{"id":"https://openalex.org/W2101680829","doi":"https://doi.org/10.1109/icassp.2009.4960456","title":"Data sampling based ensemble acoustic modelling","display_name":"Data sampling based ensemble acoustic modelling","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2101680829","doi":"https://doi.org/10.1109/icassp.2009.4960456","mag":"2101680829"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960456","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960456","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":"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/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":true,"raw_author_name":"Xin Chen","raw_affiliation_strings":["Department of Computer Science, University of Missouri, Columbia, MO, USA","Department of Computer Science, University of Missouri-Columbia 65211, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Missouri, Columbia, MO, USA","institution_ids":["https://openalex.org/I76835614"]},{"raw_affiliation_string":"Department of Computer Science, University of Missouri-Columbia 65211, USA","institution_ids":[]}]},{"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","Department of Computer Science, University of Missouri-Columbia 65211, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Missouri, Columbia, MO, USA","institution_ids":["https://openalex.org/I76835614"]},{"raw_affiliation_string":"Department of Computer Science, University of Missouri-Columbia 65211, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100363084"],"corresponding_institution_ids":["https://openalex.org/I76835614"],"apc_list":null,"apc_paid":null,"fwci":1.4099,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.80719794,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"16","issue":null,"first_page":"3805","last_page":"3808"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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":0.9984999895095825,"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/computer-science","display_name":"Computer science","score":0.6927497386932373},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.48013660311698914},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.0716530978679657}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6927497386932373},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.48013660311698914},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0716530978679657},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2009.4960456","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960456","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":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1491514470","https://openalex.org/W1534477342","https://openalex.org/W1539943318","https://openalex.org/W1904457459","https://openalex.org/W2102183254","https://openalex.org/W2103248292","https://openalex.org/W2108446915","https://openalex.org/W2110829996","https://openalex.org/W2158069733","https://openalex.org/W2160237783","https://openalex.org/W2911964244","https://openalex.org/W6632579566","https://openalex.org/W6676666668"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W2530322880"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4,28],"a":[5,114,131],"novel":[6],"technique":[7],"of":[8,19,64,73,81,90,109,118],"using":[9,29,70],"cross":[10],"validation":[11],"(CV)":[12],"data":[13,38],"sampling":[14],"to":[15,39,51,145],"construct":[16],"an":[17],"ensemble":[18,42,56,66,89,140],"acoustic":[20,57,67,91,125,141],"models":[21,68,92],"for":[22,55,123],"conversational":[23],"speech":[24],"recognition.":[25],"We":[26,59,84,105],"further":[27],"hierarchical":[30],"Gaussian":[31],"mixture":[32],"model":[33],"(HGMM)":[34],"and":[35,44,79,96,101],"repartition":[36],"training":[37],"increase":[40],"the":[41,62,65,71,88,94,97,103,107,138],"size":[43],"diversity.":[45],"The":[46],"proposed":[47,111,139],"methods":[48],"are":[49],"found":[50,86],"work":[52],"well":[53],"together":[54],"modeling.":[58],"also":[60],"evaluated":[61],"quality":[63],"by":[69],"measures":[72],"classification":[74],"margin,":[75],"average":[76,98],"correct":[77,82,99],"score":[78],"variance":[80],"score.":[83],"have":[85],"that":[87,137],"increases":[93],"margin":[95],"score,":[100],"reduces":[102],"variance.":[104],"compared":[106],"performance":[108],"our":[110],"method":[112,117],"with":[113],"recently":[115],"reported":[116],"CV":[119],"expectation":[120],"maximization":[121],"(CVEM)":[122],"single":[124],"models.":[126],"Our":[127],"experimental":[128],"results":[129],"on":[130],"telemedicine":[132],"automatic":[133],"captioning":[134],"task":[135],"showed":[136],"modeling":[142],"has":[143],"led":[144],"significant":[146],"improvements":[147],"in":[148],"word":[149],"recognition":[150],"accuracy.":[151]},"counts_by_year":[{"year":2014,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}