{"id":"https://openalex.org/W2062274687","doi":"https://doi.org/10.1142/s0218001412500152","title":"SPARSE-BASED AUDITORY MODEL FOR ROBUST SPEAKER RECOGNITION","display_name":"SPARSE-BASED AUDITORY MODEL FOR ROBUST SPEAKER RECOGNITION","publication_year":2012,"publication_date":"2012-11-01","ids":{"openalex":"https://openalex.org/W2062274687","doi":"https://doi.org/10.1142/s0218001412500152","mag":"2062274687"},"language":"en","primary_location":{"id":"doi:10.1142/s0218001412500152","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218001412500152","pdf_url":null,"source":{"id":"https://openalex.org/S41486457","display_name":"International Journal of Pattern Recognition and Artificial Intelligence","issn_l":"0218-0014","issn":["0218-0014","1793-6381"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Pattern Recognition and Artificial Intelligence","raw_type":"journal-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/A5005904745","display_name":"Datao You","orcid":"https://orcid.org/0000-0001-5968-4994"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"DATAO YOU","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, 92 West Dazhi Street, Nan Gang District, Harbin, 150001, P. R. China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, 92 West Dazhi Street, Nan Gang District, Harbin, 150001, P. R. China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101508830","display_name":"Jiqing Han","orcid":"https://orcid.org/0000-0002-4297-4300"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"JIQING HAN","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, 92 West Dazhi Street, Nan Gang District, Harbin, 150001, P. R. China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, 92 West Dazhi Street, Nan Gang District, Harbin, 150001, P. R. China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101846141","display_name":"Tieran Zheng","orcid":"https://orcid.org/0009-0006-5179-0278"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"TIERAN ZHENG","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, 92 West Dazhi Street, Nan Gang District, Harbin, 150001, P. R. China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, 92 West Dazhi Street, Nan Gang District, Harbin, 150001, P. R. China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041058909","display_name":"Guibin Zheng","orcid":"https://orcid.org/0000-0002-4280-5224"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"GUIBIN ZHENG","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, 92 West Dazhi Street, Nan Gang District, Harbin, 150001, P. R. China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, 92 West Dazhi Street, Nan Gang District, Harbin, 150001, P. R. China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5005904745"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":0.2448,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.55007714,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"26","issue":"07","first_page":"1250015","last_page":"1250015"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9993000030517578,"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":0.9968000054359436,"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/basilar-membrane","display_name":"Basilar membrane","score":0.8667365312576294},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7443811893463135},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7095174193382263},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6914865374565125},{"id":"https://openalex.org/keywords/sparse-approximation","display_name":"Sparse approximation","score":0.6259087324142456},{"id":"https://openalex.org/keywords/neural-coding","display_name":"Neural coding","score":0.6037839651107788},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.592103123664856},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4972076714038849},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43036335706710815},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42620033025741577},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.391653835773468},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.14610961079597473}],"concepts":[{"id":"https://openalex.org/C2780807236","wikidata":"https://www.wikidata.org/wiki/Q3503790","display_name":"Basilar membrane","level":3,"score":0.8667365312576294},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7443811893463135},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7095174193382263},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6914865374565125},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.6259087324142456},{"id":"https://openalex.org/C77637269","wikidata":"https://www.wikidata.org/wiki/Q7002051","display_name":"Neural coding","level":2,"score":0.6037839651107788},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.592103123664856},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4972076714038849},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43036335706710815},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42620033025741577},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.391653835773468},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.14610961079597473},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C2780130748","wikidata":"https://www.wikidata.org/wiki/Q317857","display_name":"Cochlea","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s0218001412500152","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218001412500152","pdf_url":null,"source":{"id":"https://openalex.org/S41486457","display_name":"International Journal of Pattern Recognition and Artificial Intelligence","issn_l":"0218-0014","issn":["0218-0014","1793-6381"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Pattern Recognition and Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W228380312","https://openalex.org/W1977450749","https://openalex.org/W2001687950","https://openalex.org/W2010023285","https://openalex.org/W2012937237","https://openalex.org/W2029654180","https://openalex.org/W2034260606","https://openalex.org/W2050693797","https://openalex.org/W2064022796","https://openalex.org/W2083197070","https://openalex.org/W2090861223","https://openalex.org/W2092389568","https://openalex.org/W2095096550","https://openalex.org/W2100969003","https://openalex.org/W2121061347","https://openalex.org/W2133285226","https://openalex.org/W2137075158","https://openalex.org/W2140609183","https://openalex.org/W2146871184","https://openalex.org/W2154278880","https://openalex.org/W3105340263","https://openalex.org/W4231354308"],"related_works":["https://openalex.org/W2890544631","https://openalex.org/W2067062989","https://openalex.org/W3004790527","https://openalex.org/W2998105788","https://openalex.org/W4205656132","https://openalex.org/W2539392819","https://openalex.org/W2111634407","https://openalex.org/W2783282829","https://openalex.org/W2579633471","https://openalex.org/W2203155458"],"abstract_inverted_index":{"The":[0],"mismatch":[1,26],"between":[2,93],"the":[3,6,11,43,64,71,79,88,105,117,123],"training":[4],"and":[5,86,96],"testing":[7],"environments":[8],"greatly":[9],"degrades":[10],"performance":[12],"of":[13,45,52,63,81,125],"speaker":[14,23,46,126],"recognition.":[15],"Although":[16],"many":[17],"robust":[18],"techniques":[19],"have":[20],"been":[21],"proposed,":[22],"recognition":[24,47,127],"in":[25,128],"condition":[27],"is":[28],"still":[29],"a":[30,38],"challenge.":[31],"To":[32,55],"solve":[33],"this":[34,56],"problem,":[35],"we":[36,58],"propose":[37],"sparse-based":[39,118],"auditory":[40,50,119],"model":[41,120],"as":[42,78],"front-end":[44],"by":[48,99],"simulating":[49],"processing":[51],"speech":[53],"signal.":[54],"end,":[57],"introduce":[59],"narrow-band":[60],"filter-bank":[61,68],"instead":[62],"widely":[65],"used":[66],"wide-band":[67],"to":[69],"simulate":[70],"basilar":[72,82,97],"membrane":[73,83,95,98],"filter-bank,":[74],"use":[75],"sparse":[76],"representation":[77],"approximation":[80],"coding":[84],"strategy,":[85],"incorporate":[87],"frequency":[89],"selectivity":[90],"enhance":[91],"mechanism":[92],"tectorial":[94],"practical":[100],"engineering":[101],"approximation.":[102],"Compared":[103],"with":[104],"standard":[106],"Mel-frequency":[107],"cepstral":[108],"coefficient":[109],"approach,":[110],"our":[111],"preliminary":[112],"experimental":[113],"results":[114],"indicate":[115],"that":[116],"consistently":[121],"improve":[122],"robustness":[124],"mismatched":[129],"condition.":[130]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
