{"id":"https://openalex.org/W2158273884","doi":"https://doi.org/10.1109/tasl.2008.2010214","title":"Static and Dynamic Variance Compensation for Recognition of Reverberant Speech With Dereverberation Preprocessing","display_name":"Static and Dynamic Variance Compensation for Recognition of Reverberant Speech With Dereverberation Preprocessing","publication_year":2009,"publication_date":"2009-01-16","ids":{"openalex":"https://openalex.org/W2158273884","doi":"https://doi.org/10.1109/tasl.2008.2010214","mag":"2158273884"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2008.2010214","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2008.2010214","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5023868166","display_name":"Marc Delcroix","orcid":"https://orcid.org/0000-0002-5175-7834"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"M. Delcroix","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021240106","display_name":"Tomohiro Nakatani","orcid":"https://orcid.org/0000-0002-7487-7150"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"T. Nakatani","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"S. Watanabe","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":6.3456,"has_fulltext":false,"cited_by_count":54,"citation_normalized_percentile":{"value":0.97080194,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"17","issue":"2","first_page":"324","last_page":"334"},"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/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/T11447","display_name":"Blind Source Separation Techniques","score":0.9979000091552734,"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/reverberation","display_name":"Reverberation","score":0.8383539915084839},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8122725486755371},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7829488515853882},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5643866658210754},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4967499375343323},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.4774925410747528},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.44822224974632263},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4213588237762451},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2715260982513428},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.13003411889076233},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09281423687934875}],"concepts":[{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.8383539915084839},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8122725486755371},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7829488515853882},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5643866658210754},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4967499375343323},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.4774925410747528},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.44822224974632263},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4213588237762451},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2715260982513428},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.13003411889076233},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09281423687934875},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tasl.2008.2010214","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2008.2010214","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"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":43,"referenced_works":["https://openalex.org/W2738404","https://openalex.org/W38568696","https://openalex.org/W74241614","https://openalex.org/W84880661","https://openalex.org/W166348608","https://openalex.org/W1557133539","https://openalex.org/W1831910457","https://openalex.org/W1967639437","https://openalex.org/W2009415244","https://openalex.org/W2037740282","https://openalex.org/W2045036776","https://openalex.org/W2063291689","https://openalex.org/W2074354966","https://openalex.org/W2082474452","https://openalex.org/W2105592556","https://openalex.org/W2110322414","https://openalex.org/W2111093880","https://openalex.org/W2111581792","https://openalex.org/W2116590962","https://openalex.org/W2121640030","https://openalex.org/W2125471631","https://openalex.org/W2128653836","https://openalex.org/W2128911505","https://openalex.org/W2132214945","https://openalex.org/W2138084857","https://openalex.org/W2143343256","https://openalex.org/W2145475542","https://openalex.org/W2146083413","https://openalex.org/W2151484683","https://openalex.org/W2163970171","https://openalex.org/W2166458192","https://openalex.org/W2547288128","https://openalex.org/W2911394281","https://openalex.org/W3149837617","https://openalex.org/W4229501483","https://openalex.org/W6600113195","https://openalex.org/W6601546906","https://openalex.org/W6602998950","https://openalex.org/W6603374476","https://openalex.org/W6606623981","https://openalex.org/W6676989848","https://openalex.org/W6684255531","https://openalex.org/W6758139422"],"related_works":["https://openalex.org/W2097834170","https://openalex.org/W2187325407","https://openalex.org/W2061778110","https://openalex.org/W2782900155","https://openalex.org/W2170239774","https://openalex.org/W2292655135","https://openalex.org/W2384383430","https://openalex.org/W58750608","https://openalex.org/W2949386652","https://openalex.org/W4288357365"],"abstract_inverted_index":{"The":[0,159],"performance":[1],"of":[2,12,28,31,125,186,208,214],"automatic":[3],"speech":[4,33,75,157,181,210],"recognition":[5,30,207],"is":[6,123],"severely":[7],"degraded":[8],"in":[9,146,199],"the":[10,26,29,78,169,176,200,206,217,228],"presence":[11],"noise":[13,22],"or":[14],"reverberation.":[15],"Much":[16],"research":[17],"has":[18,34],"been":[19],"undertaken":[20],"on":[21],"robustness.":[23],"In":[24,43],"contrast,":[25],"problem":[27],"reverberant":[32,180],"received":[35],"far":[36],"less":[37],"attention":[38],"and":[39,77,102,129,143,155,216,232],"remains":[40],"very":[41],"challenging.":[42],"this":[44,91],"paper,":[45],"we":[46],"use":[47],"a":[48,58,71,99,109,118,134,156,183],"dereverberation":[49,154],"method":[50,178],"to":[51,55,89,148,194],"reduce":[52,90],"reverberation":[53,63,184],"prior":[54],"recognition.":[56,83],"Such":[57],"preprocessor":[59],"may":[60,103],"remove":[61],"most":[62],"effects.":[64],"However,":[65,93],"it":[66,191],"often":[67],"introduces":[68],"distortion,":[69],"causing":[70],"dynamic":[72,110,130,144],"mismatch":[73,101,111],"between":[74,153],"features":[76],"acoustic":[79],"model":[80,95,136,160],"used":[81,88],"for":[82,137,182],"Model":[84],"adaptation":[85,96,120,139],"could":[86],"be":[87],"mismatch.":[92],"conventional":[94],"techniques":[97],"assume":[98],"static":[100,128,142],"therefore":[104],"not":[105],"cope":[106],"well":[107],"with":[108,168,179,205],"arising":[112],"from":[113],"dereverberation.":[114],"This":[115],"paper":[116],"proposes":[117],"novel":[119],"scheme":[121],"that":[122,140,190],"capable":[124],"managing":[126],"both":[127],"mismatches.":[131],"We":[132],"introduce":[133],"parametric":[135],"variance":[138,230],"includes":[141],"components":[145],"order":[147],"realize":[149],"an":[150,196],"appropriate":[151],"interconnection":[152],"recognizer.":[158],"parameters":[161],"are":[162],"optimized":[163],"using":[164,175],"adaptive":[165],"training":[166],"implemented":[167],"expectation":[170],"maximization":[171],"algorithm.":[172],"An":[173],"experiment":[174],"proposed":[177,229],"time":[185],"0.5":[187],"s":[188],"revealed":[189],"was":[192,221,224],"possible":[193],"achieve":[195],"80%":[197],"reduction":[198],"relative":[201],"error":[202,212,219],"rate":[203,213,220],"compared":[204],"dereverberated":[209],"(word":[211],"31%),":[215],"final":[218],"5.4%,":[222],"which":[223],"obtained":[225],"by":[226],"combining":[227],"compensation":[231],"MLLR":[233],"adaptation.":[234]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":8}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}