{"id":"https://openalex.org/W2162818124","doi":"https://doi.org/10.1109/icassp.2010.5495029","title":"Data sampling ensemble acoustic modelling in speaker independent speech recognition","display_name":"Data sampling ensemble acoustic modelling in speaker independent speech recognition","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2162818124","doi":"https://doi.org/10.1109/icassp.2010.5495029","mag":"2162818124"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2010.5495029","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495029","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/A5100363084","display_name":"Xin Chen","orcid":"https://orcid.org/0000-0002-5406-4136"},"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":"Xin Chen","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"]}]},{"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":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I76835614"],"apc_list":null,"apc_paid":null,"fwci":0.8174,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.73592735,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"16","issue":null,"first_page":"5130","last_page":"5133"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9991000294685364,"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/T10860","display_name":"Speech and Audio Processing","score":0.9977999925613403,"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/timit","display_name":"TIMIT","score":0.8396294116973877},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8193224668502808},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7092577219009399},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6425365209579468},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6114768981933594},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4988584518432617},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.48658692836761475},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4764595031738281},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4725472629070282},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.46557778120040894},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4516361355781555},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.44338834285736084},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.43929535150527954},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.4293380081653595},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2800986170768738},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.08130627870559692}],"concepts":[{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.8396294116973877},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8193224668502808},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7092577219009399},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6425365209579468},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6114768981933594},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4988584518432617},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.48658692836761475},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4764595031738281},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4725472629070282},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.46557778120040894},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4516361355781555},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.44338834285736084},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.43929535150527954},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.4293380081653595},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2800986170768738},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.08130627870559692},{"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},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2010.5495029","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495029","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W285205250","https://openalex.org/W1539943318","https://openalex.org/W1575599472","https://openalex.org/W1904457459","https://openalex.org/W2101680829","https://openalex.org/W2102183254","https://openalex.org/W2103248292","https://openalex.org/W2108446915","https://openalex.org/W2127158193","https://openalex.org/W2160237783","https://openalex.org/W6610301154","https://openalex.org/W6632579566","https://openalex.org/W6676666668"],"related_works":["https://openalex.org/W3134920593","https://openalex.org/W2143247386","https://openalex.org/W1990589093","https://openalex.org/W2206035908","https://openalex.org/W2501000458","https://openalex.org/W2149220986","https://openalex.org/W4247736853","https://openalex.org/W1578749070","https://openalex.org/W1992908141","https://openalex.org/W2146842779"],"abstract_inverted_index":{"In":[0,54],"this":[1],"paper,":[2],"we":[3,56,101],"extend":[4],"our":[5,84],"recent":[6],"data-sampling":[7],"based":[8,71],"ensemble":[9,30,45,85],"acoustic":[10,31,47,86],"modeling":[11],"technique":[12],"for":[13,49,67],"the":[14,26,29,58,94],"speaker-independent":[15],"task":[16],"of":[17,28,46,60,81],"TIMIT":[18,97],"and":[19],"propose":[20,34],"new":[21],"methods":[22,92],"to":[23,42],"further":[24],"improve":[25],"effectiveness":[27],"models.":[32],"We":[33,74],"applying":[35],"overlapped":[36],"speaker":[37,50,95],"clustering":[38],"in":[39,63,79,83],"data":[40,61],"sampling":[41,62],"construct":[43],"an":[44],"models":[48],"independent":[51,96],"speech":[52],"recognition.":[53],"addition,":[55],"evaluate":[57],"method":[59],"recurrent":[64],"neural":[65],"network":[66],"constructing":[68],"a":[69,104,112],"RNN":[70],"frame":[72],"classifier.":[73],"also":[75],"investigate":[76],"using":[77,90],"CVEM":[78],"place":[80],"EM":[82],"model":[87],"training.":[88],"By":[89],"these":[91],"on":[93,108],"phone":[98,109],"recognition":[99],"task,":[100],"have":[102],"obtained":[103],"2.5%":[105],"absolute":[106],"gain":[107],"accuracy":[110],"over":[111],"standard":[113],"HMM":[114],"baseline":[115],"system.":[116]},"counts_by_year":[{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}