{"id":"https://openalex.org/W2092545824","doi":"https://doi.org/10.1109/icassp.2002.5743735","title":"Perceptual speech modeling for noisy speech recognition","display_name":"Perceptual speech modeling for noisy speech recognition","publication_year":2002,"publication_date":"2002-05-01","ids":{"openalex":"https://openalex.org/W2092545824","doi":"https://doi.org/10.1109/icassp.2002.5743735","mag":"2092545824"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2002.5743735","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743735","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/A5103251327","display_name":"Chung\u2010Hsien Wu","orcid":"https://orcid.org/0000-0002-3947-2123"},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Chung-Hsien Wu","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan","Dept. of Comput. Sci. & Inf. Eng., Nat. Cheng Kung Univ., Tainan, Taiwan, ROC"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan","institution_ids":["https://openalex.org/I91807558"]},{"raw_affiliation_string":"Dept. of Comput. Sci. & Inf. Eng., Nat. Cheng Kung Univ., Tainan, Taiwan, ROC","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052495842","display_name":"Yu\u2010Hsien Chiu","orcid":"https://orcid.org/0000-0002-8233-4631"},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Hsien Chiu","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan","Dept. of Comput. Sci. & Inf. Eng., Nat. Cheng Kung Univ., Tainan, Taiwan, ROC"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan","institution_ids":["https://openalex.org/I91807558"]},{"raw_affiliation_string":"Dept. of Comput. Sci. & Inf. Eng., Nat. Cheng Kung Univ., Tainan, Taiwan, ROC","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062100309","display_name":"Huigan Lim","orcid":null},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Huigan Lim","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan","Dept. of Comput. Sci. & Inf. Eng., Nat. Cheng Kung Univ., Tainan, Taiwan, ROC"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan","institution_ids":["https://openalex.org/I91807558"]},{"raw_affiliation_string":"Dept. of Comput. Sci. & Inf. Eng., Nat. Cheng Kung Univ., Tainan, Taiwan, ROC","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103251327"],"corresponding_institution_ids":["https://openalex.org/I91807558"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11426188,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"assp 31","issue":null,"first_page":"I","last_page":"385"},"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":0.9994999766349792,"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":0.9987999796867371,"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/speech-recognition","display_name":"Speech recognition","score":0.8402277231216431},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7933318614959717},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.5958981513977051},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5762348175048828},{"id":"https://openalex.org/keywords/maximum-a-posteriori-estimation","display_name":"Maximum a posteriori estimation","score":0.5532719492912292},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.45718759298324585},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4524464011192322},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.44923171401023865},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.44665947556495667},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.44293439388275146},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4392669200897217},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4285503029823303},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.42626190185546875},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.4240630269050598},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.41244256496429443},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.41009190678596497},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3693293035030365},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.19667789340019226},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.14631903171539307}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8402277231216431},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7933318614959717},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.5958981513977051},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5762348175048828},{"id":"https://openalex.org/C9810830","wikidata":"https://www.wikidata.org/wiki/Q635384","display_name":"Maximum a posteriori estimation","level":3,"score":0.5532719492912292},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.45718759298324585},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4524464011192322},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.44923171401023865},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.44665947556495667},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.44293439388275146},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4392669200897217},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4285503029823303},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.42626190185546875},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.4240630269050598},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.41244256496429443},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.41009190678596497},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3693293035030365},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.19667789340019226},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.14631903171539307},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2002.5743735","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743735","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":[{"display_name":"Peace, Justice and strong institutions","score":0.6600000262260437,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1658344067","https://openalex.org/W1992576854","https://openalex.org/W2017103364","https://openalex.org/W2018228148","https://openalex.org/W2128653836","https://openalex.org/W2140419980","https://openalex.org/W2158185319","https://openalex.org/W2159948467","https://openalex.org/W6655020483"],"related_works":["https://openalex.org/W2294333436","https://openalex.org/W2360887461","https://openalex.org/W2373767407","https://openalex.org/W2653598178","https://openalex.org/W2747006289","https://openalex.org/W3160071434","https://openalex.org/W109284678","https://openalex.org/W2851491717","https://openalex.org/W4252682934","https://openalex.org/W2072884270"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,8,53,74,89],"perceptual":[4],"modeling":[5,33],"approach":[6],"with":[7,13],"two-stage":[9,49],"recognition":[10,17,91],"to":[11,36,61,69,94],"deal":[12],"the":[14,38,48,51,64,95],"issues":[15],"of":[16],"degradation":[18],"in":[19,34,108],"noisy":[20,45],"environment.":[21],"The":[22,81],"auditory":[23],"masking":[24],"effect":[25],"is":[26,59],"used":[27,60],"for":[28,106],"speech":[29,43],"enhancement":[30],"and":[31,44,100,111],"acoustic":[32],"order":[35,68],"overcome":[37],"model":[39,102],"inconsistencies":[40],"between":[41],"training":[42],"input.":[46],"In":[47,67],"recognition,":[50],"maximum":[52],"posteriori":[54],"(MAP)":[55],"based":[56],"adaptation":[57],"algorithm":[58],"incrementally":[62],"adapt":[63],"noise":[65,97],"model.":[66],"evaluate":[70],"our":[71,85],"proposed":[72,86],"approach,":[73],"Mandarin":[75],"keyword":[76],"spotting":[77],"system":[78],"was":[79],"constructed.":[80],"experimental":[82],"results":[83],"show":[84],"method":[87],"achieves":[88],"better":[90],"rate":[92],"compared":[93],"audible":[96],"suppression":[98],"(ANS)":[99],"parallel":[101],"combination":[103],"(PMC)":[104],"methods":[105],"both":[107],"70km/hr":[109],"(10.3dB)":[110],"90km/hr":[112],"(6.4dB)":[113],"car":[114],"environments.":[115]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}