{"id":"https://openalex.org/W348996839","doi":"https://doi.org/10.21437/eurospeech.1995-129","title":"A unified approach for robust speech recognition","display_name":"A unified approach for robust speech recognition","publication_year":1995,"publication_date":"1995-09-18","ids":{"openalex":"https://openalex.org/W348996839","doi":"https://doi.org/10.21437/eurospeech.1995-129","mag":"348996839"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.1995-129","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.1995-129","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"4th European Conference on Speech Communication and Technology (Eurospeech 1995)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5103874391","display_name":"Pedro J. Moreno","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pedro J. Moreno","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113017615","display_name":"Bhiksha Raj","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bhiksha Raj","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5069424860","display_name":"Richard M. Stern","orcid":"https://orcid.org/0000-0003-0557-7282"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Richard M. Stern","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"481","last_page":"484"},"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":0.9993000030517578,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/cepstrum","display_name":"Cepstrum","score":0.7861530780792236},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7805213928222656},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7223870158195496},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5940566658973694},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.563204824924469},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4911482036113739},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.4588083028793335},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.44607147574424744},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4456183612346649},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4425746202468872},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41774624586105347},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.24807459115982056}],"concepts":[{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.7861530780792236},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7805213928222656},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7223870158195496},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5940566658973694},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.563204824924469},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4911482036113739},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.4588083028793335},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.44607147574424744},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4456183612346649},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4425746202468872},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41774624586105347},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.24807459115982056},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/eurospeech.1995-129","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.1995-129","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"4th European Conference on Speech Communication and Technology (Eurospeech 1995)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Life in Land","id":"https://metadata.un.org/sdg/15","score":0.6899999976158142}],"awards":[{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320332923","display_name":"U.S. Navy","ror":"https://ror.org/03ar0mv07"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1531799152","https://openalex.org/W1608451537","https://openalex.org/W1656317801","https://openalex.org/W1831910457","https://openalex.org/W1992576854","https://openalex.org/W2086699924","https://openalex.org/W2129967803","https://openalex.org/W2157590573","https://openalex.org/W3141839452"],"related_works":["https://openalex.org/W4252379076","https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W4385672897","https://openalex.org/W2373675101","https://openalex.org/W106160982","https://openalex.org/W3119288895","https://openalex.org/W2359140082","https://openalex.org/W1556565948"],"abstract_inverted_index":{"There":[0],"are":[1],"two":[2],"major":[3],"structural":[4],"approaches":[5,93],"to":[6,13,30,77,90,94,178,198],"robust":[7,95],"speech":[8,41,72,96,119,163],"recognition.In":[9],"the":[10,14,21,61,65,68,75,83,104,117,125,151,155,161,167,190,209],"first":[11],"approach":[12,59],"problem,":[15],"compensation":[16],"is":[17],"performed":[18],"by":[19,50,63,98],"modifying":[20,64],"incoming":[22,118,142,213],"cepstral":[23],"stream":[24],"using":[25,160],"ML":[26],"or":[27,49,121],"MMSE":[28],"methods":[29],"estimate":[31],"parameters":[32],"characterizing":[33],"environmental":[34],"degradation,":[35],"from":[36],"direct":[37],"frame-by-frame":[38],"comparisons":[39],"between":[40],"recorded":[42],"in":[43,74,113],"high-quality":[44],"and":[45,108,135,176,182],"degraded":[46,86],"acoustical":[47],"environments,":[48],"signal":[51],"processing":[52],"techniques":[53,101],"such":[54],"as":[55,203],"spectral":[56],"subtraction.The":[57],"second":[58],"tackles":[60],"problem":[62],"statistics":[66,84,153],"of":[67,71,85,154,172,174,208],"internal":[69,109,152],"representation":[70],"cepstra":[73,120],"classifier":[76,126],"make":[78],"them":[79],"more":[80],"closely":[81],"resemble":[82],"speech.This":[87],"paper":[88],"attempts":[89],"unify":[91],"these":[92],"recognition":[97,164],"presenting":[99],"three":[100],"that":[102,211],"share":[103],"same":[105],"basic":[106],"assumptions":[107],"structure":[110],"but":[111],"differ":[112],"whether":[114,122],"they":[115,123],"modify":[116,124,141,212],"statistics.We":[127],"present":[128],"SNR-dependent":[129],"multi-vaRiate":[130],"gAussian-based":[131],"cepsTral":[132],"normaliZation":[133],"(SNR-RATZ)":[134],"SNR-based":[136],"Blind":[137],"RATZ":[138],"(SNR-BRATZ),":[139],"which":[140,149,179],"cepstra,":[143],"along":[144],"with":[145],"STAR":[146,195],"(STAtistical":[147],"Re-estimation),":[148],"modifies":[150],"classifier.The":[156],"algorithms":[157,191,210],"were":[158],"tested":[159],"SPHINX-II":[162],"system":[165],"on":[166],"CENSUS":[168],"database,":[169],"a":[170],"database":[171],"strings":[173],"letters":[175],"numbers":[177],"unknown":[180,183],"added":[181],"linear":[184],"filtering":[185],"was":[186,196],"introduced":[187],"artificially.While":[188],"all":[189],"showed":[192],"good":[193],"performance,":[194],"observed":[197],"provide":[199],"lower":[200],"error":[201],"rates":[202],"SNR":[204],"decreases":[205],"than":[206],"any":[207],"cepstra.":[214]},"counts_by_year":[{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}