{"id":"https://openalex.org/W214562933","doi":"https://doi.org/10.21437/eurospeech.2001-450","title":"A new method for speech denoising and robust speech recognition using probabilistic models for clean speech and for noise","display_name":"A new method for speech denoising and robust speech recognition using probabilistic models for clean speech and for noise","publication_year":2001,"publication_date":"2001-09-03","ids":{"openalex":"https://openalex.org/W214562933","doi":"https://doi.org/10.21437/eurospeech.2001-450","mag":"214562933"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.2001-450","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2001-450","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th European Conference on Speech Communication and Technology (Eurospeech 2001)","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/A5110453625","display_name":"Hagai Attias","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Hagai Attias","raw_affiliation_strings":["Microsoft"],"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100671326","display_name":"Li Deng","orcid":"https://orcid.org/0000-0002-7140-0701"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Li Deng","raw_affiliation_strings":["Microsoft"],"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111957484","display_name":"Alex Acero","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alex Acero","raw_affiliation_strings":["Microsoft"],"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073032636","display_name":"John Platt","orcid":"https://orcid.org/0000-0002-5652-5303"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"John C. Platt","raw_affiliation_strings":["Microsoft"],"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5110453625"],"corresponding_institution_ids":["https://openalex.org/I4210164937"],"apc_list":null,"apc_paid":null,"fwci":4.3638,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.94155844,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1903","last_page":"1906"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9988999962806702,"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":0.9941999912261963,"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":0.7861124277114868},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7120578289031982},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5870653390884399},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5847580432891846},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5641643404960632},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5360738635063171},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4983217716217041},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.48256149888038635},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43999382853507996},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4336474537849426},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36400049924850464}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7861124277114868},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7120578289031982},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5870653390884399},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5847580432891846},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5641643404960632},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5360738635063171},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4983217716217041},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.48256149888038635},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43999382853507996},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4336474537849426},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36400049924850464},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/eurospeech.2001-450","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2001-450","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th European Conference on Speech Communication and Technology (Eurospeech 2001)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.1.8524","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1.8524","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.goldenmetallic.com/eurospeech01.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.9.4635","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.9.4635","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/srg/papers/2001-attias-Eurospeech.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W84880661","https://openalex.org/W2016254085","https://openalex.org/W2100578078","https://openalex.org/W2161597062"],"related_works":["https://openalex.org/W2418631473","https://openalex.org/W2485008119","https://openalex.org/W2810291168","https://openalex.org/W2118415306","https://openalex.org/W4224919439","https://openalex.org/W2008181868","https://openalex.org/W2893030838","https://openalex.org/W2137177114","https://openalex.org/W3164076963","https://openalex.org/W2355125052"],"abstract_inverted_index":{"We":[0,64],"present":[1],"a":[2,33,43,66],"new":[3],"method":[4],"for":[5],"speech":[6,10,23,60,87,95,102],"denoising":[7,40,120],"and":[8,25,68,97,129],"robust":[9,86],"recognition.":[11],"Using":[12],"the":[13,39,91,119,125,131],"framework":[14,37],"of":[15,27,45,55,58,71,80],"probabilistic":[16],"models":[17,24,26],"allows":[18],"us":[19],"to":[20,124],"integrate":[21],"detailed":[22],"realistic":[28],"non-stationary":[29],"noise":[30],"signals":[31],"in":[32,85],"principled":[34],"manner.":[35],"The":[36,78],"transforms":[38],"problem":[41,44],"into":[42],"Bayes-optimal":[46],"signal":[47],"estimation,":[48],"producing":[49],"minimum":[50],"mean":[51],"square":[52],"error":[53,109,137],"estimators":[54],"desired":[56],"features":[57],"clean":[59],"from":[61],"noisy":[62,126],"data.":[63],"describe":[65],"fast":[67],"efficient":[69],"implementation":[70],"an":[72],"algorithm":[73,82,121],"that":[74],"computes":[75],"these":[76],"estimators.":[77],"effectiveness":[79],"this":[81],"is":[83,122,133],"demonstrated":[84],"recognition":[88],"experiments,":[89],"using":[90],"Wall":[92],"Street":[93],"Journal":[94],"corpus":[96],"Microsoft":[98],"Whisper":[99],"large-vocabulary":[100],"continuous":[101],"recognizer.":[103],"Results":[104],"show":[105],"significantly":[106],"lower":[107],"word":[108],"rates":[110,138],"than":[111],"those":[112],"under":[113],"noisy-matched":[114],"condition.":[115],"In":[116],"particular,":[117],"when":[118],"applied":[123],"training":[127],"data":[128],"subsequently":[130],"recognizer":[132],"retrained,":[134],"very":[135],"low":[136],"are":[139],"obtained.":[140]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}