{"id":"https://openalex.org/W3158374895","doi":"https://doi.org/10.1109/taslp.2021.3074757","title":"Extracting and Predicting Word-Level Style Variations for Speech Synthesis","display_name":"Extracting and Predicting Word-Level Style Variations for Speech Synthesis","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3158374895","doi":"https://doi.org/10.1109/taslp.2021.3074757","mag":"3158374895"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2021.3074757","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3074757","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5100430526","display_name":"Yajie Zhang","orcid":"https://orcid.org/0000-0002-9916-080X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ya-Jie Zhang","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059767940","display_name":"Zhen-Hua Ling","orcid":"https://orcid.org/0000-0001-7853-5273"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen-Hua Ling","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-7853-5273","affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":1.9108,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.87947789,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"29","issue":null,"first_page":"1582","last_page":"1593"},"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":0.9966999888420105,"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/T10028","display_name":"Topic Modeling","score":0.993399977684021,"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/computer-science","display_name":"Computer science","score":0.8052765130996704},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.7213848829269409},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.557174801826477},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5158030986785889},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.5067489743232727},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.49014267325401306},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.45080748200416565},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4389286935329437},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3947148621082306},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3250318169593811},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.125969797372818}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8052765130996704},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7213848829269409},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.557174801826477},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5158030986785889},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.5067489743232727},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.49014267325401306},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.45080748200416565},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4389286935329437},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3947148621082306},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3250318169593811},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.125969797372818},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2021.3074757","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3074757","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5799999833106995,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G3288249144","display_name":null,"funder_award_id":"2019YFF0303001","funder_id":"https://openalex.org/F4320336026","funder_display_name":"National Key Research and Development Program of China Stem Cell and Translational Research"},{"id":"https://openalex.org/G8663906801","display_name":"\u9762\u5411\u8bed\u97f3\u5408\u6210\u7684\u795e\u7ecf\u7f51\u7edc\u58f0\u7801\u5668\u7814\u7a76","funder_award_id":"61871358","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320336026","display_name":"National Key Research and Development Program of China Stem Cell and Translational Research","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":98,"referenced_works":["https://openalex.org/W24795087","https://openalex.org/W38285298","https://openalex.org/W59470279","https://openalex.org/W73525854","https://openalex.org/W113106864","https://openalex.org/W188951208","https://openalex.org/W1522301498","https://openalex.org/W1584787447","https://openalex.org/W1586037671","https://openalex.org/W1599623585","https://openalex.org/W1959608418","https://openalex.org/W2030438891","https://openalex.org/W2049686551","https://openalex.org/W2053154970","https://openalex.org/W2064675550","https://openalex.org/W2088009352","https://openalex.org/W2102003408","https://openalex.org/W2111284386","https://openalex.org/W2119929864","https://openalex.org/W2133148365","https://openalex.org/W2144054949","https://openalex.org/W2150658333","https://openalex.org/W2151499469","https://openalex.org/W2154920538","https://openalex.org/W2157331557","https://openalex.org/W2168531172","https://openalex.org/W2330979245","https://openalex.org/W2394761397","https://openalex.org/W2395980997","https://openalex.org/W2402144811","https://openalex.org/W2519091