{"id":"https://openalex.org/W2009922355","doi":"https://doi.org/10.1109/icassp.2013.6639031","title":"Noise model transfer using affine transformation with application to large vocabulary reverberant speech recognition","display_name":"Noise model transfer using affine transformation with application to large vocabulary reverberant speech recognition","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2009922355","doi":"https://doi.org/10.1109/icassp.2013.6639031","mag":"2009922355"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6639031","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639031","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5101618071","display_name":"Takuya Yoshioka","orcid":"https://orcid.org/0009-0003-7791-3545"},"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":true,"raw_author_name":"Takuya Yoshioka","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","NTT Commun. Sci. Labs., NTT Corp., Keihanna Science City, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Commun. Sci. Labs., NTT Corp., Keihanna Science City, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","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":"Tomohiro Nakatani","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","NTT Commun. Sci. Labs., NTT Corp., Keihanna Science City, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Commun. Sci. Labs., NTT Corp., Keihanna Science City, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101618071"],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":0.9576,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.74095115,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"87","issue":null,"first_page":"7058","last_page":"7062"},"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":0.9991000294685364,"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":0.995199978351593,"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/noise","display_name":"Noise (video)","score":0.6916251182556152},{"id":"https://openalex.org/keywords/value-noise","display_name":"Value noise","score":0.6357338428497314},{"id":"https://openalex.org/keywords/affine-transformation","display_name":"Affine transformation","score":0.6116266250610352},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5966348648071289},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5929890871047974},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.5419832468032837},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.5183221101760864},{"id":"https://openalex.org/keywords/gradient-noise","display_name":"Gradient noise","score":0.4833931028842926},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.4700561761856079},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4698055386543274},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46299582719802856},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.4497140645980835},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41138774156570435},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2960759401321411},{"id":"https://openalex.org/keywords/noise-floor","display_name":"Noise floor","score":0.24145618081092834},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.23140877485275269},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.22453033924102783},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.13741374015808105}],"concepts":[{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6916251182556152},{"id":"https://openalex.org/C182163834","wikidata":"https://www.wikidata.org/wiki/Q2926529","display_name":"Value noise","level":5,"score":0.6357338428497314},{"id":"https://openalex.org/C92757383","wikidata":"https://www.wikidata.org/wiki/Q382497","display_name":"Affine transformation","level":2,"score":0.6116266250610352},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5966348648071289},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5929890871047974},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.5419832468032837},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.5183221101760864},{"id":"https://openalex.org/C200378446","wikidata":"https://www.wikidata.org/wiki/Q4147391","display_name":"Gradient noise","level":5,"score":0.4833931028842926},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.4700561761856079},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4698055386543274},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46299582719802856},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4497140645980835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41138774156570435},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2960759401321411},{"id":"https://openalex.org/C187612029","wikidata":"https://www.wikidata.org/wiki/Q17083130","display_name":"Noise floor","level":4,"score":0.24145618081092834},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.23140877485275269},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.22453033924102783},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.13741374015808105},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2013.6639031","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639031","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W35070573","https://openalex.org/W1512562331","https://openalex.org/W1973669708","https://openalex.org/W2006783645","https://openalex.org/W2009106392","https://openalex.org/W2024490156","https://openalex.org/W2088817208","https://openalex.org/W2104780554","https://openalex.org/W2106718021","https://openalex.org/W2113981416","https://openalex.org/W2124611315","https://openalex.org/W2126597753","https://openalex.org/W2132350316","https://openalex.org/W2147706354","https://openalex.org/W2148898720","https://openalex.org/W2155137502","https://openalex.org/W2165534711","https://openalex.org/W2188162373","https://openalex.org/W4256112632","https://openalex.org/W6672555887","https://openalex.org/W6686978693"],"related_works":["https://openalex.org/W3125397569","https://openalex.org/W4226451553","https://openalex.org/W2588855097","https://openalex.org/W2161471497","https://openalex.org/W2032021057","https://openalex.org/W2170781407","https://openalex.org/W2005333371","https://openalex.org/W2057119739","https://openalex.org/W3033631740","https://openalex.org/W2144739192"],"abstract_inverted_index":{"This":[0,119],"paper":[1,154],"considers":[2],"using":[3,97,149],"the":[4,35,55,64,76,82,87,108,124,129,133,139,144,171,174],"feature":[5,83,100],"enhancement":[6],"approach":[7],"for":[8,19,53,92],"automatic":[9],"recognition":[10,168],"of":[11,37,164,173],"speech":[12,167],"corrupted":[13],"by":[14,21,28,96,122],"severely":[15],"nonstationary":[16],"noise,":[17],"caused":[18],"example":[20],"interfering":[22],"talkers":[23],"and":[24,42,102],"inter-frame":[25],"distortion":[26],"induced":[27],"reverberation.":[29],"In":[30],"particular,":[31],"we":[32],"focus":[33],"on":[34,63,107],"issue":[36],"feature-domain":[38],"noise":[39,49,58,67,88,103,113,134],"model":[40,50,59,89,135],"estimation":[41],"investigate":[43],"a":[44,111,150,156],"recently":[45],"proposed":[46],"approach,":[47],"called":[48],"transfer":[51],"(NMT),":[52],"estimating":[54],"rapidly":[56],"changing":[57],"parameter":[60,90,136],"values.":[61],"Based":[62],"fact":[65],"that":[66,110,127],"spectral":[68,105],"changes":[69],"can":[70],"be":[71],"detected":[72],"more":[73,157],"easily":[74],"in":[75,81,138],"power":[77,104,114,130],"spectrum":[78,115],"domain":[79],"than":[80],"domain,":[84],"NMT":[85],"estimates":[86],"values":[91],"each":[93],"time":[94],"frame":[95],"both":[98],"observed":[99],"vectors":[101],"estimates,":[106],"assumption":[109],"separate":[112],"estimator":[116],"is":[117,120],"available.":[118],"achieved":[121],"finding":[123],"best":[125],"transformation":[126,145,160,176],"maps":[128],"spectra":[131],"onto":[132],"space":[137],"maximum":[140],"likelihood":[141],"sense.":[142],"Whereas":[143],"was":[146],"previously":[147],"modeled":[148],"bias":[151],"vector,":[152],"this":[153],"employs":[155],"flexible":[158],"affine":[159,175],"model.":[161,177],"The":[162],"results":[163],"20,000-word":[165],"reverberant":[166],"experiments":[169],"show":[170],"advantage":[172]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}