{"id":"https://openalex.org/W1891566590","doi":"https://doi.org/10.1109/icassp.2003.1198892","title":"Triphone model reconstruction for Mandarin pronunciation variations","display_name":"Triphone model reconstruction for Mandarin pronunciation variations","publication_year":2003,"publication_date":"2003-11-21","ids":{"openalex":"https://openalex.org/W1891566590","doi":"https://doi.org/10.1109/icassp.2003.1198892","mag":"1891566590"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2003.1198892","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1198892","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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/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":"P. Fung","raw_affiliation_strings":["Human Language Technology Center, Department of Electrical and Electronic Engineering, University of Science and Technology (HKUST), Hong Kong, China","Human Language Technol. Center, Univ. of Sci. & Technol., Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology Center, Department of Electrical and Electronic Engineering, University of Science and Technology (HKUST), Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"Human Language Technol. Center, Univ. of Sci. & Technol., Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100330493","display_name":"Yi Liu","orcid":"https://orcid.org/0000-0002-1383-7067"},"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":"Liu Yi","raw_affiliation_strings":["Human Language Technology Center, Department of Electrical and Electronic Engineering, University of Science and Technology (HKUST), Hong Kong, China","Human Language Technol. Center, Univ. of Sci. & Technol., Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology Center, Department of Electrical and Electronic Engineering, University of Science and Technology (HKUST), Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"Human Language Technol. Center, 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":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"760"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9864000082015991,"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":0.9814000129699707,"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/pronunciation","display_name":"Pronunciation","score":0.7991209030151367},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7857859134674072},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7728803753852844},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.673025906085968},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.668669581413269},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.5487736463546753},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5185987949371338},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4538995623588562},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.42584794759750366},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.4198184609413147},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.34001508355140686},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09132328629493713}],"concepts":[{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.7991209030151367},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7857859134674072},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7728803753852844},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.673025906085968},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.668669581413269},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.5487736463546753},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5185987949371338},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4538995623588562},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.42584794759750366},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.4198184609413147},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.34001508355140686},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09132328629493713},{"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.2003.1198892","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1198892","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-13012","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-13012","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W88081813","https://openalex.org/W111333879","https://openalex.org/W133406983","https://openalex.org/W1932371945","https://openalex.org/W2115900267","https://openalex.org/W2131463853","https://openalex.org/W2586367986","https://openalex.org/W6604521839","https://openalex.org/W6605486246","https://openalex.org/W6679342420"],"related_works":["https://openalex.org/W2222951281","https://openalex.org/W2272290179","https://openalex.org/W2068412075","https://openalex.org/W156219719","https://openalex.org/W27484908","https://openalex.org/W2163874654","https://openalex.org/W2061937230","https://openalex.org/W2132658536","https://openalex.org/W3081187864","https://openalex.org/W151018310"],"abstract_inverted_index":{"The":[0,83,95],"high":[1],"error":[2,124],"rate":[3,125],"of":[4,18,51,97,115],"recognition":[5],"accuracy":[6],"in":[7,12,127],"spontaneous":[8,128],"speech":[9],"is":[10,55,89,100],"due":[11],"part":[13],"to":[14,41,47,91],"the":[15,49,64,103],"poor":[16],"modeling":[17,25],"pronunciations.":[19],"In":[20,45],"this":[21,98],"paper,":[22],"we":[23],"propose":[24],"pronunciation":[26,43],"variations":[27],"through":[28,68],"triphone":[29,52,81],"model":[30,39,60,67,69,73,85],"reconstruction.":[31,70],"We":[32],"first":[33],"generate":[34],"a":[35,58,119],"partial":[36],"change":[37],"phone":[38],"(PCPM)":[40],"differentiate":[42],"variations.":[44],"order":[46],"improve":[48],"resolution":[50],"models,":[53],"PCPM":[54],"used":[56],"as":[57],"hidden":[59],"and":[61],"merged":[62],"into":[63],"pre-trained":[65],"acoustic":[66,84],"To":[71],"avoid":[72],"confusion,":[74],"auxiliary":[75],"decision":[76,92],"trees":[77],"are":[78],"established":[79],"for":[80],"PCPM.":[82],"reconstruction":[86],"on":[87,102],"triphones":[88],"equivalent":[90],"tree":[93],"merging.":[94],"effectiveness":[96],"approach":[99],"evaluated":[101],"1997":[104],"Hub4NE":[105],"Mandarin":[106],"Broadcast":[107],"News":[108],"Corpus":[109],"(1997":[110],"MBN)":[111],"with":[112],"different":[113],"styles":[114],"speech.":[116,129],"It":[117],"gives":[118],"significant":[120],"2.39%":[121],"absolute":[122],"syllable":[123],"reduction":[126]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}