744","https://openalex.org/W2785978752","https://openalex.org/W2794490148","https://openalex.org/W2795109282","https://openalex.org/W2797310469","https://openalex.org/W2885800352","https://openalex.org/W2896457183","https://openalex.org/W2901997113","https://openalex.org/W2903739847","https://openalex.org/W2904459034","https://openalex.org/W2946200149","https://openalex.org/W2950151997","https://openalex.org/W2953384591","https://openalex.org/W2963272440","https://openalex.org/W2963341956","https://openalex.org/W2963568578","https://openalex.org/W2963609956","https://openalex.org/W2963691546","https://openalex.org/W2963927338","https://openalex.org/W2963975282","https://openalex.org/W2964121744","https://openalex.org/W2964138190","https://openalex.org/W2964243274","https://openalex.org/W2964307104","https://openalex.org/W2970730223","https://openalex.org/W2972881244","https://openalex.org/W2973158936","https://openalex.org/W2973217961","https://openalex.org/W2977728465","https://openalex.org/W2980708516","https://openalex.org/W3015282541","https://openalex.org/W3015338123","https://openalex.org/W3015440759","https://openalex.org/W3016137096","https://openalex.org/W3096442195","https://openalex.org/W3097538987","https://openalex.org/W3141224548","https://openalex.org/W3142087749","https://openalex.org/W3168542456","https://openalex.org/W4289383906","https://openalex.org/W4295731579","https://openalex.org/W4298580827","https://openalex.org/W4391602018","https://openalex.org/W4395962053","https://openalex.org/W6601598784","https://openalex.org/W6602426571","https://openalex.org/W6604530167","https://openalex.org/W6607761755","https://openalex.org/W6631190155","https://openalex.org/W6640963894","https://openalex.org/W6675380101","https://openalex.org/W6681953571","https://openalex.org/W6712034360","https://openalex.org/W6713134421","https://openalex.org/W6729448088","https://openalex.org/W6736996214","https://openalex.org/W6748409065","https://openalex.org/W6749489859","https://openalex.org/W6750489868","https://openalex.org/W6753855596","https://openalex.org/W6755207826","https://openalex.org/W6755300632","https://openalex.org/W6756197946","https://openalex.org/W6759121725","https://openalex.org/W6763832098","https://openalex.org/W6781784828","https://openalex.org/W6789468613","https://openalex.org/W6865530009"],"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/W2535215250","https://openalex.org/W1813881148","https://openalex.org/W1537411440"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,31,35,45,51,124],"speech":[4,175,215],"synthesis":[5],"method":[6,208],"based":[7],"on":[8],"unsupervisedly-learned":[9],"fine-grained":[10],"style":[11,15,69,95,221],"representations,":[12],"named":[13],"word-level":[14,88],"variations":[16],"(WSVs),":[17],"in":[18,61],"order":[19],"to":[20,75,92,111,144,162],"improve":[21],"the":[22,55,62,67,80,106,116,129,160,164,173,187,193,199],"naturalness":[23,212],"of":[24,57,83,131,167,189,195,213],"synthetic":[25,214],"speech.":[26],"The":[27,38,120,179],"whole":[28],"model":[29,126,156],"contains":[30],"WSV":[32,36,39,52,121,132,180,190],"extractor":[33,40],"and":[34,49,89,105,192,224],"predictor.":[37],"is":[41,103,123,157,182],"jointly":[42],"trained":[43,183],"with":[44],"sequence-to-sequence":[46],"(Seq2seq)":[47],"synthesizer":[48],"learns":[50],"vector":[53],"from":[54,134,153,198],"mel-spectrogram":[56],"each":[58],"prosodic":[59],"word":[60],"training":[63],"set":[64],"by":[65,159,184],"extending":[66],"global":[68,81,220],"token":[70,222],"(GST)":[71],"framework.":[72],"In":[73,142],"contrast":[74],"GST":[76],"weights":[77],"which":[78,114,127],"describe":[79,93],"styles":[82],"utterances,":[84],"WSVs":[85,108],"operate":[86],"at":[87],"are":[90,109],"expected":[91],"local":[94],"properties,":[96],"such":[97],"as":[98],"stresses.":[99],"Besides,":[100],"Gumbel":[101],"softmax":[102],"adopted":[104],"extracted":[107],"close":[110],"one-hot":[112],"vectors":[113,133],"facilitate":[115],"subsequent":[117],"prediction":[118,191],"task.":[119],"predictor":[122,161,181],"deterministic":[125],"generates":[128],"sequence":[130],"input":[135,168],"text":[136,169],"using":[137],"an":[138],"autoregressive":[139],"LSTM":[140],"network.":[141],"addition":[143],"phonetic":[145],"information,":[146],"e.g.,":[147],"phoneme":[148],"sequences,":[149],"Bidirectional":[150],"Encoder":[151],"Representation":[152],"Transformers":[154],"(BERT)":[155],"employed":[158],"obtain":[163],"semantic":[165],"descriptions":[166],"for":[170],"better":[171,211],"predicting":[172],"latent":[174],"representation,":[176],"i.e.,":[177],"WSVs.":[178,201],"considering":[185],"both":[186],"accuracy":[188],"distortion":[194],"mel-spectrograms":[196],"recovered":[197],"predicted":[200],"Experimental":[202],"results":[203],"show":[204],"that":[205],"our":[206],"proposed":[207],"can":[209],"achieve":[210],"than":[216],"baseline":[217],"Tacotron2,":[218],"text-predicted":[219],"(TP-GST)":[223],"BERT-Tacotron2":[225],"models.":[226]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}