{"id":"https://openalex.org/W2398699645","doi":"https://doi.org/10.21437/interspeech.2012-159","title":"Hierarchical English emphatic speech synthesis based on HMM with limited training data","display_name":"Hierarchical English emphatic speech synthesis based on HMM with limited training data","publication_year":2012,"publication_date":"2012-09-09","ids":{"openalex":"https://openalex.org/W2398699645","doi":"https://doi.org/10.21437/interspeech.2012-159","mag":"2398699645"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2012-159","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-159","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","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/A5100705251","display_name":"Fanbo Meng","orcid":"https://orcid.org/0000-0002-1356-445X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Fanbo Meng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102869280","display_name":"Zhiyong Wu","orcid":"https://orcid.org/0000-0001-8533-0524"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiyong Wu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100405572","display_name":"Jia Jia","orcid":"https://orcid.org/0000-0002-7336-4003"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jia Jia","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5053661520","display_name":"Lianhong Cai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lianhong Cai","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100705251"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7125,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.87325725,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"466","last_page":"469"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9983999729156494,"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":0.9937999844551086,"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/naturalness","display_name":"Naturalness","score":0.9417459964752197},{"id":"https://openalex.org/keywords/emphasis","display_name":"Emphasis (telecommunications)","score":0.9039599895477295},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.8174906969070435},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8138707876205444},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6165381669998169},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5418072938919067},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.514137327671051},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4771363437175751},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.4389404356479645},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3372342586517334},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07247787714004517}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.9417459964752197},{"id":"https://openalex.org/C177454536","wikidata":"https://www.wikidata.org/wiki/Q578290","display_name":"Emphasis (telecommunications)","level":2,"score":0.9039599895477295},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8174906969070435},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8138707876205444},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6165381669998169},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5418072938919067},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.514137327671051},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4771363437175751},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.4389404356479645},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3372342586517334},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07247787714004517},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2012-159","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-159","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W1963627370","https://openalex.org/W2048389584","https://openalex.org/W2146871184","https://openalex.org/W2154280657","https://openalex.org/W2400063444"],"related_works":["https://openalex.org/W4391272374","https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W40885451","https://openalex.org/W2108985546","https://openalex.org/W2081919107","https://openalex.org/W2433276473","https://openalex.org/W1537411440","https://openalex.org/W1984347656","https://openalex.org/W2535215250"],"abstract_inverted_index":{"Emphasis":[0],"is":[1,129,148],"an":[2],"important":[3],"form":[4],"of":[5,38,50,72,111,120,177],"expressiveness":[6],"in":[7,20,68,88,116,136],"speech.":[8,23],"Hidden":[9],"Markov":[10],"model":[11,29,147,161],"(HMM)":[12],"based":[13,30,125],"speech":[14,37,165],"synthesis":[15],"has":[16],"shown":[17],"great":[18],"flexibility":[19],"generating":[21],"expressive":[22],"This":[24],"paper":[25],"proposes":[26],"a":[27,123,133,145],"hierarchical":[28,160],"on":[31,126],"HMMs":[32],"aiming":[33],"at":[34],"synthesizing":[35],"emphatic":[36,164],"both":[39,61,170],"high":[40,44,167],"emphasis":[41,64,79,91,114],"quality":[42,168],"and":[43,63,98,172],"naturalness":[45,171],"with":[46,57,166],"the":[47,73,83,89,117,121,137,152,158],"limited":[48,175],"amount":[49,176],"data.":[51,179],"Decision":[52],"trees":[53],"(DTs)":[54],"are":[55,75,93,99],"constructed":[56],"non-emphasis-related":[58],"questions":[59],"using":[60,174],"neutral":[62],"corpora.":[65],"The":[66,86],"data":[67,87,110],"each":[69],"leaf":[70,118,139],"node":[71,140],"DTs":[74],"classified":[76],"into":[77,95],"6":[78],"categories":[80,115],"according":[81],"to":[82,101,131,150],"emphasis-related":[84],"questions.":[85],"same":[90,138],"category":[92],"grouped":[94],"one":[96,103],"sub-node":[97],"used":[100],"train":[102],"HMM.":[104],"As":[105],"there":[106],"might":[107],"be":[108],"no":[109],"some":[112],"specific":[113],"nodes":[119],"DTs,":[122],"method":[124],"cost":[127],"calculation":[128],"proposed":[130,149,159],"select":[132],"suitable":[134],"HMM":[135],"for":[141,169],"predicting":[142],"parameters.":[143,154],"Further":[144],"compensation":[146],"adjust":[151],"predicted":[153],"Experiments":[155],"show":[156],"that":[157],"can":[162],"synthesize":[163],"emphasis,":[173],"training":[178]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}