{"id":"https://openalex.org/W21805524","doi":"https://doi.org/10.21437/eurospeech.1995-140","title":"A discriminative filter bank model for speech recognition","display_name":"A discriminative filter bank model for speech recognition","publication_year":1995,"publication_date":"1995-09-18","ids":{"openalex":"https://openalex.org/W21805524","doi":"https://doi.org/10.21437/eurospeech.1995-140","mag":"21805524"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.1995-140","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.1995-140","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"4th European Conference on Speech Communication and Technology (Eurospeech 1995)","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/A5069833586","display_name":"Alain Biem","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Alain Biem","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030109648","display_name":"Erik McDermott","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Erik McDermott","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5027443847","display_name":"Shigeru Katagiri","orcid":"https://orcid.org/0000-0003-4738-5385"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shigeru Katagiri","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5069833586"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.00108225,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"545","last_page":"548"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9986000061035156,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9986000061035156,"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/T11309","display_name":"Music and Audio Processing","score":0.9983999729156494,"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":0.9911999702453613,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.8179140090942383},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7824385166168213},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6818472146987915},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6563006043434143},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4679243564605713},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38215136528015137},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36126989126205444},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.09122934937477112}],"concepts":[{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.8179140090942383},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7824385166168213},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6818472146987915},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6563006043434143},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4679243564605713},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38215136528015137},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36126989126205444},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.09122934937477112}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/eurospeech.1995-140","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.1995-140","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"4th European Conference on Speech Communication and Technology (Eurospeech 1995)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.49.6527","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.49.6527","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.hip.atr.co.jp/~biem/WORK/report/Eurospeech-94/paper2.ps","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7799999713897705,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":1,"referenced_works":["https://openalex.org/W2148154194"],"related_works":["https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W1482209366","https://openalex.org/W2404514746","https://openalex.org/W1652783584","https://openalex.org/W2082783427"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"the":[3,24,32,36,40,66,69,76,85,95,125,140],"realization":[4],"of":[5,42,60,75,84,113,143],"a":[6,100],"filter":[7,61],"bank":[8],"model":[9],"that":[10,87,124],"achieves":[11],"minimum":[12],"classification":[13,131],"error.":[14],"A":[15],"bank-of-filter":[16],"feature":[17,77],"extractor":[18],"module":[19],"is":[20],"jointly":[21],"optimized":[22],"with":[23],"classifier":[25],"'s":[26],"parameters":[27,59],"so":[28],"as":[29],"to":[30,56,90,99],"minimize":[31],"errors":[33],"occurring":[34],"at":[35],"back-end":[37],"classifier,":[38],"in":[39,107],"framework":[41],"Minimum":[43],"Classification":[44],"Error":[45],"/Generalized":[46],"Probabilistic":[47],"Descent":[48],"Method":[49],"(MCE/GPD).":[50],"The":[51],"method":[52,96],"was":[53,97],"first":[54],"applied":[55,98],"readjusting":[57],"various":[58],"banks":[62],"linearly":[63],"spaced":[64],"on":[65],"Mel-scale":[67],"for":[68],"Japanese":[70],"vowel":[71],"recognition":[72,103,135],"task.":[73],"Analysis":[74],"extraction":[78],"process":[79],"shows":[80],"how":[81],"those":[82],"parts":[83],"spectrum":[86],"are":[88,92],"relevant":[89],"discrimination":[91],"captured.":[93],"Then":[94],"multi-speaker":[101],"word":[102,109],"system,":[104],"which":[105],"resulted":[106],"an":[108],"error":[110],"rate":[111],"reduction":[112],"more":[114],"than":[115],"20":[116],"%.":[117],"1.":[118],"INTRODUCTION":[119],"It":[120],"has":[121],"been":[122],"argued":[123],"interaction":[126],"between":[127],"signal":[128],"representation":[129],"and":[130],"strongly":[132],"influences":[133],"speech":[134],"performance":[136],"[2],":[137],"[6].":[138],"However,":[139],"underlying":[141],"nature":[142],"this...":[144]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}