{"id":"https://openalex.org/W2111492050","doi":"https://doi.org/10.1109/tasl.2009.2031236","title":"A Study on the Generalization Capability of Acoustic Models for Robust Speech Recognition","display_name":"A Study on the Generalization Capability of Acoustic Models for Robust Speech Recognition","publication_year":2009,"publication_date":"2009-09-01","ids":{"openalex":"https://openalex.org/W2111492050","doi":"https://doi.org/10.1109/tasl.2009.2031236","mag":"2111492050"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2009.2031236","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2009.2031236","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/A5101602536","display_name":"Xiong Xiao","orcid":"https://orcid.org/0009-0001-5128-6518"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Xiong Xiao","raw_affiliation_strings":["School of Computer Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computer Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365053","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-1089-9748"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinyu Li","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070872826","display_name":"Eng Siong Chng","orcid":"https://orcid.org/0000-0001-6257-7399"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Eng Siong Chng","raw_affiliation_strings":["School of Computer Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computer Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Institute for Infocomm Research, Singapore","School of Computer Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000"]},{"raw_affiliation_string":"School of Computer Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066868860","display_name":"Chin\u2010Hui Lee","orcid":"https://orcid.org/0000-0002-1892-2551"},"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":"Chin-Hui Lee","raw_affiliation_strings":["School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101602536"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":3.9256,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.93829585,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"18","issue":"6","first_page":"1158","last_page":"1169"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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/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/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"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/computer-science","display_name":"Computer science","score":0.7856669425964355},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.7372987270355225},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7191881537437439},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5988839268684387},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5977700352668762},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5832070708274841},{"id":"https://openalex.org/keywords/digit-recognition","display_name":"Digit recognition","score":0.534020721912384},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5088844299316406},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42551523447036743},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41107094287872314},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2522752285003662},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09922382235527039}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7856669425964355},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7372987270355225},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7191881537437439},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5988839268684387},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5977700352668762},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5832070708274841},{"id":"https://openalex.org/C2984784707","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Digit recognition","level":3,"score":0.534020721912384},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5088844299316406},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42551523447036743},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41107094287872314},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2522752285003662},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09922382235527039},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tasl.2009.2031236","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2009.2031236","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W33099690","https://openalex.org/W84880661","https://openalex.org/W111968546","https://openalex.org/W1665196592","https://openalex.org/W1877570817","https://openalex.org/W1973211667","https://openalex.org/W1992576854","https://openalex.org/W2033565080","https://openalex.org/W2052667477","https://openalex.org/W2063541597","https://openalex.org/W2066561607","https://openalex.org/W2069976350","https://openalex.org/W2080921589","https://openalex.org/W2092305100","https://openalex.org/W2100969003","https://openalex.org/W2104997912","https://openalex.org/W2105613180","https://openalex.org/W2105885996","https://openalex.org/W2106714211","https://openalex.org/W2111479622","https://openalex.org/W2115515280","https://openalex.org/W2121973264","https://openalex.org/W2133628825","https://openalex.org/W2134218976","https://openalex.org/W2136386449","https://openalex.org/W2137075158","https://openalex.org/W2137401359","https://openalex.org/W2143855671","https://openalex.org/W2146871184","https://openalex.org/W2150142469","https://openalex.org/W2150252476","https://openalex.org/W2150735731","https://openalex.org/W2151484683","https://openalex.org/W2152175514","https://openalex.org/W2156909104","https://openalex.org/W2157590573","https://openalex.org/W2158289097","https://openalex.org/W2159112514","https://openalex.org/W2161010732","https://openalex.org/W2171000037","https://openalex.org/W2990138404","https://openalex.org/W3147539069","https://openalex.org/W6601380903","https://openalex.org/W6675604347","https://openalex.org/W6682194319"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4224009465","https://openalex.org/W2016839265","https://openalex.org/W2508457823","https://openalex.org/W1991269640","https://openalex.org/W1650162272","https://openalex.org/W1593615848","https://openalex.org/W2153557281","https://openalex.org/W2246967174"],"abstract_inverted_index":{"In":[0],"this":[1,184],"paper,":[2],"we":[3,49,192],"explore":[4],"the":[5,28,40,46,91,103,116,180,194],"generalization":[6,20,53,118],"capability":[7,54,119],"of":[8,45,207],"acoustic":[9,84],"model":[10,72,143],"for":[11,58],"improving":[12,115],"speech":[13,123,190],"recognition":[14,110,124],"robustness":[15,210],"against":[16],"noise":[17],"distortions.":[18],"While":[19],"in":[21,130,212],"statistical":[22],"learning":[23,197,215],"theory":[24],"originally":[25],"refers":[26],"to":[27,31,63,69,79,83,135,166,177,202],"model's":[29,117],"ability":[30],"generalize":[32],"well":[33],"on":[34,102,188],"unseen":[35],"testing":[36,138],"data":[37],"drawn":[38],"from":[39],"same":[41],"distribution":[42],"as":[43],"that":[44,51,148,172],"training":[47,73],"data,":[48],"show":[50,147],"good":[52],"is":[55,68,186],"also":[56],"desirable":[57],"mismatched":[59,137],"cases.":[60],"One":[61],"way":[62],"obtain":[64],"such":[65,171],"general":[66],"models":[67],"use":[70],"margin-based":[71,196],"method,":[74],"e.g.,":[75],"soft-margin":[76],"estimation":[77],"(SME),":[78],"enable":[80],"some":[81],"tolerance":[82],"mismatches":[85],"without":[86,155],"a":[87,163],"detailed":[88],"knowledge":[89],"about":[90],"distortion":[92],"mechanisms":[93],"through":[94,120],"enhancing":[95],"margins":[96],"between":[97],"competing":[98],"models.":[99],"Experimental":[100],"results":[101,146],"Aurora-2":[104],"and":[105,133,157,160,209],"Aurora-3":[106],"connected":[107],"digit":[108],"string":[109],"tasks":[111],"demonstrate":[112],"that,":[113],"by":[114],"SME":[121,149],"training,":[122],"performance":[125],"can":[126,174,199],"be":[127,175,200],"significantly":[128],"improved":[129],"both":[131],"matched":[132],"low":[134],"medium":[136],"cases":[139],"with":[140,153,204],"no":[141],"language":[142],"constraints.":[144],"Recognition":[145],"indeed":[150],"performs":[151],"better":[152],"than":[154],"mean":[156],"variance":[158],"normalization,":[159],"therefore":[161],"provides":[162],"complimentary":[164],"benefit":[165],"conventional":[167],"feature":[168],"normalization":[169],"techniques":[170],"they":[173],"combined":[176],"further":[178],"improve":[179],"system":[181],"performance.":[182],"Although":[183],"study":[185],"focused":[187],"noisy":[189],"recognition,":[191],"believe":[193],"proposed":[195],"framework":[198],"extended":[201],"dealing":[203],"different":[205],"types":[206],"distortions":[208],"issues":[211],"other":[213],"machine":[214],"applications.":[216]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}