{"id":"https://openalex.org/W52822164","doi":"https://doi.org/10.21437/icslp.1998-521","title":"Noise robust two-stream auditory feature extraction method for speech recognition","display_name":"Noise robust two-stream auditory feature extraction method for speech recognition","publication_year":1998,"publication_date":"1998-11-30","ids":{"openalex":"https://openalex.org/W52822164","doi":"https://doi.org/10.21437/icslp.1998-521","mag":"52822164"},"language":"en","primary_location":{"id":"doi:10.21437/icslp.1998-521","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.1998-521","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"5th International Conference on Spoken Language Processing (ICSLP 1998)","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/A5103093321","display_name":"Jilei Tian","orcid":"https://orcid.org/0000-0002-4588-9398"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jilei Tian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009715421","display_name":"Ramalingam Hariharan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ramalingam Hariharan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5073732111","display_name":"Kari Laurila","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kari Laurila","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.00747264,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"paper 0325","last_page":"0"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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/T11309","display_name":"Music and Audio Processing","score":0.9980999827384949,"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":0.7847409248352051},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7625325322151184},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7163378000259399},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6485170125961304},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.6065840125083923},{"id":"https://openalex.org/keywords/front-and-back-ends","display_name":"Front and back ends","score":0.5463805198669434},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5236384868621826},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.49528542160987854},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.48440390825271606},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.4738110601902008},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.4335612654685974},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38193410634994507},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1057104766368866}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7847409248352051},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7625325322151184},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7163378000259399},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6485170125961304},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.6065840125083923},{"id":"https://openalex.org/C53016008","wikidata":"https://www.wikidata.org/wiki/Q620167","display_name":"Front and back ends","level":2,"score":0.5463805198669434},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5236384868621826},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.49528542160987854},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.48440390825271606},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.4738110601902008},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4335612654685974},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38193410634994507},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1057104766368866},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","level":1,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/icslp.1998-521","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.1998-521","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"5th International Conference on Spoken Language Processing (ICSLP 1998)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1995522399","https://openalex.org/W2022349254","https://openalex.org/W2034610397","https://openalex.org/W2049894045","https://openalex.org/W2100643000","https://openalex.org/W2121551440","https://openalex.org/W2164720542"],"related_works":["https://openalex.org/W2349769824","https://openalex.org/W2914532148","https://openalex.org/W2372625757","https://openalex.org/W4313178214","https://openalex.org/W2970653563","https://openalex.org/W3082848404","https://openalex.org/W3093766508","https://openalex.org/W2012393389","https://openalex.org/W1979583797","https://openalex.org/W1494724239"],"abstract_inverted_index":{"Part":[0],"of":[1,18,52,56],"the":[2,25,32,53,57,65,108,127],"problems":[3],"in":[4,39],"noise":[5,63],"robust":[6],"speech":[7,34],"recognition":[8,105],"can":[9],"be":[10],"attributed":[11],"to":[12,31,74,89,126],"poor":[13],"acoustic":[14],"modeling":[15],"and":[16,71,78,87,115,139,142],"use":[17],"inappropriate":[19],"features.":[20],"It":[21],"is":[22,29,67],"known":[23],"that":[24,49],"human":[26],"auditory":[27,59],"system":[28],"superior":[30],"best":[33],"recognizer":[35],"currently":[36],"available.":[37],"Hence,":[38],"this":[40],"paper,":[41],"we":[42],"propose":[43],"a":[44,91],"new":[45],"two-stream":[46],"feature":[47,96,144],"extractor":[48],"incorporates":[50],"some":[51],"key":[54],"functions":[55],"peripheral":[58],"subsystem.":[60],"To":[61],"enhance":[62],"robustness,":[64],"input":[66],"divided":[68],"into":[69],"low-pass":[70],"high-pass":[72],"channels":[73],"form":[75],"so-called":[76],"static":[77],"dynamic":[79],"streams.":[80],"These":[81],"two":[82],"streams":[83],"are":[84],"independently":[85],"processed":[86],"recombined":[88],"produce":[90],"single":[92],"stream,":[93],"containing":[94],"13":[95,136],"vector":[97,145],"components,":[98,146],"with":[99,135],"improved":[100],"linguistic":[101],"information.":[102],"Speaker-dependent":[103],"isolated-word":[104],"tests,":[106],"using":[107],"proposed":[109],"front-end,":[110],"produced":[111],"an":[112],"average":[113],"39%":[114],"17%":[116],"error":[117],"rate":[118],"reductions,":[119],"over":[120],"all":[121],"noisy":[122],"environments,":[123],"as":[124],"compared":[125],"standard":[128],"Mel":[129],"Frequency":[130],"Cepstral":[131],"Coefficient":[132],"(MFCC)":[133],"front-ends":[134],"(statics":[137,141],"only)":[138],"26":[140],"deltas)":[143],"respectively.":[147]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}