{"id":"https://openalex.org/W1965469083","doi":"https://doi.org/10.1109/icassp.2002.5743840","title":"Including detailed information feature in MFCC for large vocabulary contious speech recornition","display_name":"Including detailed information feature in MFCC for large vocabulary contious speech recornition","publication_year":2002,"publication_date":"2002-05-01","ids":{"openalex":"https://openalex.org/W1965469083","doi":"https://doi.org/10.1109/icassp.2002.5743840","mag":"1965469083"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2002.5743840","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743840","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"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/A5022255906","display_name":"Lei Jia","orcid":"https://orcid.org/0000-0002-4405-7274"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lei Jia","raw_affiliation_strings":["National Laboratory Of Pattern Recognition, Chinese Academy of Science, Beijing, China 100080"],"affiliations":[{"raw_affiliation_string":"National Laboratory Of Pattern Recognition, Chinese Academy of Science, Beijing, China 100080","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020681500","display_name":"Bo Xu","orcid":"https://orcid.org/0000-0002-2083-4307"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Xu","raw_affiliation_strings":["National Laboratory Of Pattern Recognition, Chinese Academy of Science, Beijing, China 100080"],"affiliations":[{"raw_affiliation_string":"National Laboratory Of Pattern Recognition, Chinese Academy of Science, Beijing, China 100080","institution_ids":["https://openalex.org/I4210112150"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5022255906"],"corresponding_institution_ids":["https://openalex.org/I4210112150"],"apc_list":null,"apc_paid":null,"fwci":0.3551,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.52602828,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"3","issue":null,"first_page":"I","last_page":"805"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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/T10860","display_name":"Speech and Audio Processing","score":0.9977999925613403,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9922000169754028,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.8573462963104248},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7248193025588989},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7189382910728455},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.6797587871551514},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.6164879202842712},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6049688458442688},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5514760613441467},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5513017177581787},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.48345622420310974},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.4339025318622589},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16617238521575928},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.0780438780784607}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.8573462963104248},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7248193025588989},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7189382910728455},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.6797587871551514},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.6164879202842712},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6049688458442688},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5514760613441467},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5513017177581787},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.48345622420310974},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.4339025318622589},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16617238521575928},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0780438780784607},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","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/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2002.5743840","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743840","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Acoustics Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2069723558","https://openalex.org/W2097395002","https://openalex.org/W2104448323","https://openalex.org/W2141493634","https://openalex.org/W2148154194","https://openalex.org/W2152051032","https://openalex.org/W2169513726","https://openalex.org/W6667783703"],"related_works":["https://openalex.org/W4382052966","https://openalex.org/W2283145973","https://openalex.org/W4317383455","https://openalex.org/W2548511587","https://openalex.org/W4246774824","https://openalex.org/W3202097418","https://openalex.org/W4293232884","https://openalex.org/W2422472940","https://openalex.org/W2019475500","https://openalex.org/W2548162870"],"abstract_inverted_index":{"This":[0],"paper":[1],"focuses":[2],"on":[3,98],"the":[4,14,25,40,58,64,68,89,104,114,127],"inclusion":[5],"of":[6,28,42,63],"more":[7],"detailed":[8,70],"linguistically":[9,31],"relevant":[10,32],"speech":[11,33],"information":[12,34,71],"in":[13,21,45,111,126],"Mel-Frequency":[15],"Cepstral":[16],"Coefficients(MFCC)":[17],"feature":[18,35,62,77,95,106],"extraction":[19,107],"process":[20],"order":[22],"to":[23,38,56,73,113],"improve":[24],"recognition":[26],"accuracy":[27],"LVCSR.":[29],"Detailed":[30],"is":[36,54,109,124],"extracted":[37],"reflect":[39],"change":[41],"energy":[43,61,76],"spectrum":[44],"each":[46,79],"mel-frequency":[47],"bank(MFB).":[48],"A":[49],"normalized":[50],"positive":[51],"weighting":[52,83],"vector":[53,84],"used":[55],"combine":[57],"log":[59],"channel":[60],"standard":[65,115,131],"MFCC":[66,116],"with":[67,130],"new":[69,105],"features":[72],"form":[74],"one":[75],"for":[78,122],"MFB.":[80],"The":[81],"optimal":[82],"can":[85],"be":[86],"obtained":[87],"by":[88],"Heteroscedastic":[90],"Discriminant":[91],"Analysis":[92],"(HDA)":[93],"before":[94],"extraction.":[96],"Experiments":[97],"two":[99],"test":[100,128],"sets":[101],"show":[102],"that":[103],"method":[108],"superior":[110],"performance":[112],"and":[117],"10%":[118],"relative":[119],"error":[120],"reduction":[121],"LVCSR":[123],"witnessed":[125],"set":[129],"accent":[132],"speakers.":[133]},"counts_by_year":[{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}