{"id":"https://openalex.org/W63005457","doi":"https://doi.org/10.21437/interspeech.2004-726","title":"Speech recognition system robust to noise and speaking styles","display_name":"Speech recognition system robust to noise and speaking styles","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W63005457","doi":"https://doi.org/10.21437/interspeech.2004-726","mag":"63005457"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-726","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-726","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","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/A5077037266","display_name":"Shigeki Matsuda","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Shigeki Matsuda","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061510158","display_name":"Takatoshi Jitsuhiro","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takatoshi Jitsuhiro","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039443541","display_name":"Konstantin Markov","orcid":"https://orcid.org/0000-0003-1838-4789"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Konstantin Markov","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5020994673","display_name":"Satoshi Nakamura","orcid":"https://orcid.org/0000-0001-6956-3803"},"institutions":[{"id":"https://openalex.org/I4210104143","display_name":"Advanced Telecommunications Research Institute International","ror":"https://ror.org/01pe1d703","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210104143"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Nakamura","raw_affiliation_strings":["Advanced Telecommunications Research Institute International"],"affiliations":[{"raw_affiliation_string":"Advanced Telecommunications Research Institute International","institution_ids":["https://openalex.org/I4210104143"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5077037266"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8994,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.79089461,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2817","last_page":"2820"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9980999827384949,"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":0.8490502834320068},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7305874824523926},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.7102763652801514},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6420058012008667},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5496828556060791},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5479819178581238},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5309008359909058},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5180473327636719},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.47209876775741577},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.380713552236557},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3688209652900696},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3417682647705078},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.2701580226421356},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09609800577163696}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8490502834320068},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7305874824523926},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.7102763652801514},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6420058012008667},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5496828556060791},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5479819178581238},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5309008359909058},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5180473327636719},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.47209876775741577},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.380713552236557},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3688209652900696},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3417682647705078},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2701580226421356},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09609800577163696},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2004-726","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-726","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W65442416","https://openalex.org/W93383444","https://openalex.org/W150420562","https://openalex.org/W220700577","https://openalex.org/W1587776811","https://openalex.org/W2004826498","https://openalex.org/W2045036776","https://openalex.org/W2068970468","https://openalex.org/W2080921589","https://openalex.org/W2099480894","https://openalex.org/W2128653836","https://openalex.org/W2131429563","https://openalex.org/W2137075158","https://openalex.org/W2145826596","https://openalex.org/W2146871184"],"related_works":["https://openalex.org/W3119288895","https://openalex.org/W2185075503","https://openalex.org/W4229940372","https://openalex.org/W2186375278","https://openalex.org/W2749720872","https://openalex.org/W2793748347","https://openalex.org/W4250904811","https://openalex.org/W2155047054","https://openalex.org/W2104528589","https://openalex.org/W2379120504"],"abstract_inverted_index":{"It":[0],"is":[1,23,46,91,102,112],"difficult":[2],"to":[3,24,48,181,185],"recognize":[4],"speech":[5,133,172],"distorted":[6],"by":[7,93,114,128,136],"various":[8,137],"factors,":[9],"especially":[10],"when":[11],"an":[12],"ASR":[13,43],"system":[14,44,59,127,149,187],"contains":[15],"only":[16],"a":[17,40,165,186],"single":[18],"acoustic":[19,27,77,89,189],"model.":[20],"One":[21],"solution":[22],"use":[25],"multiple":[26],"models,":[28],"one":[29,100],"model":[30,90],"for":[31,158,191],"each":[32,88,98],"different":[33,142],"condition.":[34],"In":[35],"this":[36],"paper,":[37],"we":[38],"discuss":[39],"parallel":[41],"decoding-based":[42],"that":[45,147],"robust":[47],"the":[49,118,123,148,159,174],"noise":[50,95,140],"type,":[51],"SNR,":[52,81],"speaker":[53,82],"gender":[54,83],"and":[55,68,84,87,130],"speaking":[56,85,161],"style.":[57],"Our":[58],"consists":[60],"of":[61,125,139,156,167],"two":[62,119],"recognition":[63,110,152,175],"channels":[64],"based":[65,104],"on":[66,80,105],"MFCC":[67,70],"Differential":[69],"(DMFCC)":[71],"features.":[72],"Each":[73],"channel":[74],"has":[75],"several":[76],"models":[78,190],"depending":[79],"style,":[86],"adapted":[92],"fast":[94],"adaptation.":[96],"From":[97],"channel,":[99],"hypothesis":[101],"selected":[103],"its":[106],"likelihood.":[107],"The":[108],"final":[109],"result":[111],"obtained":[113],"combining":[115],"hypotheses":[116],"from":[117,178],"channels.":[120],"We":[121],"evaluate":[122],"performance":[124],"our":[126],"normal":[129,160],"hyperarticulated":[131,192],"test":[132],"data":[134,163],"contaminated":[135],"types":[138],"at":[141,164],"SNR":[143,166],"levels.":[144],"Experiments":[145],"demonstrate":[146],"could":[150],"achieve":[151],"accuracy":[153,176],"in":[154],"excess":[155],"80%":[157],"style":[162],"0":[168],"dB.":[169],"For":[170],"hyper-articulated":[171],"data,":[173],"improved":[177],"about":[179],"10%":[180],"over":[182],"45%":[183],"compared":[184],"without":[188],"speech.":[193]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}