{"id":"https://openalex.org/W2160899562","doi":"https://doi.org/10.1109/icassp.2004.1325933","title":"Tone recognition with fractionized models and outlined features","display_name":"Tone recognition with fractionized models and outlined features","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https://openalex.org/W2160899562","doi":"https://doi.org/10.1109/icassp.2004.1325933","mag":"2160899562"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2004.1325933","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1325933","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":"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/A5101841900","display_name":"Tian Ye","orcid":"https://orcid.org/0009-0008-6106-0388"},"institutions":[{"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"],"is_corresponding":false,"raw_author_name":"Ye Tian","raw_affiliation_strings":["Microsoft Research Asia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081259452","display_name":"Jian-Lai Zhou","orcid":null},"institutions":[{"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"],"is_corresponding":false,"raw_author_name":"Jian-Lai Zhou","raw_affiliation_strings":["Microsoft Research Asia, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104229610","display_name":"Min Chu","orcid":null},"institutions":[{"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"],"is_corresponding":false,"raw_author_name":"Min Chu","raw_affiliation_strings":["Microsoft Research Asia, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"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/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"],"is_corresponding":false,"raw_author_name":"E. Chang","raw_affiliation_strings":["Microsoft Research Asia, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":1.0376,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.7634987,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"105"},"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/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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":0.9987000226974487,"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/tone","display_name":"Tone (literature)","score":0.9052696228027344},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6912482976913452},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6830654740333557},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5567914247512817},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5326658487319946},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3858717679977417},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3810470402240753}],"concepts":[{"id":"https://openalex.org/C2780583480","wikidata":"https://www.wikidata.org/wiki/Q1366327","display_name":"Tone (literature)","level":2,"score":0.9052696228027344},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6912482976913452},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6830654740333557},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5567914247512817},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5326658487319946},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3858717679977417},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3810470402240753},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2004.1325933","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1325933","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W108550785","https://openalex.org/W1986822315","https://openalex.org/W1998414250","https://openalex.org/W2038979817","https://openalex.org/W2099247481","https://openalex.org/W2144171336","https://openalex.org/W2153728019","https://openalex.org/W2793631648","https://openalex.org/W6604322312","https://openalex.org/W6646791608"],"related_works":["https://openalex.org/W4386159726","https://openalex.org/W2601157893","https://openalex.org/W2131735617","https://openalex.org/W2373006798","https://openalex.org/W3190382492","https://openalex.org/W2056912418","https://openalex.org/W2123759770","https://openalex.org/W2033213769","https://openalex.org/W2811390910","https://openalex.org/W4312376745"],"abstract_inverted_index":{"Different":[0],"feature":[1],"extraction":[2],"and":[3,12,32,110],"tone":[4,54,59,84,103,133,157],"modeling":[5],"schemes":[6],"are":[7,113],"investigated":[8],"on":[9],"both":[10],"speaker-dependent":[11],"speaker-independent":[13,143],"continuous":[14],"speech":[15],"databases.":[16],"Tone":[17,44],"recognition":[18,139],"features":[19,25,34,88],"can":[20,135],"be":[21,116],"classified":[22],"as":[23],"detailed":[24,74],"which":[26,35],"use":[27],"the":[28,37,41,73,77,93,100,125,138,153],"entire":[29],"F0":[30,42,78,109],"curve,":[31],"outlined":[33,87,118,154],"capture":[36],"main":[38],"structure":[39],"of":[40,46,76,95,102],"curve.":[43],"models":[45,55,134],"different":[47,62],"size,":[48],"ranging":[49],"from":[50],"very":[51],"simple":[52],"one-tone-one-model":[53,126],"to":[56,64,115],"complex":[57],"phoneme-dependent":[58,132],"models,":[60,150],"have":[61],"abilities":[63],"characterize":[65],"tone.":[66],"Our":[67],"experiments":[68],"show":[69],"two":[70],"conclusions.":[71],"First,":[72],"information":[75],"curve":[79],"is":[80,123,128],"not":[81,90,129],"necessary":[82],"for":[83,142,156],"recognition.":[85,104,158],"The":[86,105,120],"can,":[89],"only":[91],"reduce":[92],"number":[94],"parameters,":[96],"but":[97],"also":[98],"improve":[99,137],"accuracy":[101],"proposed":[106],"subsection":[107],"average":[108],"/spl":[111],"Delta/F0":[112],"shown":[114],"effective":[117],"features.":[119],"second":[121],"conclusion":[122],"that":[124],"scheme":[127],"sufficient.":[130],"Building":[131],"highly":[136],"accuracy,":[140],"especially":[141],"data.":[144],"Thus":[145],"we":[146],"suggest":[147],"using":[148],"fractionized":[149],"trained":[151],"with":[152],"features,":[155]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2017,"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},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}