{"id":"https://openalex.org/W2130379466","doi":"https://doi.org/10.1109/icassp.2002.5743734","title":"Discriminative auditory features for robust speech recognition","display_name":"Discriminative auditory features for robust speech recognition","publication_year":2002,"publication_date":"2002-05-01","ids":{"openalex":"https://openalex.org/W2130379466","doi":"https://doi.org/10.1109/icassp.2002.5743734","mag":"2130379466"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2002.5743734","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743734","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/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":"Brian Mak","raw_affiliation_strings":["Department of Computer Science, Hong Kong University of Science and Technology, Hong Kong, China","Hong Kong University of Science and Technology, Department of Computer Science, Clear Water Bay, Hong Kong"],"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":"Hong Kong University of Science and Technology, Department of Computer Science, Clear Water Bay, Hong Kong","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"]}],"countries":["HK"],"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","Hong Kong University of Science and Technology, Department of Computer Science, Clear Water Bay, Hong Kong"],"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":"Hong Kong University of Science and Technology, Department of Computer Science, Clear Water Bay, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100350165","display_name":"Qi Li","orcid":"https://orcid.org/0000-0001-8776-8730"},"institutions":[{"id":"https://openalex.org/I1322087612","display_name":"Alcatel Lucent (Germany)","ror":"https://ror.org/00c5mwp75","country_code":"DE","type":"company","lineage":["https://openalex.org/I1322087612"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Qi Li","raw_affiliation_strings":["Bell Laboratories, Lucent Technologies, Inc., Murray Hill, NJ, USA","Bell Laboratories, Lucent Technologies 600 Mountain Avenue, Murray Hill, NJ 07974 (USA)"],"affiliations":[{"raw_affiliation_string":"Bell Laboratories, Lucent Technologies, Inc., Murray Hill, NJ, USA","institution_ids":[]},{"raw_affiliation_string":"Bell Laboratories, Lucent Technologies 600 Mountain Avenue, Murray Hill, NJ 07974 (USA)","institution_ids":["https://openalex.org/I1322087612"]}]}],"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":1.3198,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.77074423,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"381"},"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/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"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/T11698","display_name":"Underwater Acoustics Research","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1910","display_name":"Oceanography"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.8884756565093994},{"id":"https://openalex.org/keywords/psychoacoustics","display_name":"Psychoacoustics","score":0.8629759550094604},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7244447469711304},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7111674547195435},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6317456364631653},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5996106266975403},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5541097521781921},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.511186420917511},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4432017207145691},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.4335973262786865},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.20676404237747192},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1536037027835846},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.150783509016037},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.05884048342704773}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8884756565093994},{"id":"https://openalex.org/C9940772","wikidata":"https://www.wikidata.org/wiki/Q557399","display_name":"Psychoacoustics","level":3,"score":0.8629759550094604},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7244447469711304},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7111674547195435},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6317456364631653},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5996106266975403},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5541097521781921},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.511186420917511},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4432017207145691},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.4335973262786865},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.20676404237747192},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1536037027835846},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.150783509016037},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.05884048342704773},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2002.5743734","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743734","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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.134.1827","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.134.1827","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/~yct/papers/daf.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.943.5860","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.943.5860","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.ust.hk/%7Emak/PDF/icassp2002-daf.pdf","raw_type":"text"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-27748","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-27748","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":[{"score":0.7200000286102295,"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":11,"referenced_works":["https://openalex.org/W135906098","https://openalex.org/W151018310","https://openalex.org/W1576165295","https://openalex.org/W2019125718","https://openalex.org/W2063541597","https://openalex.org/W2097395002","https://openalex.org/W2115678687","https://openalex.org/W2151484683","https://openalex.org/W2152131029","https://openalex.org/W2166661046","https://openalex.org/W6605478764"],"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/W2761785940","https://openalex.org/W2110523656","https://openalex.org/W1482209366","https://openalex.org/W2521627374"],"abstract_inverted_index":{"Recently,":[0],"Li":[1],"et":[2],"al.":[3],"proposed":[4],"a":[5,120,184],"new":[6,17],"auditory":[7,28,96,108,156],"feature":[8,18,64,74,109,142],"for":[9,89],"robust":[10],"speech":[11],"recognition":[12,86,128],"in":[13,81,98,119,136],"noise":[14],"environments.":[15],"The":[16],"was":[19],"derived":[20],"by":[21,66,171],"mimicking":[22],"closely":[23],"the":[24,36,44,63,72,82,95,107,127,137,151,155,162,179],"function":[25],"of":[26,84,154,188],"human":[27],"process.":[29],"Several":[30],"filters":[31,163],"were":[32,50],"used":[33],"to":[34,68,105,125,164],"model":[35],"outer":[37],"ear,":[38,40],"middle":[39],"and":[41,43,48,167,182],"cochlea,":[42],"initial":[45],"filter":[46],"parameters":[47,65,75,110],"shapes":[49],"obtained":[51],"from":[52,114],"crude":[53],"psychoacoustics":[54,172],"results,":[55],"experience,":[56],"or":[57],"experiments.":[58],"Although":[59],"one":[60],"may":[61,77],"adjust":[62],"hand":[67],"get":[69],"better":[70],"performance,":[71],"resulting":[73],"still":[76],"not":[78],"be":[79,165],"optimal":[80],"sense":[83],"minimal":[85],"errors,":[87],"especially":[88],"different":[90],"tasks.":[91],"To":[92],"further":[93],"improve":[94],"feature,":[97],"this":[99],"paper":[100],"we":[101,146,159],"apply":[102],"discriminative":[103,141],"training":[104],"optimize":[106],"with":[111],"some":[112],"guidance":[113],"psychoacoustic":[115],"evidence":[116],"but":[117],"otherwise":[118],"data-driven":[121],"approach":[122,175],"so":[123],"as":[124,140,169],"minimize":[126],"errors.":[129],"One":[130],"significant":[131],"contribution":[132],"over":[133],"similar":[134],"efforts":[135],"past,":[138],"such":[139],"extraction,":[143],"is":[144,176],"that":[145],"make":[147],"no":[148],"assumption":[149],"on":[150,178],"parametric":[152],"form":[153],"filters.":[157],"Instead,":[158],"only":[160],"require":[161],"smooth":[166],"triangular-like":[168],"suggested":[170],"research.":[173],"Our":[174],"evaluated":[177],"Aurora":[180],"database":[181],"achieves":[183],"word":[185],"error":[186],"reduction":[187],"19.2%.":[189]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}