{"id":"https://openalex.org/W2000949213","doi":"https://doi.org/10.1109/icassp.2010.5495669","title":"On noise estimation for robust speech recognition using vector Taylor series","display_name":"On noise estimation for robust speech recognition using vector Taylor series","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2000949213","doi":"https://doi.org/10.1109/icassp.2010.5495669","mag":"2000949213"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2010.5495669","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495669","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/A5100702071","display_name":"Yong Zhao","orcid":"https://orcid.org/0000-0003-2644-952X"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yong Zhao","raw_affiliation_strings":["Center for Signal and Image Processing, Georgia Institute of Technology, USA","[Center for Signal & Image Processing, Georgia Institute of Technology, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Signal and Image Processing, Georgia Institute of Technology, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"[Center for Signal & Image Processing, Georgia Institute of Technology, USA]","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070867959","display_name":"Biing\u2010Hwang Juang","orcid":"https://orcid.org/0000-0002-5773-5679"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Biing-Hwang Juang","raw_affiliation_strings":["Center for Signal and Image Processing, Georgia Institute of Technology, USA","[Center for Signal & Image Processing, Georgia Institute of Technology, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Signal and Image Processing, Georgia Institute of Technology, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"[Center for Signal & Image Processing, Georgia Institute of Technology, USA]","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":1.9207,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.86363636,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4290","last_page":"4293"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9994000196456909,"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":0.9976000189781189,"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":0.7208576798439026},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.64425128698349},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.5689582824707031},{"id":"https://openalex.org/keywords/taylor-series","display_name":"Taylor series","score":0.5360558032989502},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.496830016374588},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4825296103954315},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.45692846179008484},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4369683265686035},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.43678462505340576},{"id":"https://openalex.org/keywords/estimation-theory","display_name":"Estimation theory","score":0.4352872371673584},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.41217243671417236},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3360009789466858},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29983848333358765},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.17688408493995667}],"concepts":[{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.7208576798439026},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.64425128698349},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.5689582824707031},{"id":"https://openalex.org/C158946198","wikidata":"https://www.wikidata.org/wiki/Q131187","display_name":"Taylor series","level":2,"score":0.5360558032989502},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.496830016374588},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4825296103954315},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.45692846179008484},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4369683265686035},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.43678462505340576},{"id":"https://openalex.org/C167928553","wikidata":"https://www.wikidata.org/wiki/Q1376021","display_name":"Estimation theory","level":2,"score":0.4352872371673584},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.41217243671417236},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3360009789466858},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29983848333358765},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.17688408493995667},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2010.5495669","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495669","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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.719.5896","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.719.5896","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://users.ece.gatech.edu/%7Eyzhao33/publications/VTSNoiseEstimation_ICASSP2010.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1573570773","https://openalex.org/W1665196592","https://openalex.org/W2063291689","https://openalex.org/W2080921589","https://openalex.org/W2111093880","https://openalex.org/W2120025343","https://openalex.org/W2137401359","https://openalex.org/W2150660184","https://openalex.org/W2151484683","https://openalex.org/W2155445312","https://openalex.org/W6634340323","https://openalex.org/W6680646222"],"related_works":["https://openalex.org/W2395105737","https://openalex.org/W2369507325","https://openalex.org/W3208270790","https://openalex.org/W3135719690","https://openalex.org/W2368550193","https://openalex.org/W1985023705","https://openalex.org/W2061027733","https://openalex.org/W2387252559","https://openalex.org/W2032389377","https://openalex.org/W2144623417"],"abstract_inverted_index":{"In":[0,115],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5,27,70,74,129],"novel":[6],"noise":[7,44,55,94,102,124],"variance":[8,45,56,80,125],"estimation":[9,95,103,108,126,148],"method":[10,15,67,127,137],"using":[11,30,138],"the":[12,17,37,43,49,54,60,63,77,83,93,116,122,136,145,169],"fixed":[13,50],"point":[14,51],"for":[16,96],"VTS-based":[18],"robust":[19],"speech":[20],"recognition.":[21],"Noise":[22],"parameters":[23],"are":[24,105],"re-estimated":[25],"over":[26,118,135,149,168],"given":[28],"utterance":[29],"an":[31,153],"EM":[32],"algorithm.":[33],"The":[34,66,158],"derivative":[35],"of":[36,62],"auxiliary":[38],"function":[39],"with":[40,73],"respect":[41],"to":[42,69],"is":[46,86,152],"resolved,":[47],"and":[48,82,112],"algorithm":[52],"estimates":[53],"by":[57],"recursively":[58],"approximating":[59],"root":[61],"resulting":[64],"derivative.":[65],"leads":[68],"re-estimation":[71],"formula":[72],"flavor":[75],"like":[76],"standard":[78],"ML":[79,147],"estimation,":[81],"iteration":[84],"procedure":[85],"step-size":[87],"free.":[88],"We":[89],"also":[90],"investigate":[91],"improving":[92],"efficient":[97],"VTS":[98,146,171],"adaptation.":[99,114,172],"Several":[100],"fast":[101,155],"methods":[104],"examined":[106],"including":[107],"from":[109],"non-speech":[110,150],"areas":[111,151],"incremental":[113],"evaluation":[117],"Aurora":[119],"2":[120],"database,":[121],"proposed":[123],"obtains":[128],"significant":[130],"improvement":[131,167],"in":[132],"recognition":[133],"accuracy":[134],"sample":[139],"variance.":[140],"Further":[141],"experiments":[142],"show":[143],"that":[144],"effective":[154],"adaptation":[156],"method.":[157],"final":[159],"refined":[160],"approach":[161],"achieves":[162],"8.75%":[163],"WER,":[164],"13%":[165],"relative":[166],"conventional":[170]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}