{"id":"https://openalex.org/W2034585809","doi":"https://doi.org/10.1109/icassp.2013.6639094","title":"Improved mixed language speech recognition using asymmetric acoustic model and language model with code-switch inversion constraints","display_name":"Improved mixed language speech recognition using asymmetric acoustic model and language model with code-switch inversion constraints","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2034585809","doi":"https://doi.org/10.1109/icassp.2013.6639094","mag":"2034585809"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6639094","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639094","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 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/A5106406655","display_name":"Ying Li","orcid":"https://orcid.org/0009-0004-1669-1878"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ying Li","raw_affiliation_strings":["Human Language Technology Center, Department of Electronic and Computer Engineering, Hong Kong University of Science and Technology, Hong Kong, China","[Dept. of Electron. & Comput. Eng., Hong Kong Univ. of Sci. & Technol., Hong Kong, China]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology Center, Department of Electronic and Computer Engineering, Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"[Dept. of Electron. & Comput. Eng., Hong Kong Univ. of Sci. & Technol., Hong Kong, China]","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065856469","display_name":"Pascale Fung","orcid":"https://orcid.org/0000-0002-0628-7132"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Pascale Fung","raw_affiliation_strings":["Human Language Technology Center, Department of Electronic and Computer Engineering, Hong Kong University of Science and Technology, Hong Kong, China","[Dept. of Electron. & Comput. Eng., Hong Kong Univ. of Sci. & Technol., Hong Kong, China]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology Center, Department of Electronic and Computer Engineering, Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"[Dept. of Electron. & Comput. Eng., Hong Kong Univ. of Sci. & Technol., Hong Kong, China]","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I200769079"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":48,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7368","last_page":"7372"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9994999766349792,"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/T10028","display_name":"Topic Modeling","score":0.9933000206947327,"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/computer-science","display_name":"Computer science","score":0.8212602138519287},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.695578396320343},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.619560718536377},{"id":"https://openalex.org/keywords/inversion","display_name":"Inversion (geology)","score":0.5706108212471008},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5316057205200195},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.43518736958503723},{"id":"https://openalex.org/keywords/code-switching","display_name":"Code-switching","score":0.4226033091545105},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3438093364238739},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34202492237091064},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.31705838441848755},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.23584869503974915},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10660862922668457}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8212602138519287},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.695578396320343},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.619560718536377},{"id":"https://openalex.org/C1893757","wikidata":"https://www.wikidata.org/wiki/Q3653001","display_name":"Inversion (geology)","level":3,"score":0.5706108212471008},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5316057205200195},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.43518736958503723},{"id":"https://openalex.org/C18552078","wikidata":"https://www.wikidata.org/wiki/Q255615","display_name":"Code-switching","level":2,"score":0.4226033091545105},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3438093364238739},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34202492237091064},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.31705838441848755},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.23584869503974915},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10660862922668457},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C109007969","wikidata":"https://www.wikidata.org/wiki/Q749565","display_name":"Structural basin","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2013.6639094","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639094","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-61054","is_oa":false,"landing_page_url":"http://lbdiscover.ust.hk/uresolver?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rfr_id=info:sid/HKUST:SPI&rft.genre=article&rft.issn=1520-6149&rft.volume=&rft.issue=&rft.date=2013&rft.spage=7368&rft.aulast=Li&rft.aufirst=&rft.atitle=Improved%20Mixed%20Language%20Speech%20Recognition%20Using%20Asymmetric%20Acoustic%20Model%20and%20Language%20Model%20with%20Code-switch%20Inversion%20Constraints&rft.title=2013%20IEEE%20International%20Conference%20on%20Acoustics%2C%20Speech%20and%20Signal%20Processing%3A%20Proceedings","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8299999833106995,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W34000504","https://openalex.org/W104360363","https://openalex.org/W761725120","https://openalex.org/W1497396626","https://openalex.org/W1543317902","https://openalex.org/W1549308892","https://openalex.org/W2080550848","https://openalex.org/W2099808146","https://openalex.org/W2103635804","https://openalex.org/W2123162330","https://openalex.org/W2153433699","https://openalex.org/W2158388102","https://openalex.org/W2251238585","https://openalex.org/W2950517417","https://openalex.org/W3149829789","https://openalex.org/W4236564204","https://openalex.org/W6601391525","https://openalex.org/W6604326787","https://openalex.org/W6683509824"],"related_works":["https://openalex.org/W2126322296","https://openalex.org/W2163537793","https://openalex.org/W2037769829","https://openalex.org/W2916997151","https://openalex.org/W2781555308","https://openalex.org/W3021690593","https://openalex.org/W2125343999","https://openalex.org/W4200200210","https://openalex.org/W2161188302","https://openalex.org/W2888189389"],"abstract_inverted_index":{"We":[0],"propose":[1],"an":[2],"integrated":[3],"framework":[4],"for":[5],"large":[6],"vocabulary":[7],"continuous":[8],"mixed":[9,76],"language":[10,33,57,77,98,122,127,132,167],"speech":[11,146],"recognition":[12],"that":[13,96,106],"handles":[14],"the":[15,19,24,32,66,75,101,118,130,160],"accent":[16],"effect":[17],"in":[18,31,74,129],"bilingual":[20,162],"acoustic":[21,37,119,163],"model":[22,38,58,87,91,99,123,128,164],"and":[23,53,78,88,124,148,165],"inversion":[25,67],"constraint":[26,68],"well":[27],"known":[28],"to":[29,69],"linguists":[30],"model.":[34,168],"Our":[35,56,135],"asymmetric":[36],"with":[39,156],"phone":[40],"set":[41],"extension":[42],"improves":[43,59],"upon":[44,60],"previous":[45,61],"work":[46,62],"by":[47,63,141,149],"striking":[48],"a":[49,81,85,89,114,125,144,152],"balance":[50],"between":[51],"data":[52],"phonetic":[54],"knowledge.":[55],"(1)":[64],"using":[65],"predict":[70],"code":[71],"switching":[72],"points":[73],"(2)":[79],"integrating":[80],"code-switch":[82,121],"prediction":[83],"model,":[84],"translation":[86],"reconstruction":[90],"together.":[92,134],"This":[93],"integration":[94],"means":[95],"our":[97],"avoids":[100],"pitfall":[102],"of":[103],"propagated":[104],"error":[105,139],"could":[107],"arise":[108],"from":[109],"decoupling":[110],"these":[111],"steps.":[112],"Finally,":[113],"WFST-based":[115],"decoder":[116],"integrates":[117],"models,":[120],"monolingual":[126],"matrix":[131],"all":[133],"system":[136],"reduces":[137],"word":[138],"rate":[140],"1.88%":[142],"on":[143,151],"lecture":[145],"corpus":[147],"2.43%":[150],"lunch":[153],"conversation":[154],"corpus,":[155],"statistical":[157],"significance,":[158],"over":[159],"conventional":[161],"interpolated":[166]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":5},{"year":2014,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}