{"id":"https://openalex.org/W4385696300","doi":"https://doi.org/10.1109/taslp.2023.3301235","title":"Adversarial Multi-Task Learning for Mandarin Prosodic Boundary Prediction With Multi-Modal Embeddings","display_name":"Adversarial Multi-Task Learning for Mandarin Prosodic Boundary Prediction With Multi-Modal Embeddings","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4385696300","doi":"https://doi.org/10.1109/taslp.2023.3301235"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3301235","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/taslp.2023.3301235","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/A5078525423","display_name":"Jiangyan Yi","orcid":"https://orcid.org/0000-0003-2422-4618"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangyan Yi","raw_affiliation_strings":["State Key Laboratory of Multimodal Arcial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2422-4618","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Arcial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112613657","display_name":"Jianhua Tao","orcid":"https://orcid.org/0000-0002-9344-6428"},"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"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhua Tao","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China","School of Artificial Intelligence,, University of Sciences and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-9344-6428","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"School of Artificial Intelligence,, University of Sciences and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073918837","display_name":"Ruibo Fu","orcid":"https://orcid.org/0000-0001-9598-1881"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruibo Fu","raw_affiliation_strings":["State Key Laboratory of Multimodal Arcial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9598-1881","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Arcial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071038184","display_name":"Tao Wang","orcid":"https://orcid.org/0000-0003-1490-6973"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Wang","raw_affiliation_strings":["State Key Laboratory of Multimodal Arcial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1490-6973","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Arcial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026641664","display_name":"Chu Yuan Zhang","orcid":"https://orcid.org/0009-0006-3461-3034"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chu Yuan Zhang","raw_affiliation_strings":["State Key Laboratory of Multimodal Arcial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-3461-3034","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Arcial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004011841","display_name":"Chenglong Wang","orcid":"https://orcid.org/0000-0002-5785-7027"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenglong Wang","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5785-7027","affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3173,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.62273378,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"31","issue":null,"first_page":"2963","last_page":"2973"},"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":0.9980999827384949,"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":0.9977999925613403,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6914008855819702},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.5969217419624329},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5606339573860168},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5450045466423035},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5384357571601868},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.5384113788604736},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5095186829566956},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5031558871269226},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4897587299346924},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.42490154504776},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.13841351866722107},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08074316382408142}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6914008855819702},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.5969217419624329},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5606339573860168},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5450045466423035},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5384357571601868},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.5384113788604736},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5095186829566956},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5031558871269226},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4897587299346924},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.42490154504776},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13841351866722107},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08074316382408142},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2023.3301235","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/taslp.2023.3301235","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":[{"id":"https://metadata.un.org/sdg/4","score":0.7300000190734863,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1202467192","display_name":null,"funder_award_id":"U21B2010","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1448168285","display_name":null,"funder_award_id":"62276259","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4754633920","display_name":"\u57fa\u4e8e\u7a7a\u95f4\u91c7\u6837\u4e0e\u6df1\u5ea6\u611f\u77e5\u878d\u5408\u7b56\u7565\u7684\u8bed\u97f3\u5206\u79bb\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61971419","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5381013183","display_name":null,"funder_award_id":"61831022","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7270707897","display_name":null,"funder_award_id":"62206278","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7853071381","display_name":null,"funder_award_id":"62101553","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7925330915","display_name":null,"funder_award_id":"62006223","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8569810394","display_name":null,"funder_award_id":"62201572","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/F4320325902","display_name":"Beijing