{"id":"https://openalex.org/W2021428249","doi":"https://doi.org/10.1109/iscslp.2010.5684841","title":"Mandarin-English bilingual phone modeling and combining MPE based Discriminative training for cross-language speech recognition","display_name":"Mandarin-English bilingual phone modeling and combining MPE based Discriminative training for cross-language speech recognition","publication_year":2010,"publication_date":"2010-11-01","ids":{"openalex":"https://openalex.org/W2021428249","doi":"https://doi.org/10.1109/iscslp.2010.5684841","mag":"2021428249"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2010.5684841","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2010.5684841","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 7th International Symposium on Chinese Spoken Language 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/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua National Laboratory for Information Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua National Laboratory for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100409741","display_name":"Jia Liu","orcid":"https://orcid.org/0000-0003-0383-0934"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Liu","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua National Laboratory for Information Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua National Laboratory for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.8174,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.70963573,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"1","issue":null,"first_page":"103","last_page":"108"},"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/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/T11309","display_name":"Music and Audio Processing","score":0.9973999857902527,"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/discriminative-model","display_name":"Discriminative model","score":0.9177172183990479},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.832106351852417},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7201296091079712},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6559421420097351},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6274341344833374},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.625558078289032},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5536469221115112},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5016255378723145},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4771539568901062},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.46054428815841675},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45384305715560913},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4484335780143738},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3375903069972992},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07343712449073792},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06060519814491272}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.9177172183990479},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.832106351852417},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7201296091079712},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6559421420097351},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6274341344833374},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.625558078289032},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5536469221115112},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5016255378723145},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4771539568901062},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.46054428815841675},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45384305715560913},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4484335780143738},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3375903069972992},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07343712449073792},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06060519814491272},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2010.5684841","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2010.5684841","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 7th International Symposium on Chinese Spoken Language Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7400000095367432,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W156213964","https://openalex.org/W1904457459","https://openalex.org/W2018466475","https://openalex.org/W2033436836","https://openalex.org/W2102775757","https://openalex.org/W2125610823","https://openalex.org/W2132663820","https://openalex.org/W2132974827","https://openalex.org/W2151941172","https://openalex.org/W2164499211","https://openalex.org/W2536834305","https://openalex.org/W4300869073","https://openalex.org/W6679957448","https://openalex.org/W6729096895"],"related_works":["https://openalex.org/W2153098279","https://openalex.org/W2061937230","https://openalex.org/W2163874654","https://openalex.org/W2162582511","https://openalex.org/W4245698648","https://openalex.org/W2405257913","https://openalex.org/W3133710586","https://openalex.org/W2125964738","https://openalex.org/W2098529290","https://openalex.org/W2026402306"],"abstract_inverted_index":{"Automatic":[0],"multilingual":[1,154],"speech":[2,21,51,90],"recognition":[3,22,52,83,91],"is":[4,39,96],"always":[5],"a":[6,18,25,34],"difficult":[7],"task.":[8],"This":[9],"paper":[10],"presents":[11],"recent":[12],"work":[13],"on":[14,33],"the":[15,43,46,49,64,71,105,118,123,130,148,153,163],"development":[16],"of":[17,28,48,144,152],"Mandarin-English":[19],"bilingual":[20,29,50,89,106,124],"system.":[23,53,92],"Firstly":[24],"universal":[26],"set":[27],"acoustic":[30],"models":[31],"based":[32],"novel":[35],"State-Time-Alignment":[36],"(STA)":[37],"method":[38,95,134],"proposed":[40],"to":[41,80,87,98,116],"balance":[42],"performance":[44,121,164],"and":[45,70,108,156],"complexity":[47],"Then":[54],"Discriminative":[55],"training":[56,62,104,111,146,160],"approaches":[57],"such":[58],"as":[59],"discriminative":[60,110,145,159],"Gaussian":[61],"using":[63],"minimum":[65],"phone":[66,132,138],"error":[67,150],"(MPE)":[68],"criterion":[69],"discriminatively":[72],"trained":[73],"feature":[74],"transform":[75],"fMPE,":[76],"which":[77],"are":[78,85,113],"proved":[79],"improved":[81],"monolingual":[82],"performance,":[84],"modified":[86],"manage":[88],"A":[93],"new":[94],"applied":[97],"generate":[99],"significantly":[100],"better":[101],"lattices":[102],"for":[103],"model,":[107],"complementary":[109,158],"methods":[112,161],"also":[114],"explored":[115],"get":[117],"best":[119],"ROVER":[120],"in":[122],"situation.":[125],"Experimental":[126],"results":[127],"show":[128],"that":[129],"STA":[131],"clustering":[133,139],"outperforms":[135],"other":[136],"existing":[137],"methods.":[140],"Furthermore":[141],"both":[142],"forms":[143],"reduce":[147],"word":[149],"rate":[151],"system,":[155],"combining":[157],"improves":[162],"significantly.":[165]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}