{"id":"https://openalex.org/W2103635804","doi":"https://doi.org/10.1109/icassp.2008.4518594","title":"Mandarin-English bilingual Speech Recognition for real world music retrieval","display_name":"Mandarin-English bilingual Speech Recognition for real world music retrieval","publication_year":2008,"publication_date":"2008-03-01","ids":{"openalex":"https://openalex.org/W2103635804","doi":"https://doi.org/10.1109/icassp.2008.4518594","mag":"2103635804"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2008.4518594","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518594","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 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/A5100375543","display_name":"Qingqing Zhang","orcid":"https://orcid.org/0000-0002-1464-6203"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qingqing Zhang","raw_affiliation_strings":["ThinkIT Speech Laboratory, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China","Inst. of Acoust., Chinese Acad. of Sci., Beijing"],"affiliations":[{"raw_affiliation_string":"ThinkIT Speech Laboratory, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Inst. of Acoust., Chinese Acad. of Sci., Beijing","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111847664","display_name":"Jielin Pan","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jielin Pan","raw_affiliation_strings":["ThinkIT Speech Laboratory, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China","Inst. of Acoust., Chinese Acad. of Sci., Beijing"],"affiliations":[{"raw_affiliation_string":"ThinkIT Speech Laboratory, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Inst. of Acoust., Chinese Acad. of Sci., Beijing","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100425112","display_name":"Yonghong Yan","orcid":"https://orcid.org/0000-0001-6907-5770"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yonghong Yan","raw_affiliation_strings":["ThinkIT Speech Laboratory, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China","Inst. of Acoust., Chinese Acad. of Sci., Beijing"],"affiliations":[{"raw_affiliation_string":"ThinkIT Speech Laboratory, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Inst. of Acoust., Chinese Acad. of Sci., Beijing","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100375543"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210099069"],"apc_list":null,"apc_paid":null,"fwci":2.709,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.89153439,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"23","issue":null,"first_page":"4253","last_page":"4256"},"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":0.9998000264167786,"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/T10860","display_name":"Speech and Audio Processing","score":0.9990000128746033,"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":0.7907813191413879},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7833062410354614},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6931555867195129},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.605912446975708},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5965120792388916},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.5666390061378479},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5461456179618835},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5333371758460999},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5325621366500854},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.48422789573669434},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.47022247314453125},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4690908193588257},{"id":"https://openalex.org/keywords/grammar","display_name":"Grammar","score":0.4253075420856476},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2738049030303955},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.10528185963630676}],"concepts":[{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.7907813191413879},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7833062410354614},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6931555867195129},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.605912446975708},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5965120792388916},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.5666390061378479},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5461456179618835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5333371758460999},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5325621366500854},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.48422789573669434},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.47022247314453125},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4690908193588257},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.4253075420856476},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2738049030303955},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10528185963630676},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","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":2,"locations":[{"id":"doi:10.1109/icassp.2008.4518594","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518594","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.634.5257","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.634.5257","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.iis.sinica.edu.tw/page/jise/2010/201007_21.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8100000023841858}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W77825124","https://openalex.org/W121747529","https://openalex.org/W1767292398","https://openalex.org/W1783786615","https://openalex.org/W1846073453","https://openalex.org/W1998541766","https://openalex.org/W2014962660","https://openalex.org/W2132974827","https://openalex.org/W2153159136","https://openalex.org/W2165355580","https://openalex.org/W2167949757","https://openalex.org/W2169405831","https://openalex.org/W2169883442","https://openalex.org/W6604978991","https://openalex.org/W6679957448","https://openalex.org/W6684707517"],"related_works":["https://openalex.org/W2031478549","https://openalex.org/W4379055549","https://openalex.org/W2150890698","https://openalex.org/W2163874654","https://openalex.org/W4245698648","https://openalex.org/W2401394187","https://openalex.org/W2405257913","https://openalex.org/W3133710586","https://openalex.org/W2125964738","https://openalex.org/W2098529290"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"our":[3],"recent":[4],"work":[5],"on":[6,58,94,125],"the":[7,27,30,33,67,76,89,100,117,123,133,139],"development":[8],"of":[9,32,41,92,105,132],"a":[10],"grammar-constrained,":[11],"Mandarin-English":[12],"bilingual":[13,34,42,142],"Speech":[14],"Recognition":[15],"System":[16],"(MESRS)":[17],"for":[18,107,141],"real":[19],"world":[20],"music":[21],"retrieval.":[22],"In":[23,71],"order":[24,72],"to":[25,73,116,130],"balance":[26],"performance":[28,140],"and":[29,64,97,138],"complexity":[31],"SR":[35],"system,":[36,137],"an":[37],"unified":[38],"single":[39],"set":[40],"acoustic":[43],"models":[44],"derived":[45],"by":[46,112],"phone":[47,54,95],"clustering":[48,55,96],"is":[49,62],"developed.":[50],"A":[51],"novel":[52],"Two-pass":[53],"method":[56],"based":[57],"Confusion":[59],"Matrix":[60],"(TCM)":[61],"presented":[63],"compared":[65,115],"with":[66,75],"log-likelihood":[68],"measure":[69],"method.":[70],"deal":[74],"Mandarin":[77,126,136],"accent":[78],"in":[79],"spoken":[80],"English,":[81],"different":[82],"non-native":[83,98],"adaptation":[84],"approaches":[85,93],"are":[86],"investigated.":[87],"With":[88],"effective":[90],"incorporation":[91],"adaptation,":[99],"Phrase":[101],"Error":[102],"Rate":[103],"(PhrER)":[104],"MESRS":[106],"English":[108,120],"utterances":[109,127,144],"was":[110,128],"reduced":[111],"24.5%":[113],"relatively":[114],"baseline":[118,134],"monolingual":[119,135],"system":[121],"while":[122],"PhrER":[124,148],"comparable":[129],"that":[131],"code-mixing":[143],"achieved":[145],"22.4%":[146],"relative":[147],"reduction.":[149]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
