{"id":"https://openalex.org/W2165251700","doi":"https://doi.org/10.1109/tasl.2012.2227729","title":"Building Acoustic Model Ensembles by Data Sampling With Enhanced Trainings and Features","display_name":"Building Acoustic Model Ensembles by Data Sampling With Enhanced Trainings and Features","publication_year":2012,"publication_date":"2012-11-14","ids":{"openalex":"https://openalex.org/W2165251700","doi":"https://doi.org/10.1109/tasl.2012.2227729","mag":"2165251700"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2012.2227729","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2012.2227729","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/A5100363116","display_name":"Xin Chen","orcid":"https://orcid.org/0000-0003-1950-2468"},"institutions":[{"id":"https://openalex.org/I1283104182","display_name":"Pearson (United States)","ror":"https://ror.org/02naadr48","country_code":"US","type":"company","lineage":["https://openalex.org/I1283104182","https://openalex.org/I4210088969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xin Chen","raw_affiliation_strings":["Pearson Knowledge Technologies, Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pearson Knowledge Technologies, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1283104182"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033518479","display_name":"Yunxin Zhao","orcid":"https://orcid.org/0000-0001-5511-3692"},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yunxin Zhao","raw_affiliation_strings":["Department of Computer Science, University of Missouri, Columbia, MO, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Missouri, Columbia, MO, USA","institution_ids":["https://openalex.org/I76835614"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.0446,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.92029581,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"21","issue":"3","first_page":"498","last_page":"507"},"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":0.9994999766349792,"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":0.9987999796867371,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.7811487317085266},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7611235976219177},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.7166452407836914},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7119461297988892},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5828108191490173},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.570095956325531},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5647734999656677},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.534682035446167},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.5263215899467468},{"id":"https://openalex.org/keywords/multilayer-perceptron","display_name":"Multilayer perceptron","score":0.5235995054244995},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5053884983062744},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42711925506591797},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0842447578907013}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7811487317085266},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7611235976219177},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.7166452407836914},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7119461297988892},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5828108191490173},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.570095956325531},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5647734999656677},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.534682035446167},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.5263215899467468},{"id":"https://openalex.org/C179717631","wikidata":"https://www.wikidata.org/wiki/Q2991667","display_name":"Multilayer perceptron","level":3,"score":0.5235995054244995},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5053884983062744},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42711925506591797},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0842447578907013},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tasl.2012.2227729","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2012.2227729","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":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7300000190734863}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W21249823","https://openalex.org/W87092222","https://openalex.org/W113920312","https://openalex.org/W177307080","https://openalex.org/W285205250","https://openalex.org/W1500724501","https://openalex.org/W1534477342","https://openalex.org/W1539943318","https://openalex.org/W1582923974","https://openalex.org/W1877570817","https://openalex.org/W1904457459","https://openalex.org/W2033178790","https://openalex.org/W2063541597","https://openalex.org/W2069631319","https://openalex.org/W2073101704","https://openalex.org/W2077804127","https://openalex.org/W2090751903","https://openalex.org/W2101680829","https://openalex.org/W2103248292","https://openalex.org/W2108446915","https://openalex.org/W2110829996","https://openalex.org/W2150907703","https://openalex.org/W2158069733","https://openalex.org/W2160237783","https://openalex.org/W2161306565","https://openalex.org/W2162818124","https://openalex.org/W2165119652","https://openalex.org/W2165712214","https://openalex.org/W2911964244","https://openalex.org/W6603586546","https://openalex.org/W6607143959","https://openalex.org/W6610301154","https://openalex.org/W6632075054","https://openalex.org/W6632579566","https://openalex.org/W6634886751","https://openalex.org/W6676320771","https://openalex.org/W6682398751"],"related_works":["https://openalex.org/W2167155152","https://openalex.org/W2155033763","https://openalex.org/W3134920593","https://openalex.org/W2143247386","https://openalex.org/W1990589093","https://openalex.org/W161037869","https://openalex.org/W2501000458","https://openalex.org/W1578749070","https://openalex.org/W2146842779","https://openalex.org/W2340308015"],"abstract_inverted_index":{"We":[0,27,61],"propose":[1],"a":[2,76],"novel":[3],"approach":[4],"of":[5,21,32,36,54,103,117],"using":[6],"Cross":[7,37],"Validation":[8,38],"(CV)":[9],"and":[10,45,100,108,126],"Speaker":[11],"Clustering":[12],"(SC)":[13],"based":[14,122],"data":[15],"samplings":[16],"to":[17,86,135],"construct":[18],"an":[19,138],"ensemble":[20,57],"acoustic":[22,58],"models":[23,59],"for":[24],"speech":[25],"recognition.":[26],"also":[28,111],"investigate":[29],"the":[30,33,52,55,64,101,114,118,129,142],"effects":[31],"existing":[34],"techniques":[35],"Expectation":[39],"Maximization":[40],"(CVEM),":[41],"Discriminative":[42],"Training":[43],"(DT),":[44],"Multiple":[46],"Layer":[47],"Perceptron":[48],"(MLP)":[49],"features":[50],"on":[51,67,75,123],"quality":[53],"proposed":[56,65,82],"(EAMs).":[60],"have":[62,84,136],"evaluated":[63],"methods":[66,83],"TIMIT":[68],"phoneme":[69],"recognition":[70,90],"task":[71],"as":[72,74],"well":[73],"telemedicine":[77],"automatic":[78],"captioning":[79],"task.":[80],"The":[81],"led":[85],"significant":[87],"improvements":[88],"in":[89,141],"accuracy":[91,115],"over":[92],"conventional":[93],"Hidden":[94],"Markov":[95],"Model":[96],"(HMM)":[97],"baseline":[98],"systems,":[99],"integration":[102],"EAMs":[104],"with":[105],"CVEM,":[106,124],"DT,":[107,125],"MLP":[109],"has":[110],"significantly":[112],"improved":[113],"performances":[116],"single":[119],"model":[120],"systems":[121],"MLP,":[127],"where":[128],"increased":[130],"inter-model":[131],"diversity":[132],"is":[133],"shown":[134],"played":[137],"important":[139],"role":[140],"performance":[143],"gain.":[144]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}