{"id":"https://openalex.org/W71807618","doi":"https://doi.org/10.21437/eurospeech.2003-515","title":"Noise-robust automatic speech recognition using orthogonalized distinctive phonetic feature vectors","display_name":"Noise-robust automatic speech recognition using orthogonalized distinctive phonetic feature vectors","publication_year":2003,"publication_date":"2003-09-01","ids":{"openalex":"https://openalex.org/W71807618","doi":"https://doi.org/10.21437/eurospeech.2003-515","mag":"71807618"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.2003-515","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-515","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","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/A5037089480","display_name":"Takashi Fukuda","orcid":"https://orcid.org/0000-0001-9599-6274"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Takashi Fukuda","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5109901270","display_name":"Tsuneo Nitta","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tsuneo Nitta","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5037089480"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.00776774,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2189","last_page":"2192"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9968000054359436,"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":0.9968000054359436,"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":0.9941999912261963,"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":0.965399980545044,"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":0.7446879148483276},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.7420613169670105},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7418230772018433},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6805908679962158},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5964599847793579},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5430225729942322},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4843200743198395},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.46700677275657654},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.4332254230976105},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4228993356227875},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4206072688102722}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7446879148483276},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.7420613169670105},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7418230772018433},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6805908679962158},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5964599847793579},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5430225729942322},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4843200743198395},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.46700677275657654},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.4332254230976105},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4228993356227875},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4206072688102722},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/eurospeech.2003-515","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-515","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2349769824","https://openalex.org/W2914532148","https://openalex.org/W4317383455","https://openalex.org/W2548511587","https://openalex.org/W1996690921","https://openalex.org/W4293232884","https://openalex.org/W2422472940","https://openalex.org/W2019475500","https://openalex.org/W2548162870","https://openalex.org/W2144773493"],"abstract_inverted_index":{"Abstract":[0],"With":[1],"the":[2,48,89,97,108,149,185],"aim":[3],"of":[4,50,69,140],"using":[5,79,107],"an":[6,57,61,67,124,153],"automatic":[7],"speech":[8,161,164],"recognition":[9,127,156],"(ASR)":[10],"system":[11,177],"in":[12,152],"practical":[13],"environments,":[14],"various":[15],"approaches":[16],"focused":[17],"on":[18,123],"noise-robustness":[19],"such":[20],"as":[21,66],"noise":[22],"adaptation":[23],"and":[24,162,180,192],"reduction":[25],"techniques":[26],"have":[27,31],"been":[28],"investigated.":[29],"We":[30],"previously":[32],"proposed":[33,73,144],"a":[34,42,101,175],"distinctive":[35],"phonetic":[36],"feature":[37],"(DPF)":[38],"parameter":[39,64],"set":[40,65],"for":[41],"noise-robust":[43],"ASR":[44],"system,":[45],"which":[46],"reduced":[47],"effect":[49],"high-level":[51],"additive":[52,141,167],"noise[1].":[53],"This":[54],"paper":[55],"describes":[56],"attempt":[58],"to":[59,95],"apply":[60],"orthogonalized":[62,113,145,186],"DPF":[63,81,114,121],"input":[68],"HMMs.":[70],"In":[71,111],"our":[72],"method,":[74],"orthogonal":[75,109],"bases":[76],"are":[77],"calculated":[78],"conventional":[80,189],"vectors":[82],"that":[83],"represent":[84],"38":[85],"Japanese":[86],"phonemes,":[87],"then":[88,135],"Karhunen-Loeve":[90],"transform":[91],"(KLT)":[92],"is":[93],"used":[94],"orthogonalize":[96],"DPFs,":[98],"output":[99],"from":[100],"multi-layer":[102],"neural":[103],"network":[104],"(MLN),":[105],"by":[106,166],"bases.":[110],"experiments,":[112],"parameters":[115,122],"were":[116],"firstly":[117],"compared":[118],"with":[119,129,137,159,163,178,188],"original":[120],"isolated":[125,154],"spoken-word":[126,155],"task":[128,157],"clean":[130,160],"speech.":[131],"Noise":[132],"robustness":[133],"was":[134],"tested":[136],"four":[138],"types":[139],"noise.":[142,168],"The":[143],"DPFs":[146,187],"can":[147],"reduce":[148],"error":[150],"rate":[151],"both":[158],"contaminated":[165],"Furthermore,":[169],"we":[170],"achieved":[171],"significant":[172],"improvements":[173],"over":[174],"baseline":[176],"MFCC":[179],"dynamic":[181],"feature-set":[182],"when":[183],"combining":[184],"static":[190],"MFCCs":[191],"\u2206P.":[193]},"counts_by_year":[{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}