{"id":"https://openalex.org/W2158387599","doi":"https://doi.org/10.1109/icassp.2008.4518704","title":"Text normalization in mandarin text-to-speech system","display_name":"Text normalization in mandarin text-to-speech system","publication_year":2008,"publication_date":"2008-03-01","ids":{"openalex":"https://openalex.org/W2158387599","doi":"https://doi.org/10.1109/icassp.2008.4518704","mag":"2158387599"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2008.4518704","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518704","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":"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/A5064013704","display_name":"Yuxiang Jia","orcid":"https://orcid.org/0000-0003-0481-0740"},"institutions":[{"id":"https://openalex.org/I19370010","display_name":"Orange (France)","ror":"https://ror.org/035j0tq82","country_code":"FR","type":"company","lineage":["https://openalex.org/I19370010"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Yuxiang Jia","raw_affiliation_strings":["Speech and Natural Language Processing Unit, France Telecom R&D, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech and Natural Language Processing Unit, France Telecom R&D, Beijing, China","institution_ids":["https://openalex.org/I19370010"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108142875","display_name":"Dezhi Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I19370010","display_name":"Orange (France)","ror":"https://ror.org/035j0tq82","country_code":"FR","type":"company","lineage":["https://openalex.org/I19370010"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Dezhi Huang","raw_affiliation_strings":["Speech and Natural Language Processing Unit, France Telecom R&D, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech and Natural Language Processing Unit, France Telecom R&D, Beijing, China","institution_ids":["https://openalex.org/I19370010"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100743423","display_name":"Wu Liu","orcid":"https://orcid.org/0000-0003-3058-2067"},"institutions":[{"id":"https://openalex.org/I19370010","display_name":"Orange (France)","ror":"https://ror.org/035j0tq82","country_code":"FR","type":"company","lineage":["https://openalex.org/I19370010"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Wu Liu","raw_affiliation_strings":["Speech and Natural Language Processing Unit, France Telecom R&D, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech and Natural Language Processing Unit, France Telecom R&D, Beijing, China","institution_ids":["https://openalex.org/I19370010"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056136429","display_name":"Yuan Dong","orcid":"https://orcid.org/0009-0004-8650-1603"},"institutions":[{"id":"https://openalex.org/I19370010","display_name":"Orange (France)","ror":"https://ror.org/035j0tq82","country_code":"FR","type":"company","lineage":["https://openalex.org/I19370010"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Yuan Dong","raw_affiliation_strings":["Speech and Natural Language Processing Unit, France Telecom R&D, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech and Natural Language Processing Unit, France Telecom R&D, Beijing, China","institution_ids":["https://openalex.org/I19370010"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052324373","display_name":"Shiwen Yu","orcid":"https://orcid.org/0000-0002-8514-3195"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiwen Yu","raw_affiliation_strings":["Institute of Computational Linguistics, Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computational Linguistics, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078897088","display_name":"Haila Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I19370010","display_name":"Orange (France)","ror":"https://ror.org/035j0tq82","country_code":"FR","type":"company","lineage":["https://openalex.org/I19370010"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Haila Wang","raw_affiliation_strings":["Speech and Natural Language Processing Unit, France Telecom R&D, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech and Natural Language Processing Unit, France Telecom R&D, Beijing, China","institution_ids":["https://openalex.org/I19370010"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"4693","last_page":"4696"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9959999918937683,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9959999918937683,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9828000068664551,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9745000004768372,"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/normalization","display_name":"Normalization (sociology)","score":0.7989697456359863},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.778577446937561},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.7117743492126465},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6468256115913391},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6030308604240417},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.5034269690513611},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.4510870575904846},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3801414668560028},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08273512125015259}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7989697456359863},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.778577446937561},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.7117743492126465},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6468256115913391},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6030308604240417},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.5034269690513611},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.4510870575904846},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3801414668560028},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08273512125015259},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","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},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2008.4518704","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518704","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W62144051","https://openalex.org/W1535857482","https://openalex.org/W1560680030","https://openalex.org/W1589180892","https://openalex.org/W1989026251","https://openalex.org/W2076467305","https://openalex.org/W2099531983","https://openalex.org/W2140016149","https://openalex.org/W2164107060","https://openalex.org/W2369721020","https://openalex.org/W2389448094","https://openalex.org/W6602579319","https://openalex.org/W6635291372","https://openalex.org/W6674798237","https://openalex.org/W6884970104"],"related_works":["https://openalex.org/W2990005675","https://openalex.org/W2374317326","https://openalex.org/W1603321096","https://openalex.org/W2394766824","https://openalex.org/W2078713291","https://openalex.org/W2361574037","https://openalex.org/W2386292991","https://openalex.org/W2364440891","https://openalex.org/W2393726922","https://openalex.org/W2366752344"],"abstract_inverted_index":{"Text":[0],"normalization":[1,14],"is":[2,15],"an":[3,70],"important":[4],"component":[5],"in":[6,12,74],"text-to-speech":[7],"system":[8],"and":[9,38,52,97,103],"the":[10,18,30,62,66,88,104],"difficulty":[11],"text":[13],"to":[16,109],"disambiguate":[17],"non-standard":[19],"words":[20],"(NSWs).":[21],"This":[22],"paper":[23],"develops":[24],"a":[25,33,40,93],"taxonomy":[26,90],"of":[27,32,72,81],"NSWs":[28,42,64,89],"on":[29,61],"basis":[31],"large":[34],"scale":[35],"Chinese":[36],"corpus,":[37],"proposes":[39],"two-stage":[41,67,105],"disambiguation":[43],"strategy,":[44],"finite":[45],"state":[46],"automata":[47],"(FSA)":[48],"for":[49,57],"initial":[50],"classification":[51],"maximum":[53],"entropy":[54],"(ME)":[55],"classifiers":[56,99],"subclass":[58],"disambiguation.":[59],"Based":[60],"above":[63],"taxonomy,":[65],"approach":[68,106],"achieves":[69],"F-score":[71],"98.53%":[73],"open":[75],"test,":[76],"5.23%":[77],"higher":[78],"than":[79],"that":[80,87],"FSA":[82,92],"based":[83],"approach.":[84],"Experiments":[85],"show":[86],"ensures":[91],"high":[94],"baseline":[95],"performance":[96],"ME":[98],"make":[100],"considerable":[101],"improvement,":[102],"adapts":[107],"well":[108],"new":[110],"domains.":[111]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}