{"id":"https://openalex.org/W2146442261","doi":"https://doi.org/10.1109/icassp.2003.1202290","title":"Discriminative training of auditory filters of different shapes for robust speech recognition","display_name":"Discriminative training of auditory filters of different shapes for robust speech recognition","publication_year":2003,"publication_date":"2003-12-22","ids":{"openalex":"https://openalex.org/W2146442261","doi":"https://doi.org/10.1109/icassp.2003.1202290","mag":"2146442261"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2003.1202290","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1202290","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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/A5059141717","display_name":"Brian Mak","orcid":"https://orcid.org/0000-0001-6787-5555"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"B. Mak","raw_affiliation_strings":["Department of Computer Science, Hong Kong University of Science and Technology, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033756912","display_name":"Wilson Tam","orcid":"https://orcid.org/0000-0003-0641-3060"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["HK","US"],"is_corresponding":false,"raw_author_name":"Yik-Cheung Tam","raw_affiliation_strings":["Department of Computer Science, Hong Kong University of Science and Technology, Hong Kong, China","School of Computer Science, Camegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"School of Computer Science, Camegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033764781","display_name":"Roger Hsiao","orcid":"https://orcid.org/0000-0001-8638-4508"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"R. Hsiao","raw_affiliation_strings":["Department of Computer Science, Hong Kong University of Science and Technology, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5059141717"],"corresponding_institution_ids":["https://openalex.org/I200769079"],"apc_list":null,"apc_paid":null,"fwci":0.3887,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.5752608,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"2","issue":null,"first_page":"II","last_page":"45"},"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/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"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/discriminative-model","display_name":"Discriminative model","score":0.7487592101097107},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.7323120832443237},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7189980745315552},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.640519917011261},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5475382804870605},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.519015908241272},{"id":"https://openalex.org/keywords/band-pass-filter","display_name":"Band-pass filter","score":0.5100613236427307},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47472819685935974},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4426334500312805},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42078763246536255},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.21307995915412903},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1914389431476593},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.13864031434059143},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10655534267425537}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7487592101097107},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.7323120832443237},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7189980745315552},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.640519917011261},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5475382804870605},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.519015908241272},{"id":"https://openalex.org/C147788027","wikidata":"https://www.wikidata.org/wiki/Q2718101","display_name":"Band-pass filter","level":2,"score":0.5100613236427307},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47472819685935974},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4426334500312805},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42078763246536255},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.21307995915412903},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1914389431476593},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.13864031434059143},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10655534267425537},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2003.1202290","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1202290","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-44964","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-44964","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.75,"display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320327240","display_name":"Liga Portuguesa Contra o Cancro","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W135906098","https://openalex.org/W2013020033","https://openalex.org/W2069723558","https://openalex.org/W2104153163","https://openalex.org/W2116447236","https://openalex.org/W2130379466","https://openalex.org/W2142756061","https://openalex.org/W2151484683","https://openalex.org/W4234676713","https://openalex.org/W6667783703","https://openalex.org/W6679123997","https://openalex.org/W6680789782"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2110523656","https://openalex.org/W1482209366","https://openalex.org/W2146591867","https://openalex.org/W1578916557"],"abstract_inverted_index":{"The":[0,18,119],"bank-of-filters":[1],"spectrum":[2],"analysis":[3,24],"model":[4,25,114],"is":[5,26,56,122],"commonly":[6],"used":[7],"in":[8,22],"the":[9,23,50,90,97,103,107,112,134,141],"extraction":[10],"of":[11,29,41,44,53,61,64],"acoustic":[12,109,113],"features":[13,94],"for":[14],"automatic":[15],"speech":[16],"recognition.":[17],"most":[19],"critical":[20],"component":[21],"a":[27,34,39,54],"bank":[28,40],"bandpass":[30],"filters.":[31,84,143],"We":[32],"studied":[33],"data-driven":[35],"approach":[36],"to":[37,88],"designing":[38],"\"optimal\"":[42],"filters":[43,104,127,136],"various":[45],"shapes":[46,60],"discriminatively":[47,117],"so":[48],"that":[49,123],"recognition":[51],"error":[52],"task":[55],"minimized.":[57],"Three":[58],"different":[59],"varying":[62],"degree":[63],"constraints":[65],"were":[66,86,116],"investigated:":[67],"(1)":[68],"parametric":[69],"Gaussian":[70,142],"filters;":[71,77],"(2)":[72],"non-parametric":[73,80],"but":[74],"constrained":[75],"triangular-like":[76,126],"and":[78,81,111,137],"(3)":[79],"unconstrained":[82],"free-formed":[83,135],"Filters":[85],"trained":[87],"derive":[89],"new":[91],"robust":[92],"auditory":[93],"proposed":[95,125],"by":[96],"Bell":[98],"Labs.":[99],"In":[100],"addition,":[101],"both":[102],"(and":[105],"thus":[106],"ensuing":[108],"features)":[110],"parameters":[115],"trained.":[118],"major":[120],"result":[121],"our":[124],"perform":[128,138],"at":[129],"least":[130],"as":[131,133],"well":[132],"better":[139],"than":[140]},"counts_by_year":[{"year":2019,"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"}