{"id":"https://openalex.org/W2112445791","doi":"https://doi.org/10.1109/icassp.2003.1198921","title":"Improving the performance of an LVCSR system through ensembles of acoustic models","display_name":"Improving the performance of an LVCSR system through ensembles of acoustic models","publication_year":2003,"publication_date":"2003-11-20","ids":{"openalex":"https://openalex.org/W2112445791","doi":"https://doi.org/10.1109/icassp.2003.1198921","mag":"2112445791"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2003.1198921","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1198921","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/journal_contribution/Improving_the_Performance_of_an_LVCSR_System_Through_Ensembles_of_Acoustic_Models/6606407","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100451786","display_name":"Rong Zhang","orcid":"https://orcid.org/0000-0002-2288-2847"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rong Zhang","raw_affiliation_strings":["School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, USA","[Sch. of Comput. Sci., Carnegie, Mellon Univ., Pittsburgh, PA, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"[Sch. of Comput. Sci., Carnegie, Mellon Univ., Pittsburgh, PA, USA]","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040668817","display_name":"Alexander I. Rudnicky","orcid":"https://orcid.org/0000-0003-2044-8446"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"A.I. Rudnicky","raw_affiliation_strings":["School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, USA","[Sch. of Comput. Sci., Carnegie, Mellon Univ., Pittsburgh, PA, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"[Sch. of Comput. Sci., Carnegie, Mellon Univ., Pittsburgh, PA, USA]","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"876"},"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/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/T10181","display_name":"Natural Language Processing Techniques","score":0.9987000226974487,"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":0.8459516167640686},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.7897888422012329},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.717806875705719},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6628307700157166},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5995895266532898},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5779353380203247},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5762250423431396},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5174151659011841},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.49645787477493286},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4925921559333801},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37738627195358276},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36368685960769653},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.31865283846855164},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.24181640148162842},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07384729385375977}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8459516167640686},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.7897888422012329},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.717806875705719},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6628307700157166},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5995895266532898},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5779353380203247},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5762250423431396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5174151659011841},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.49645787477493286},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4925921559333801},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37738627195358276},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36368685960769653},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.31865283846855164},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.24181640148162842},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07384729385375977},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"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}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/icassp.2003.1198921","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1198921","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.cmu.edu:compsci-2393","is_oa":false,"landing_page_url":"http://repository.cmu.edu/compsci/1394","pdf_url":null,"source":{"id":"https://openalex.org/S7407050927","display_name":"KiltHub Repository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computer Science Department","raw_type":"text"},{"id":"pmh:doi:10.1184/r1/6606407","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal contribution"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.137.8988","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.137.8988","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/~rongz/icassp_2003.pdf","raw_type":"text"},{"id":"pmh:oai:figshare.com:article/6606407","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Improving_the_Performance_of_an_LVCSR_System_Through_Ensembles_of_Acoustic_Models/6606407","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"doi:10.1184/r1/6606407.v1","is_oa":true,"landing_page_url":"https://doi.org/10.1184/r1/6606407.v1","pdf_url":null,"source":{"id":"https://openalex.org/S7407050927","display_name":"KiltHub Repository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"JournalArticle"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/6606407","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Improving_the_Performance_of_an_LVCSR_System_Through_Ensembles_of_Acoustic_Models/6606407","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7300000190734863}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W140747314","https://openalex.org/W1496929357","https://openalex.org/W1540371141","https://openalex.org/W1555037511","https://openalex.org/W1920186165","https://openalex.org/W2013196554","https://openalex.org/W2093677674","https://openalex.org/W2119442556","https://openalex.org/W2128022812","https://openalex.org/W2146197305","https://openalex.org/W2151345160","https://openalex.org/W2912934387","https://openalex.org/W3146702093","https://openalex.org/W4212883601","https://openalex.org/W4402490925","https://openalex.org/W6605693470","https://openalex.org/W6632223008","https://openalex.org/W6653769920","https://openalex.org/W6682471998","https://openalex.org/W6871885761"],"related_works":["https://openalex.org/W1997182898","https://openalex.org/W2119113516","https://openalex.org/W2944691285","https://openalex.org/W151018310","https://openalex.org/W3081187864","https://openalex.org/W4380605396","https://openalex.org/W3133352777","https://openalex.org/W2008737763","https://openalex.org/W2584084702","https://openalex.org/W2784059283"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"our":[3,43,75],"work":[4],"on":[5,49,102,118,130],"applying":[6],"ensembles":[7],"of":[8,14,39],"acoustic":[9,84],"models":[10],"to":[11,126],"the":[12,50,110],"problem":[13],"large":[15,69,104],"vocabulary":[16],"continuous":[17],"speech":[18],"recognition":[19],"(LVCSR).":[20],"We":[21,87,98],"propose":[22],"three":[23],"algorithms":[24,44],"for":[25,71,83,96],"constructing":[26],"ensembles.":[27],"The":[28,54],"first":[29],"two":[30],"have":[31],"their":[32],"roots":[33],"in":[34,123],"bagging":[35],"algorithms;":[36],"however,":[37],"instead":[38],"randomly":[40],"sampling":[41],"examples":[42],"construct":[45],"training":[46],"sets":[47],"based":[48],"word":[51,131],"error":[52,132],"rate.":[53],"third":[55],"one":[56],"is":[57,134],"a":[58,78,90,103],"boosting":[59,65],"style":[60],"algorithm.":[61],"Different":[62],"from":[63,109],"other":[64],"methods":[66],"which":[67],"demand":[68],"resources":[70],"computation":[72],"and":[73],"storage,":[74],"method":[76,91],"present":[77],"more":[79],"efficient":[80],"solution":[81],"suitable":[82],"model":[85],"training.":[86],"also":[88],"investigate":[89],"that":[92,124],"seeks":[93],"optimal":[94],"combination":[95],"models.":[97],"report":[99],"experimental":[100],"results":[101],"real":[105],"world":[106],"corpus":[107],"collected":[108],"Carnegie":[111],"Mellon":[112],"Communicator":[113],"dialog":[114],"system.":[115],"Significant":[116],"improvements":[117],"system":[119],"performance":[120],"are":[121],"observed":[122],"up":[125],"15.56%":[127],"relative":[128],"reduction":[129],"rate":[133],"achieved.":[135]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}