{"id":"https://openalex.org/W2139473043","doi":"https://doi.org/10.1109/icassp.2009.4960447","title":"Generalized Baum-Welch algorithm for discriminative training on large vocabulary continuous speech recognition system","display_name":"Generalized Baum-Welch algorithm for discriminative training on large vocabulary continuous speech recognition system","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2139473043","doi":"https://doi.org/10.1109/icassp.2009.4960447","mag":"2139473043"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960447","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960447","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/A5033764781","display_name":"Roger Hsiao","orcid":"https://orcid.org/0000-0001-8638-4508"},"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":true,"raw_author_name":"Roger Hsiao","raw_affiliation_strings":["InterACT, Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA","InterACT, Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA 15213 USA#TAB#"],"affiliations":[{"raw_affiliation_string":"InterACT, Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"InterACT, Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA 15213 USA#TAB#","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033756912","display_name":"Wilson Tam","orcid":"https://orcid.org/0000-0003-0641-3060"},"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":"Yik-Cheung Tam","raw_affiliation_strings":["InterACT, Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA","InterACT, Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA 15213 USA#TAB#"],"affiliations":[{"raw_affiliation_string":"InterACT, Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"InterACT, Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA 15213 USA#TAB#","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058049725","display_name":"Tanja Schultz","orcid":"https://orcid.org/0000-0002-9809-7028"},"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":"Tanja Schultz","raw_affiliation_strings":["InterACT, Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA","InterACT, Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA 15213 USA#TAB#"],"affiliations":[{"raw_affiliation_string":"InterACT, Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"InterACT, Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA 15213 USA#TAB#","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5033764781"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":1.4272,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.81862192,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"19","issue":null,"first_page":"3769","last_page":"3772"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9955999851226807,"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/T10860","display_name":"Speech and Audio Processing","score":0.9955999851226807,"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9922999739646912,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9900000095367432,"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/discriminative-model","display_name":"Discriminative model","score":0.9318504929542542},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.8595995903015137},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7082434892654419},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6937894821166992},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6877047419548035},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5811705589294434},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5081272125244141}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.9318504929542542},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8595995903015137},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7082434892654419},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6937894821166992},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6877047419548035},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5811705589294434},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5081272125244141},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2009.4960447","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960447","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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.149.6453","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.149.6453","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://csl.ira.uka.de/fileadmin/media/publication_files/HsiaoSchultz-ICASSP2009.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.206.3169","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.206.3169","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/%7Ewrhsiao/papers/icassp2009_gbw.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2033565080","https://openalex.org/W2039151035","https://openalex.org/W2150142469","https://openalex.org/W2296319761","https://openalex.org/W4250589301","https://openalex.org/W6682334925"],"related_works":["https://openalex.org/W2167155152","https://openalex.org/W2136763963","https://openalex.org/W2404514746","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1652783584","https://openalex.org/W1909151225","https://openalex.org/W3184123547","https://openalex.org/W2160030256","https://openalex.org/W2088733771"],"abstract_inverted_index":{"We":[0,31],"propose":[1],"a":[2,27],"new":[3],"optimization":[4,29],"algorithm":[5,11,37,50],"called":[6],"Generalized":[7],"Baum":[8],"Welch":[9],"(GBW)":[10],"for":[12,38,51,66],"discriminative":[13,52],"training":[14,53],"on":[15,23,26],"hidden":[16],"Markov":[17],"model":[18],"(HMM).":[19],"GBW":[20,63],"is":[21],"based":[22],"Lagrange":[24],"relaxation":[25],"transformed":[28],"problem.":[30],"show":[32],"that":[33],"both":[34],"Baum-Welch":[35,48],"(BW)":[36],"ML":[39],"estimate":[40],"of":[41,57,62],"HMM":[42],"parameters,":[43],"and":[44,64],"the":[45,60],"popular":[46],"extended":[47],"(EBW)":[49],"are":[54],"special":[55],"cases":[56],"GBW.We":[58],"compare":[59],"performance":[61],"EBW":[65],"Farsi":[67],"large":[68],"vocabulary":[69],"continuous":[70],"speech":[71],"recognition":[72],"(LVCSR).":[73]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}