{"id":"https://openalex.org/W2153270237","doi":"https://doi.org/10.1109/icassp.2009.4960488","title":"Stereo-based stochastic mapping with discriminative training for noise robust speech recognition","display_name":"Stereo-based stochastic mapping with discriminative training for noise robust speech recognition","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2153270237","doi":"https://doi.org/10.1109/icassp.2009.4960488","mag":"2153270237"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960488","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960488","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 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/A5102014291","display_name":"Xiaodong Cui","orcid":"https://orcid.org/0000-0003-4865-1307"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaodong Cui","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021938376","display_name":"Mohamed Afify","orcid":"https://orcid.org/0000-0002-4445-9767"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohamed Afify","raw_affiliation_strings":["Orange Laboratory, Cairo, Egypt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Orange Laboratory, Cairo, Egypt","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074146436","display_name":"Yuqing Gao","orcid":"https://orcid.org/0000-0001-8709-8378"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuqing Gao","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3933","last_page":"3936"},"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/T11309","display_name":"Music and Audio Processing","score":0.9976999759674072,"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":0.9976000189781189,"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/discriminative-model","display_name":"Discriminative model","score":0.8999751210212708},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7660542726516724},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6269763708114624},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5909244418144226},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5904411673545837},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5243421196937561},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.4296310544013977},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.426339328289032},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.3534260392189026},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.12280544638633728}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8999751210212708},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7660542726516724},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6269763708114624},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5909244418144226},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5904411673545837},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5243421196937561},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.4296310544013977},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.426339328289032},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3534260392189026},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.12280544638633728},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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.2009.4960488","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960488","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W156213964","https://openalex.org/W1279245896","https://openalex.org/W2097427452","https://openalex.org/W2106554350","https://openalex.org/W2106714211","https://openalex.org/W2116496426","https://openalex.org/W2125610823","https://openalex.org/W2128653836","https://openalex.org/W2132056905","https://openalex.org/W2150907703","https://openalex.org/W3149335959","https://openalex.org/W6677520260"],"related_works":["https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W3108403339","https://openalex.org/W2162712524","https://openalex.org/W4287867034","https://openalex.org/W2175872006","https://openalex.org/W3005783148","https://openalex.org/W3021143552","https://openalex.org/W2004821155"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"an":[3],"enhanced":[4],"stochastic":[5],"mapping":[6,29],"technique":[7],"in":[8],"the":[9,28,33,36,42,46,81],"discriminative":[10,69],"feature":[11],"(fMPE)":[12],"space":[13],"that":[14,51],"exploits":[15],"stereo":[16],"data":[17],"for":[18],"noise":[19],"robust":[20],"LVCSR.":[21],"Both":[22],"MMSE":[23,53],"and":[24,32,54,59,84],"MAP":[25,47,55],"estimates":[26,56],"of":[27,35,45],"are":[30],"given":[31],"performance":[34,62,87],"two":[37],"is":[38,57,77],"investigated.":[39],"Due":[40],"to":[41,80],"iterative":[43],"nature":[44],"estimate,":[48],"we":[49],"show":[50],"combining":[52],"possible":[58],"yields":[60],"superior":[61],"than":[63],"each":[64],"individual":[65],"estimate.":[66],"A":[67],"multi-style":[68],"training":[70],"with":[71],"minimum":[72],"phone":[73],"error":[74],"(MPE)":[75],"criterion":[76],"further":[78],"applied":[79],"compensated":[82],"features":[83],"obtains":[85],"significant":[86],"improvement":[88],"on":[89],"real-world":[90],"noisy":[91],"test":[92],"sets.":[93]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}