648","display_name":"Di Wu","orcid":"https://orcid.org/0000-0002-5364-4657"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Di Wu","raw_affiliation_strings":["College of Physics, Optoelectronics and Energy, Soochow University, Suzhou, China","School of Electronic Information, Soochow University, Suzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Physics, Optoelectronics and Energy, Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]},{"raw_affiliation_string":"School of Electronic Information, Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048071193","display_name":"Heming Zhao","orcid":"https://orcid.org/0000-0001-9947-7754"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heming Zhao","raw_affiliation_strings":["School of Electronic Information, Soochow University, Suzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic Information, Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100711648","display_name":"Di Wu","orcid":"https://orcid.org/0000-0002-5364-4657"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Di Wu","raw_affiliation_strings":["College of Physics, Optoelectronics and Energy, Soochow University, Suzhou, China","School of Electronic Information, Soochow University, Suzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Physics, Optoelectronics and Energy, Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]},{"raw_affiliation_string":"School of Electronic Information, Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063460883","display_name":"Zhe Feng","orcid":"https://orcid.org/0000-0001-6036-375X"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhe Feng","raw_affiliation_strings":["College of Physics, Optoelectronics and Energy, Soochow University, Suzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Physics, Optoelectronics and Energy, Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100715502","display_name":"Liyuan Chen","orcid":"https://orcid.org/0000-0002-5345-0086"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liyuan Chen","raw_affiliation_strings":["College of Physics, Optoelectronics and Energy, Soochow University, Suzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Physics, Optoelectronics and Energy, Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019579930","display_name":"Zhongzhe Xiao","orcid":"https://orcid.org/0000-0003-3950-3070"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongzhe Xiao","raw_affiliation_strings":["College of Physics, Optoelectronics and Energy, Soochow University, Suzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Physics, Optoelectronics and Energy, Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042111579","display_name":"Xiaojun Zhang","orcid":"https://orcid.org/0000-0001-6022-0943"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojun Zhang","raw_affiliation_strings":["College of Physics, Optoelectronics and Energy, Soochow University, Suzhou, China","Soochow University, Suzhou, Jiangsu, CN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Physics, Optoelectronics and Energy, Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]},{"raw_affiliation_string":"Soochow University, Suzhou, Jiangsu, CN","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006311218","display_name":"Zhi Tao","orcid":"https://orcid.org/0000-0001-8715-6603"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi Tao","raw_affiliation_strings":["College of Physics, Optoelectronics and Energy, Soochow University, Suzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Physics, Optoelectronics and Energy, Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I3923682"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1916","last_page":"1920"},"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":0.9995999932289124,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9952999949455261,"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":0.8206486105918884},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7465783953666687},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7368465065956116},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6970086097717285},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6317349672317505},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.5917976498603821},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5657681226730347},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5472509264945984},{"id":"https://openalex.org/keywords/factor","display_name":"Factor (programming language)","score":0.45255744457244873},{"id":"https://openalex.org/keywords/computational-auditory-scene-analysis","display_name":"Computational auditory scene analysis","score":0.4438017010688782},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.41899752616882324},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4151556193828583},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40218162536621094},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08373254537582397}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8206486105918884},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7465783953666687},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7368465065956116},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6970086097717285},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6317349672317505},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.5917976498603821},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5657681226730347},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5472509264945984},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.45255744457244873},{"id":"https://openalex.org/C73208851","wikidata":"https://www.wikidata.org/wiki/Q5157303","display_name":"Computational auditory scene analysis","level":2,"score":0.4438017010688782},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.41899752616882324},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4151556193828583},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40218162536621094},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08373254537582397},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","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},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fskd.2016.7603472","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fskd.2016.7603472","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1586084638","https://openalex.org/W2047365428","https://openalex.org/W2051428568","https://openalex.org/W2069976350","https://openalex.org/W2080794664","https://openalex.org/W2090711167","https://openalex.org/W2100643000","https://openalex.org/W2121750345","https://openalex.org/W2128370471","https://openalex.org/W2140419980","https://openalex.org/W2154278880","https://openalex.org/W2397634864","https://openalex.org/W6712325649"],"related_works":["https://openalex.org/W3119288895","https://openalex.org/W2185075503","https://openalex.org/W4229940372","https://openalex.org/W2186375278","https://openalex.org/W2749720872","https://openalex.org/W2793748347","https://openalex.org/W4250904811","https://openalex.org/W2155047054","https://openalex.org/W2104528589","https://openalex.org/W2379120504"],"abstract_inverted_index":{"Speaker":[0],"recognition":[1,30,118,140],"plays":[2],"an":[3],"important":[4],"role":[5],"in":[6,31,84,99,141],"speech":[7,36,49,61],"processing":[8],"and":[9,43,124],"classification.":[10],"In":[11],"this":[12],"paper,":[13],"we":[14],"propose":[15],"a":[16,100],"features":[17,69],"extraction":[18],"method":[19,91,98,134],"using":[20,73],"Perception":[21,65,74],"Auditory":[22,66,75],"Factor":[23,76],"to":[24,63,95,108,112,126],"improve":[25],"the":[26,35,44,89,93,96,113,116,127],"performance":[27],"of":[28,103],"speaker":[29,78,139],"noisy":[32,54,87,142],"environment.":[33,143],"After":[34],"enhancement":[37,46],"based":[38],"on":[39],"auditory":[40],"perception":[41,60],"characteristic":[42],"2-dimension":[45],"for":[47,77,138],"spectrogram,":[48],"distribution":[50],"is":[51,57,135],"obtained":[52],"from":[53,105],"speech,":[55],"which":[56],"combined":[58],"with":[59],"content":[62],"extract":[64],"Factor.":[67],"Speech":[68],"are":[70],"extracted":[71],"by":[72],"recognition.":[79],"The":[80,132],"experiments":[81],"prove":[82],"that,":[83],"four":[85],"different":[86],"environments,":[88],"proposed":[90,114,133],"improves":[92],"robustness":[94],"compared":[97,129],"wide":[101],"range":[102],"SNR":[104],"\u221210":[106],"dB":[107],"20":[109],"dB.":[110],"Thanks":[111],"method,":[115],"average":[117],"correctness":[119],"rates":[120],"increase":[121],"25.2%,":[122],"19.1%":[123],"9.7%":[125],"three":[128],"methods":[130],"respectively.":[131],"more":[136],"suitable":[137]},"counts_by_year":[{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}