{"id":"https://openalex.org/W2166114080","doi":"https://doi.org/10.1109/icassp.2012.6288969","title":"Stereo-based stochastic mapping with context using probabilistic PCA for noise robust automatic speech recognition","display_name":"Stereo-based stochastic mapping with context using probabilistic PCA for noise robust automatic speech recognition","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2166114080","doi":"https://doi.org/10.1109/icassp.2012.6288969","mag":"2166114080"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6288969","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288969","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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 Laboratories, Cairo, Egypt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Orange Laboratories, Cairo, Egypt","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107808331","display_name":"Bowen Zhou","orcid":"https://orcid.org/0000-0003-1062-9526"},"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":"Bowen Zhou","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":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"39","issue":null,"first_page":"4705","last_page":"4708"},"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":0.9991000294685364,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9970999956130981,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.736684262752533},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6891628503799438},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6457624435424805},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6021780967712402},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.5930337309837341},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5703086853027344},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5435774326324463},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5130971670150757},{"id":"https://openalex.org/keywords/minimum-mean-square-error","display_name":"Minimum mean square error","score":0.49226537346839905},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.44304734468460083},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.43047863245010376},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.42675361037254333},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21750059723854065}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.736684262752533},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6891628503799438},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6457624435424805},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6021780967712402},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.5930337309837341},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5703086853027344},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5435774326324463},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5130971670150757},{"id":"https://openalex.org/C90652560","wikidata":"https://www.wikidata.org/wiki/Q11091747","display_name":"Minimum mean square error","level":3,"score":0.49226537346839905},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.44304734468460083},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.43047863245010376},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.42675361037254333},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21750059723854065},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/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/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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.2012.6288969","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288969","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6600000262260437,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W88081813","https://openalex.org/W1279245896","https://openalex.org/W2049633694","https://openalex.org/W2096779346","https://openalex.org/W2120605154","https://openalex.org/W2125027820","https://openalex.org/W2125234026","https://openalex.org/W2131118736","https://openalex.org/W2132056905","https://openalex.org/W2132462584","https://openalex.org/W2145760110","https://openalex.org/W6628082926","https://openalex.org/W7048738093"],"related_works":["https://openalex.org/W1980381208","https://openalex.org/W4296209631","https://openalex.org/W2364594919","https://openalex.org/W2219338811","https://openalex.org/W3097449145","https://openalex.org/W2167092671","https://openalex.org/W1861706286","https://openalex.org/W2561617217","https://openalex.org/W3125756894","https://openalex.org/W2158511632"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"investigate":[4],"stereo-based":[5],"stochastic":[6],"mapping":[7],"(SSM)":[8],"with":[9,42,135],"context":[10,43],"for":[11,54,74],"the":[12,29,34,38,50,55,62,75,84,88,114,129,133],"noise":[13,107],"robustness":[14],"of":[15,37,57,77,101],"automatic":[16],"speech":[17,40,103,116,123],"recognition,":[18],"especially":[19],"under":[20,87,132],"unseen":[21,137],"conditions.":[22],"Probabilistic":[23],"PCA":[24],"(PPCA)":[25],"is":[26,72,111],"used":[27],"in":[28,49,65,94],"SSM":[30,85],"framework":[31],"to":[32,113],"reduce":[33,61],"high":[35],"dimensionality":[36],"noisy":[39,51],"features":[41],"and":[44,104,138],"derive":[45],"an":[46,67],"eigen":[47],"representation":[48,100],"feature":[52],"space":[53,96],"prediction":[56],"clean":[58,102],"features.":[59],"To":[60],"computational":[63],"cost":[64],"training,":[66],"approximation":[68],"by":[69],"single-pass":[70],"re-training":[71],"considered":[73],"estimation":[76],"joint":[78],"GMM.":[79],"We":[80],"also":[81],"show":[82],"that":[83],"estimate":[86],"minimum":[89],"mean":[90],"square":[91],"error":[92],"(MMSE)":[93],"a":[95],"where":[97],"low":[98],"dimensional":[99],"uncorrelated":[105],"additive":[106],"can":[108],"be":[109],"assumed":[110],"related":[112],"subspace":[115],"enhancement.":[117],"Experiments":[118],"on":[119],"large":[120],"vocabulary":[121],"continuous":[122],"recognition":[124],"tasks":[125],"observe":[126],"gains":[127],"from":[128],"proposed":[130],"approach":[131],"conditions":[134],"seen,":[136],"real":[139],"noise.":[140]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}