{"id":"https://openalex.org/W108550785","doi":"https://doi.org/10.21437/icslp.2000-436","title":"Large vocabulary Mandarin speech recognition with different approaches in modeling tones","display_name":"Large vocabulary Mandarin speech recognition with different approaches in modeling tones","publication_year":2000,"publication_date":"2000-10-16","ids":{"openalex":"https://openalex.org/W108550785","doi":"https://doi.org/10.21437/icslp.2000-436","mag":"108550785"},"language":"en","primary_location":{"id":"doi:10.21437/icslp.2000-436","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2000-436","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"6th International Conference on Spoken Language Processing (ICSLP 2000)","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/A5087298985","display_name":"Eric Chang","orcid":"https://orcid.org/0000-0002-9678-5994"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Eric Chang","raw_affiliation_strings":["Microsoft"],"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081259452","display_name":"Jian-Lai Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianlai Zhou","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030111795","display_name":"Shuo Di","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuo Di","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009913582","display_name":"Chao Huang","orcid":"https://orcid.org/0000-0002-9300-1787"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chao Huang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5064910846","display_name":"Kai-Fu Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kai-Fu Lee","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5087298985"],"corresponding_institution_ids":["https://openalex.org/I4210164937"],"apc_list":null,"apc_paid":null,"fwci":7.9568,"has_fulltext":false,"cited_by_count":79,"citation_normalized_percentile":{"value":0.97163688,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"vol. 2, 983","last_page":"986"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9975000023841858,"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":0.9958999752998352,"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":0.8448531627655029},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.8106540441513062},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8064424991607666},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7918397188186646},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6111800670623779},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.5948551297187805},{"id":"https://openalex.org/keywords/tone","display_name":"Tone (literature)","score":0.529521644115448},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.47427138686180115},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4382338523864746},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4334205090999603},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34831321239471436},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08536127209663391}],"concepts":[{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.8448531627655029},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.8106540441513062},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8064424991607666},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7918397188186646},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6111800670623779},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.5948551297187805},{"id":"https://openalex.org/C2780583480","wikidata":"https://www.wikidata.org/wiki/Q1366327","display_name":"Tone (literature)","level":2,"score":0.529521644115448},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.47427138686180115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4382338523864746},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4334205090999603},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34831321239471436},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08536127209663391},{"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":2,"locations":[{"id":"doi:10.21437/icslp.2000-436","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2000-436","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"6th International Conference on Spoken Language Processing (ICSLP 2000)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.28.7240","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.28.7240","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.microsoft.com/china/research/group/../downloads/g-nlps/NLPSP/n10.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W165808295","https://openalex.org/W1596148575","https://openalex.org/W1713240683","https://openalex.org/W2088632109","https://openalex.org/W2129604454","https://openalex.org/W2130470091"],"related_works":["https://openalex.org/W2393887907","https://openalex.org/W2347443630","https://openalex.org/W2388826840","https://openalex.org/W2481138693","https://openalex.org/W2379831327","https://openalex.org/W2386691339","https://openalex.org/W2365805939","https://openalex.org/W2287147624","https://openalex.org/W156219719","https://openalex.org/W2163874654"],"abstract_inverted_index":{"Large":[0],"vocabulary":[1,99],"continuous":[2,119],"Mandarin":[3,42,100],"speech":[4,12,64,101,120],"recognition":[5,13,65,102],"has":[6],"been":[7],"an":[8],"important":[9],"problem":[10],"for":[11,15,32,63],"researchers":[14],"several":[16],"reasons":[17],"[1],":[18],"[3].":[19,91],"First":[20],"of":[21,35,54],"all,":[22],"it":[23],"is":[24],"a":[25,60,78,97],"tonal":[26],"language":[27],"that":[28],"requires":[29],"special":[30],"treatment":[31],"the":[33,52,88],"modeling":[34,73,112],"tones.":[36],"There":[37],"are":[38,44,121],"five":[39],"tones":[40,74,113],"in":[41,111],"which":[43],"necessary":[45],"to":[46,66,72],"disambiguate":[47],"between":[48],"confusable":[49],"words.":[50],"Secondly,":[51],"difficulty":[53],"entering":[55],"Chinese":[56],"by":[57],"keyboard":[58],"presents":[59],"great":[61],"opportunity":[62],"improve":[67],"computer":[68],"usability.":[69],"Previous":[70],"approaches":[71],"have":[75],"included":[76],"using":[77],"separate":[79],"tone":[80],"classifier":[81],"[1]":[82],"and":[83,114],"incorporating":[84],"pitch":[85],"directly":[86],"into":[87],"feature":[89],"vector":[90],"In":[92],"this":[93],"paper,":[94],"we":[95],"describe":[96],"large":[98],"system":[103],"based":[104],"on":[105,118],"Microsoft's":[106],"Whisper":[107],"system.":[108],"Several":[109],"alternatives":[110],"their":[115],"error":[116],"rates":[117],"compared.":[122]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":5}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}