{"id":"https://openalex.org/W2167513360","doi":"https://doi.org/10.1109/tasl.2009.2014263","title":"Building A Highly Accurate Mandarin Speech Recognizer With Language-Independent Technologies and Language-Dependent Modules","display_name":"Building A Highly Accurate Mandarin Speech Recognizer With Language-Independent Technologies and Language-Dependent Modules","publication_year":2009,"publication_date":"2009-07-17","ids":{"openalex":"https://openalex.org/W2167513360","doi":"https://doi.org/10.1109/tasl.2009.2014263","mag":"2167513360"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2009.2014263","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2009.2014263","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/A5112467501","display_name":"Mei-Yuh Hwang","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mei-Yuh Hwang","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA","University of Washington, Seattle, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"University of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018627264","display_name":"Gang Peng","orcid":"https://orcid.org/0000-0002-1465-1301"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["HK","US"],"is_corresponding":false,"raw_author_name":"Gang Peng","raw_affiliation_strings":["Chinese University of Hong Kong, Sha Tin, Hong Kong, China","University of Washington, Seattle, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese University of Hong Kong, Sha Tin, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"University of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087215613","display_name":"Mari Ostendorf","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M. Ostendorf","raw_affiliation_strings":["Department of Electrical Engineering, University of Washington, Seattle, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100396375","display_name":"Wen Wang","orcid":"https://orcid.org/0000-0002-0356-1968"},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wen Wang","raw_affiliation_strings":["SRI International, Inc., Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI International, Inc., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109855517","display_name":"A. Faria","orcid":null},"institutions":[{"id":"https://openalex.org/I1297971548","display_name":"International Computer Science Institute","ror":"https://ror.org/01ewh7m12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1297971548"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"A. Faria","raw_affiliation_strings":["International Computer Science Institute (ICSI), University of California Berkeley, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Computer Science Institute (ICSI), University of California Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I1297971548","https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000293651","display_name":"Aaron Heidel","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"A. Heidel","raw_affiliation_strings":["National Taiwan University, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.1089,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.92416337,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"17","issue":"7","first_page":"1253","last_page":"1262"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9965999722480774,"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":0.9965000152587891,"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/mandarin-chinese","display_name":"Mandarin Chinese","score":0.8823277354240417},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7886579036712646},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7172678112983704},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7103677988052368},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7079606652259827},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5609200596809387},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5377237200737},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5324538350105286},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5247538089752197},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5236539840698242},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5146937966346741},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4972710907459259},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.48664650321006775},{"id":"https://openalex.org/keywords/tone","display_name":"Tone (literature)","score":0.4809624254703522},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.13408613204956055}],"concepts":[{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.8823277354240417},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7886579036712646},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7172678112983704},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7103677988052368},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7079606652259827},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5609200596809387},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5377237200737},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5324538350105286},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5247538089752197},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5236539840698242},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5146937966346741},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4972710907459259},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.48664650321006775},{"id":"https://openalex.org/C2780583480","wikidata":"https://www.wikidata.org/wiki/Q1366327","display_name":"Tone (literature)","level":2,"score":0.4809624254703522},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13408613204956055},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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":1,"locations":[{"id":"doi:10.1109/tasl.2009.2014263","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2009.2014263","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":[{"score":0.7099999785423279,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W34922426","https://openalex.org/W42317955","https://openalex.org/W50577135","https://openalex.org/W103244930","https://openalex.org/W169882265","https://openalex.org/W170853248","https://openalex.org/W177307080","https://openalex.org/W1586345832","https://openalex.org/W1612003148","https://openalex.org/W1631260214","https://openalex.org/W1709739193","https://openalex.org/W1797288984","https://openalex.org/W1880262756","https://openalex.org/W2002342963","https://openalex.org/W2050597349","https://openalex.org/W2096215262","https://openalex.org/W2096610504","https://openalex.org/W2102775757","https://openalex.org/W2105830342","https://openalex.org/W2110239393","https://openalex.org/W2111741330","https://openalex.org/W2122272452","https://openalex.org/W2125610823","https://openalex.org/W2135336969","https://openalex.org/W2142694085","https://openalex.org/W2145989470","https://openalex.org/W2150907703","https://openalex.org/W2154860986","https://openalex.org/W2158195707","https://openalex.org/W2167724838","https://openalex.org/W2404852420","https://openalex.org/W2594610113","https://openalex.org/W6601762979","https://openalex.org/W6604228424","https://openalex.org/W6606983177","https://openalex.org/W6634963458","https://openalex.org/W6636440780","https://openalex.org/W6636811518","https://openalex.org/W6638218882","https://openalex.org/W6639619044","https://openalex.org/W6682398751","https://openalex.org/W6713265957"],"related_works":["https://openalex.org/W2167155152","https://openalex.org/W2113687551","https://openalex.org/W2112752961","https://openalex.org/W2162582511","https://openalex.org/W2163874654","https://openalex.org/W4245698648","https://openalex.org/W2401394187","https://openalex.org/W2405257913","https://openalex.org/W3133710586","https://openalex.org/W2125964738"],"abstract_inverted_index":{"We":[0],"describe":[1],"a":[2],"system":[3,65,140],"for":[4,48,72],"highly":[5],"accurate":[6],"large-vocabulary":[7],"Mandarin":[8,138],"speech":[9],"recognition.":[10],"The":[11,78,105],"prevailing":[12],"hidden":[13],"Markov":[14],"model":[15],"based":[16],"technologies":[17],"are":[18,44,80,111],"essentially":[19],"language":[20,118],"independent":[21],"and":[22,34,60,99],"constitute":[23],"the":[24,73,108,130,136],"backbone":[25],"of":[26,69,75,87,102,107],"our":[27],"system.":[28],"These":[29],"include":[30],"minimum-phone-error":[31],"discriminative":[32,103],"training":[33],"maximum-likelihood":[35],"linear":[36],"regression":[37],"adaptation,":[38],"among":[39],"others.":[40],"Additionally,":[41],"careful":[42],"considerations":[43],"taken":[45],"into":[46],"account":[47],"Mandarin-specific":[49],"issues":[50],"including":[51],"lexical":[52],"word":[53],"segmentation,":[54],"tone":[55],"modeling,":[56],"phone":[57,97],"set":[58],"design,":[59],"automatic":[61],"acoustic":[62,70],"segmentation.":[63],"Our":[64],"comprises":[66],"two":[67,109],"sets":[68,98],"models":[71],"purposes":[74],"cross":[76],"adaptation.":[77],"systems":[79],"designed":[81],"to":[82],"be":[83],"complementary":[84],"in":[85,141],"terms":[86],"errors":[88],"but":[89],"with":[90],"similar":[91],"overall":[92],"accuracy":[93],"by":[94,114],"using":[95],"different":[96,100],"combinations":[101],"learning.":[104],"outputs":[106],"subsystems":[110],"then":[112],"rescored":[113],"an":[115],"adapted":[116],"n-gram":[117],"model.":[119],"Final":[120],"confusion":[121],"network":[122],"combination":[123],"yielded":[124],"9.1%":[125],"character":[126],"error":[127],"rate":[128],"on":[129],"DARPA":[131],"GALE":[132],"2007":[133],"official":[134],"evaluation,":[135],"best":[137],"recognition":[139],"that":[142],"year.":[143]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}