{"id":"https://openalex.org/W2162122872","doi":"https://doi.org/10.1109/icassp.2003.1198831","title":"Automatic prosody labeling using both text and acoustic information","display_name":"Automatic prosody labeling using both text and acoustic information","publication_year":2003,"publication_date":"2003-11-20","ids":{"openalex":"https://openalex.org/W2162122872","doi":"https://doi.org/10.1109/icassp.2003.1198831","mag":"2162122872"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2003.1198831","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1198831","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":"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/A5007142915","display_name":"MA Xi-jun","orcid":null},"institutions":[{"id":"https://openalex.org/I4210126794","display_name":"IBM Research (China)","ror":"https://ror.org/02yg1pf55","country_code":"CN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126794"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xijun Ma","raw_affiliation_strings":["IBM China Research Laboratory, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM China Research Laboratory, China","institution_ids":["https://openalex.org/I4210126794"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wei Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210126794","display_name":"IBM Research (China)","ror":"https://ror.org/02yg1pf55","country_code":"CN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126794"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zhang","raw_affiliation_strings":["IBM China Research Laboratory, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM China Research Laboratory, China","institution_ids":["https://openalex.org/I4210126794"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100736302","display_name":"Qin Shi","orcid":"https://orcid.org/0000-0002-9608-0345"},"institutions":[{"id":"https://openalex.org/I4210126794","display_name":"IBM Research (China)","ror":"https://ror.org/02yg1pf55","country_code":"CN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126794"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qin Shi","raw_affiliation_strings":["IBM China Research Laboratory, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM China Research Laboratory, China","institution_ids":["https://openalex.org/I4210126794"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102492475","display_name":"Weibin Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210126794","display_name":"IBM Research (China)","ror":"https://ror.org/02yg1pf55","country_code":"CN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126794"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weibin Zhu","raw_affiliation_strings":["IBM China Research Laboratory, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM China Research Laboratory, China","institution_ids":["https://openalex.org/I4210126794"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064116114","display_name":"Liqin Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210126794","display_name":"IBM Research (China)","ror":"https://ror.org/02yg1pf55","country_code":"CN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126794"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liqin Shen","raw_affiliation_strings":["IBM China Research Laboratory, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM China Research Laboratory, China","institution_ids":["https://openalex.org/I4210126794"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8343,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.74691992,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"516"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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/T12031","display_name":"Speech and dialogue systems","score":0.9977999925613403,"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":0.9968000054359436,"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/prosody","display_name":"Prosody","score":0.941261887550354},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7805215120315552},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6169840693473816},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6013932824134827},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5335332155227661},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.4638313055038452},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.45247331261634827},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.44562941789627075},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.43728557229042053},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.4136996567249298},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14212995767593384}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.941261887550354},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7805215120315552},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6169840693473816},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6013932824134827},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5335332155227661},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.4638313055038452},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.45247331261634827},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.44562941789627075},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.43728557229042053},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.4136996567249298},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14212995767593384},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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":1,"locations":[{"id":"doi:10.1109/icassp.2003.1198831","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1198831","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"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7599999904632568,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W35180317","https://openalex.org/W162654330","https://openalex.org/W178114869","https://openalex.org/W2166820052","https://openalex.org/W2543721542","https://openalex.org/W2545872914","https://openalex.org/W6601403084","https://openalex.org/W6606697926"],"related_works":["https://openalex.org/W10581632","https://openalex.org/W1927421023","https://openalex.org/W3149582125","https://openalex.org/W1984347656","https://openalex.org/W2169632867","https://openalex.org/W2465421051","https://openalex.org/W652196294","https://openalex.org/W2368700418","https://openalex.org/W1965141925","https://openalex.org/W2587342322"],"abstract_inverted_index":{"Prosody":[0],"is":[1,14,29,47,68,78,94,117,122],"an":[2,73],"important":[3,31],"factor":[4],"for":[5,130],"a":[6,18,115],"high":[7],"quality":[8],"text-to-speech":[9],"(TTS)":[10],"system.":[11,134],"The":[12],"prosody":[13,27,44,75,120,141],"often":[15],"described":[16],"with":[17],"hierarchical":[19,26],"structure.":[20],"So":[21],"the":[22,25,34,38,43,55,62,82,97,101,106,111,126,139],"generation":[23],"of":[24,114],"structure":[28],"very":[30],"both":[32],"in":[33,65,80],"corpus":[35,129],"building":[36],"and":[37,49,60,91],"run-time":[39],"text":[40,107],"analysis.":[41],"But":[42],"labeling":[45,76,142],"procedure":[46],"laborious":[48],"time":[50,67],"consuming.":[51],"Moreover,":[52],"to":[53],"keep":[54],"consistence":[56],"between":[57],"different":[58,66],"labelers":[59],"even":[61],"same":[63],"labeler":[64],"difficult.":[69],"In":[70,96],"this":[71],"paper":[72],"automatic":[74,140],"system":[77,143],"presented,":[79],"which":[81],"decision":[83],"tree":[84],"plus":[85],"Viterbi":[86],"decoding":[87],"framework":[88],"proposed":[89],"Wightman":[90],"Ostendorf":[92],"(1994)":[93],"used.":[95,118],"system,":[98],"not":[99],"only":[100],"acoustic":[102],"information":[103,108],"but":[104],"also":[105],"such":[109],"as":[110],"part-of-speech":[112],"(POS)":[113],"word":[116],"A":[119],"model":[121],"built":[123],"up":[124],"using":[125],"automatically":[127],"labeled":[128],"our":[131],"Mandarin":[132],"TTS":[133],"Listening":[135],"test":[136],"shows":[137],"that":[138],"works":[144],"pretty":[145],"well.":[146]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}