{"id":"https://openalex.org/W2000688218","doi":"https://doi.org/10.1109/icassp.2010.5495112","title":"Phone modeling and combining discriminative training for mandarinenglish bilingual speech recognition","display_name":"Phone modeling and combining discriminative training for mandarinenglish bilingual speech recognition","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2000688218","doi":"https://doi.org/10.1109/icassp.2010.5495112","mag":"2000688218"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2010.5495112","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495112","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal 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 University, Beijing, China","Department of Electronic Engineering, Tsinghua University, Beijing China 100084"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing China 100084","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 University, Beijing, China","Department of Electronic Engineering, Tsinghua University, Beijing China 100084"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing China 100084","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":1.9073,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.86809972,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"4","issue":null,"first_page":"4918","last_page":"4921"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9997000098228455,"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/T11309","display_name":"Music 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"}}],"keywords":[{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.9003598690032959},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.813355565071106},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7782686948776245},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6453401446342468},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.6068138480186462},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5760417580604553},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5664420127868652},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5570307970046997},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48645779490470886},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.47292429208755493},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.4673101603984833},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4153513014316559},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3779260218143463},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37525317072868347},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.250396728515625},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09043058753013611},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07636404037475586}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.9003598690032959},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.813355565071106},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7782686948776245},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6453401446342468},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.6068138480186462},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5760417580604553},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5664420127868652},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5570307970046997},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48645779490470886},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.47292429208755493},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.4673101603984833},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4153513014316559},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3779260218143463},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37525317072868347},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.250396728515625},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09043058753013611},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07636404037475586},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"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/icassp.2010.5495112","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495112","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal 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":12,"referenced_works":["https://openalex.org/W156213964","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/W2167949757","https://openalex.org/W4300869073","https://openalex.org/W6679957448"],"related_works":["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","https://openalex.org/W107086600","https://openalex.org/W2121652828"],"abstract_inverted_index":{"Automatic":[0],"multilingual":[1,134],"speech":[2,21,51,87,100],"recognition":[3,22,52,77],"is":[4,39,61],"always":[5],"a":[6,18,34,55],"difficult":[7],"task.":[8],"This":[9,89],"paper":[10,90],"presents":[11],"recent":[12],"work":[13],"on":[14,33,98],"the":[15,43,46,49,58,92,110,128,133],"development":[16],"of":[17,28,48,94,124,132],"Mandarin-English":[19],"bilingual":[20,29,50,86,99],"system.":[23,135],"A":[24],"unified":[25],"single":[26],"set":[27],"acoustic":[30],"models":[31],"based":[32],"novel":[35],"State-Time-Alignment":[36],"(STA)":[37],"method":[38,60,114],"proposed":[40],"to":[41,74,85],"balance":[42],"performance":[44],"and":[45,54,69,104,121],"complexity":[47],"system,":[53],"comparison":[56],"with":[57],"acoustic-likelihood":[59],"presented.":[62],"Discriminative":[63],"training":[64,96,126],"approaches":[65],"such":[66],"as":[67],"MPE":[68,103],"fMPE":[70],"have":[71,80],"been":[72,83],"shown":[73],"improve":[75],"monolingual":[76],"performance,":[78],"but":[79],"not":[81],"yet":[82],"applied":[84],"recognition.":[88],"investigates":[91],"use":[93],"discriminative":[95,125],"methods":[97],"recognition,":[101],"including":[102],"fMPE.":[105],"Experimental":[106],"results":[107],"show":[108],"that":[109],"STA":[111],"phone":[112,118],"clustering":[113,119],"outperforms":[115],"other":[116],"existing":[117],"methods,":[120],"both":[122],"forms":[123],"reduce":[127],"word":[129],"error":[130],"rate":[131]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2012,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}