Municipal Science and Technology Commission","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":69,"referenced_works":["https://openalex.org/W28194048","https://openalex.org/W287031571","https://openalex.org/W1522301498","https://openalex.org/W1614298861","https://openalex.org/W1731081199","https://openalex.org/W1882958252","https://openalex.org/W1991148915","https://openalex.org/W2112235095","https://openalex.org/W2125689567","https://openalex.org/W2131417696","https://openalex.org/W2146423738","https://openalex.org/W2159372275","https://openalex.org/W2165698076","https://openalex.org/W2184170932","https://openalex.org/W2185964918","https://openalex.org/W2254292464","https://openalex.org/W2400229727","https://openalex.org/W2511062022","https://openalex.org/W2794490148","https://openalex.org/W2794753807","https://openalex.org/W2795109282","https://openalex.org/W2889048668","https://openalex.org/W2889523925","https://openalex.org/W2895351178","https://openalex.org/W2896457183","https://openalex.org/W2906459023","https://openalex.org/W2913340405","https://openalex.org/W2937297115","https://openalex.org/W2939069254","https://openalex.org/W2953384591","https://openalex.org/W2962897020","https://openalex.org/W2963078821","https://openalex.org/W2963091184","https://openalex.org/W2963355640","https://openalex.org/W2963425185","https://openalex.org/W2963609956","https://openalex.org/W2963807318","https://openalex.org/W2964243274","https://openalex.org/W2969521066","https://openalex.org/W2972417954","https://openalex.org/W2972956685","https://openalex.org/W3094002217","https://openalex.org/W3094630302","https://openalex.org/W3096831136","https://openalex.org/W3113850747","https://openalex.org/W3143635792","https://openalex.org/W3174758275","https://openalex.org/W3196875702","https://openalex.org/W4225326644","https://openalex.org/W4295731579","https://openalex.org/W4385245566","https://openalex.org/W6610416351","https://openalex.org/W6629843454","https://openalex.org/W6631190155","https://openalex.org/W6636510571","https://openalex.org/W6637618735","https://openalex.org/W6639480849","https://openalex.org/W6676622279","https://openalex.org/W6679705213","https://openalex.org/W6691808304","https://openalex.org/W6713134421","https://openalex.org/W6739901393","https://openalex.org/W6750489868","https://openalex.org/W6754473786","https://openalex.org/W6755207826","https://openalex.org/W6785090365","https://openalex.org/W6788095661","https://openalex.org/W6796730497","https://openalex.org/W7062423369"],"related_works":["https://openalex.org/W2029561777","https://openalex.org/W172797710","https://openalex.org/W3165080709","https://openalex.org/W2945105049","https://openalex.org/W2626699140","https://openalex.org/W2909357361","https://openalex.org/W4387098302","https://openalex.org/W4288365855","https://openalex.org/W2948317131","https://openalex.org/W2111961547"],"abstract_inverted_index":{"Prosodic":[0],"boundaries":[1],"are":[2,48],"still":[3],"crucial":[4],"to":[5,16,21,30,39,116,124,168],"the":[6,59,91,94,101,106,119,136,142,148,156],"naturalness":[7],"of":[8,50,80],"end-to-end":[9],"speech":[10,54,84],"synthesis":[11],"systems.":[12],"This":[13],"article":[14],"proposes":[15],"use":[17,100],"adversarial":[18,160],"multi-task":[19,26],"learning":[20,27],"predict":[22],"prosodic":[23,41,87,95,120],"boundaries.":[24],"Adversarial":[25],"is":[28],"utilized":[29],"transfer":[31],"knowledge":[32],"from":[33,58,64,77,105,141],"an":[34],"auxiliary":[35],"POS":[36,107],"tagging":[37,108],"task":[38,109,123],"a":[40],"boundary":[42,88,96,121],"prediction":[43],"task.":[44],"Furthermore,":[45,155],"multi-modal":[46,139],"embeddings":[47,140],"composed":[49],"contextual":[51],"word":[52],"and":[53,68,74,83,145],"embedding":[55],"features":[56,103],"obtained":[57],"pre-trained":[60,143],"bidirectional":[61],"encoder":[62],"representations":[63],"transformers":[65],"(BERT)":[66],"model":[67,98],"Speech2Vec.":[69],"We":[70,126],"can":[71,99],"utilize":[72],"linguistic":[73],"acoustic":[75],"information":[76],"large":[78],"amounts":[79],"external":[81],"text":[82],"data":[85],"without":[86,110],"labels.":[89],"At":[90],"inference":[92],"stage,":[93],"predicting":[97,122],"syntactic":[102],"learnt":[104],"any":[111],"extra":[112],"computation":[113],"cost":[114],"due":[115],"only":[117],"employing":[118],"decode.":[125],"conducted":[127],"experiments":[128],"on":[129],"Mandarin":[130],"datasets.":[131],"The":[132],"results":[133],"show":[134],"that":[135],"models":[137,149,157],"using":[138],"BERT":[144],"Speech2Vec":[146],"outperform":[147],"trained":[150,158],"with":[151,159],"single":[152],"modal":[153],"embedding.":[154],"training":[161],"obtain":[162],"further":[163],"performance":[164],"gains":[165],"by":[166],"up":[167],"2.95%":[169],"in":[170],"<inline-formula":[171],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[172],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[173],"notation=\"LaTeX\">$F_{1}$</tex-math></inline-formula>":[174],"score.":[175]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}