{"id":"https://openalex.org/W2133668545","doi":"https://doi.org/10.1109/icassp.2010.5495568","title":"Optimizing spectral subtraction and wiener filtering for robust speech recognition in reverberant and noisy conditions","display_name":"Optimizing spectral subtraction and wiener filtering for robust speech recognition in reverberant and noisy conditions","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2133668545","doi":"https://doi.org/10.1109/icassp.2010.5495568","mag":"2133668545"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2010.5495568","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495568","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5052470310","display_name":"Randy G\u00f3mez","orcid":"https://orcid.org/0000-0002-3191-6818"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Randy Gomez","raw_affiliation_strings":["Kyoto University, Sakyo, Kyoto, Japan","Kyoto University, ACCMS, Sakyo-ku, 606-8501, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University, Sakyo, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Kyoto University, ACCMS, Sakyo-ku, 606-8501, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038044080","display_name":"Tatsuya Kawahara","orcid":"https://orcid.org/0000-0002-2686-2296"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuya Kawahara","raw_affiliation_strings":["Kyoto University, Sakyo, Kyoto, Japan","Kyoto University, ACCMS, Sakyo-ku, 606-8501, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University, Sakyo, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Kyoto University, ACCMS, Sakyo-ku, 606-8501, Japan","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I22299242"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4566","last_page":"4569"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9983000159263611,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7949082851409912},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7741954922676086},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7395192384719849},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.6923736929893494},{"id":"https://openalex.org/keywords/wiener-filter","display_name":"Wiener filter","score":0.626301646232605},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5304661989212036},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5251911878585815},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5143166780471802},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5098316073417664},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.44660454988479614},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.43737733364105225},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.41859617829322815},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3267720341682434},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32587409019470215},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.22270908951759338},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10302728414535522}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7949082851409912},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7741954922676086},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7395192384719849},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.6923736929893494},{"id":"https://openalex.org/C18537770","wikidata":"https://www.wikidata.org/wiki/Q25523","display_name":"Wiener filter","level":2,"score":0.626301646232605},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5304661989212036},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5251911878585815},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5143166780471802},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5098316073417664},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.44660454988479614},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.43737733364105225},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.41859617829322815},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3267720341682434},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32587409019470215},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.22270908951759338},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10302728414535522},{"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2010.5495568","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495568","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7900000214576721,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W25676668","https://openalex.org/W126265399","https://openalex.org/W1546395807","https://openalex.org/W1992012199","https://openalex.org/W2051057783","https://openalex.org/W2053241019","https://openalex.org/W2127539611","https://openalex.org/W2128653836","https://openalex.org/W2141418660","https://openalex.org/W6601019258","https://openalex.org/W6678908498","https://openalex.org/W6680865276"],"related_works":["https://openalex.org/W2106793170","https://openalex.org/W2079581646","https://openalex.org/W1577562165","https://openalex.org/W4251740529","https://openalex.org/W2028846388","https://openalex.org/W2072015625","https://openalex.org/W4295210860","https://openalex.org/W2438843077","https://openalex.org/W2117955483","https://openalex.org/W2121894251"],"abstract_inverted_index":{"Speech":[0],"enhancement":[1,68,84],"is":[2,20],"a":[3],"common":[4],"approach":[5,19],"to":[6,13,22,63,92],"address":[7,93],"the":[8,28,65,75,98,115],"effects":[9],"of":[10,74],"degradation":[11],"due":[12],"noise":[14],"and":[15,26,39,45,103],"channel":[16],"contamination.":[17],"This":[18],"intended":[21],"suppress":[23],"unwanted":[24],"signal":[25],"recover":[27],"clean":[29],"speech.":[30],"In":[31,97],"this":[32],"paper,":[33],"we":[34,106],"focus":[35],"on":[36],"two":[37],"simple":[38,82],"low-computational":[40],"methods:":[41],"Wiener":[42],"filtering":[43],"(WF)":[44],"spectral":[46],"subtraction":[47],"(SS).":[48],"Conventionally,":[49],"these":[50,81],"are":[51,87],"formulated":[52],"with":[53,56,72,100],"no":[54],"relation":[55,71],"automatic":[57],"speech":[58,67,83],"recognition":[59,112],"(ASR).":[60],"We":[61,78],"propose":[62],"optimize":[64],"conventional":[66],"technique":[69],"in":[70,111],"likelihood":[73],"acoustic":[76],"model.":[77],"also":[79],"exploit":[80],"techniques":[85],"that":[86],"originally":[88],"designed":[89],"for":[90],"denoising,":[91],"reverberation":[94],"as":[95],"well.":[96],"experiment":[99],"real":[101],"noisy":[102],"reverberant":[104],"environments,":[105],"have":[107],"achieved":[108],"significant":[109],"improvement":[110],"performance":[113],"using":[114],"proposed":[116],"approach.":[117]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2025-10-10T00:00:00"}