{"id":"https://openalex.org/W2127019176","doi":"https://doi.org/10.1109/icassp.2004.1326156","title":"Tone articulation modeling for Mandarin spontaneous speech recognition","display_name":"Tone articulation modeling for Mandarin spontaneous speech recognition","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https://openalex.org/W2127019176","doi":"https://doi.org/10.1109/icassp.2004.1326156","mag":"2127019176"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2004.1326156","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326156","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 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/A5081259452","display_name":"Jian-Lai Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Jian-lai Zhou","raw_affiliation_strings":["Microsoft Research Asia, China","[Microsoft Research Asia, CHINA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"[Microsoft Research Asia, CHINA]","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101883911","display_name":"Ye Tian","orcid":"https://orcid.org/0000-0002-6846-5141"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Ye Tian","raw_affiliation_strings":["Microsoft Research Asia, China","[Microsoft Research Asia, CHINA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"[Microsoft Research Asia, CHINA]","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081782546","display_name":"Yu Shi","orcid":"https://orcid.org/0000-0002-9392-7176"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Yu Shi","raw_affiliation_strings":["Microsoft Research Asia, China","[Microsoft Research Asia, CHINA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"[Microsoft Research Asia, CHINA]","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101528012","display_name":"Chao Huang","orcid":"https://orcid.org/0000-0003-4995-1002"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Chao Huang","raw_affiliation_strings":["Microsoft Research Asia, China","[Microsoft Research Asia, CHINA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"[Microsoft Research Asia, CHINA]","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087298985","display_name":"Eric Chang","orcid":"https://orcid.org/0000-0002-9678-5994"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"E. Chang","raw_affiliation_strings":["Microsoft Research Asia, China","[Microsoft Research Asia, CHINA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"[Microsoft Research Asia, CHINA]","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.4408,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.928041,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"997"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8246986865997314},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.7958801984786987},{"id":"https://openalex.org/keywords/tone","display_name":"Tone (literature)","score":0.7749572992324829},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.731803834438324},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6197618842124939},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4773947596549988},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4770236015319824},{"id":"https://openalex.org/keywords/articulation","display_name":"Articulation (sociology)","score":0.4575999081134796},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33108681440353394},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07748100161552429}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8246986865997314},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.7958801984786987},{"id":"https://openalex.org/C2780583480","wikidata":"https://www.wikidata.org/wiki/Q1366327","display_name":"Tone (literature)","level":2,"score":0.7749572992324829},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.731803834438324},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6197618842124939},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4773947596549988},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4770236015319824},{"id":"https://openalex.org/C2779337067","wikidata":"https://www.wikidata.org/wiki/Q4800961","display_name":"Articulation (sociology)","level":3,"score":0.4575999081134796},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33108681440353394},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07748100161552429},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"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},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2004.1326156","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326156","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.187.8987","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.187.8987","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/en-us/groups/speech/0100997.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5199999809265137,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W50577135","https://openalex.org/W108550785","https://openalex.org/W188468770","https://openalex.org/W1580270414","https://openalex.org/W1590403649","https://openalex.org/W1648698152","https://openalex.org/W1649178199","https://openalex.org/W2038979817","https://openalex.org/W2100441082","https://openalex.org/W2126289105","https://openalex.org/W2144171336","https://openalex.org/W6604322312","https://openalex.org/W6607571037","https://openalex.org/W6637086781","https://openalex.org/W6674890362"],"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/W2163874654","https://openalex.org/W156219719","https://openalex.org/W2365805939","https://openalex.org/W2287147624"],"abstract_inverted_index":{"Tone":[0,83],"modeling":[1],"is":[2,21,116,122],"an":[3],"unavoidable":[4],"problem":[5],"in":[6,42,97,173,177],"Mandarin":[7,43],"speech":[8,45,118],"recognition.":[9],"In":[10,72],"continuous":[11,44,98],"speech,":[12,135],"the":[13,37,58,62,67,120,130,136,155,168,174],"pitch":[14,92],"contour":[15],"exhibits":[16],"variable":[17],"patterns,":[18],"and":[19],"it":[20],"strongly":[22],"influenced":[23],"by":[24,52,95],"its":[25],"tone":[26,54,80,146],"context.":[27],"Although":[28],"several":[29],"effective":[30,144],"methods":[31,108],"have":[32,164],"been":[33],"proposed":[34,137,169],"to":[35,89,141,166],"improve":[36,167],"accuracy":[38],"for":[39,66,129,154],"tonal":[40],"syllables":[41],"recognition,":[46],"many":[47],"recognition":[48,68],"errors":[49],"are":[50,87,103,109,152,171],"caused":[51,94],"poor":[53],"discrimination":[55],"capability":[56],"of":[57,69,133,158],"acoustic":[59,101],"model.":[60],"Furthermore,":[61],"case":[63],"becomes":[64],"worse":[65],"spontaneous":[70],"speech.":[71,99,160],"this":[73,178],"paper,":[74],"we":[75],"report":[76],"our":[77],"work":[78],"on":[79,111],"articulation":[81],"modeling.":[82],"context":[84,147],"dependent":[85],"models":[86],"used":[88],"model":[90],"unstable":[91],"patterns":[93],"co-articulation":[96],"Corresponding":[100],"features":[102],"investigated":[104],"as":[105],"well.":[106],"Our":[107],"evaluated":[110],"two":[112],"test":[113,131,156],"sets:":[114],"one":[115],"reading-style":[117,159],"data,":[119],"other":[121],"spontaneous.":[123],"The":[124],"experimental":[125],"results":[126],"show":[127],"that":[128],"set":[132,157],"casual":[134],"method":[138,170],"turns":[139],"out":[140],"be":[142],"more":[143],"than":[145],"independent":[148],"model,":[149],"while":[150],"they":[151],"comparable":[153],"Several":[161],"factors":[162],"which":[163],"potential":[165],"discussed":[172],"final":[175],"part":[176],"paper.":[179]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}