{"id":"https://openalex.org/W4283076240","doi":"https://doi.org/10.21437/interspeech.2022-10005","title":"Automatic Prosody Annotation with Pre-Trained Text-Speech Model","display_name":"Automatic Prosody Annotation with Pre-Trained Text-Speech Model","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4283076240","doi":"https://doi.org/10.21437/interspeech.2022-10005"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10005","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10005","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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/A5022038123","display_name":"Ziqian Dai","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ziqian Dai","raw_affiliation_strings":["Tencent AI Lab,","Peking University"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102286496","display_name":"Jianwei Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianwei Yu","raw_affiliation_strings":["Tencent AI Lab,"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100322682","display_name":"Yan Wang","orcid":"https://orcid.org/0000-0002-3984-6973"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Wang","raw_affiliation_strings":["Tencent AI Lab,"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100740158","display_name":"Nuo Chen","orcid":"https://orcid.org/0000-0001-6563-1215"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nuo Chen","raw_affiliation_strings":["Peking University","Tencent AI Lab,"],"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Tencent AI Lab,","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017831085","display_name":"Yanyao Bian","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanyao Bian","raw_affiliation_strings":["Tencent AI Lab,"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039907074","display_name":"GuangZhi Li","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"GuangZhi Li","raw_affiliation_strings":["Tencent AI Lab,"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037942269","display_name":"Deng Cai","orcid":"https://orcid.org/0000-0001-9817-4065"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deng Cai","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":["Tencent AI Lab,"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5022038123"],"corresponding_institution_ids":["https://openalex.org/I20231570","https://openalex.org/I2250653659"],"apc_list":null,"apc_paid":null,"fwci":0.2086,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.39152093,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5513","last_page":"5517"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991000294685364,"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":0.7955976128578186},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.7929989099502563},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.7816298007965088},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.658282995223999},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6216418743133545},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5666635632514954}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7955976128578186},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.7929989099502563},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7816298007965088},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.658282995223999},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6216418743133545},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5666635632514954}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10005","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10005","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2164777277","https://openalex.org/W2194775991","https://openalex.org/W2518172956","https://openalex.org/W2794490148","https://openalex.org/W2861969375","https://openalex.org/W2896457183","https://openalex.org/W2937297115","https://openalex.org/W2972881244","https://openalex.org/W2972956685","https://openalex.org/W2973000405","https://openalex.org/W2973190645","https://openalex.org/W3010888783","https://openalex.org/W3011931830","https://openalex.org/W3015841236","https://openalex.org/W3021733045","https://openalex.org/W3092028330","https://openalex.org/W3097538987","https://openalex.org/W3097777922","https://openalex.org/W3148096012","https://openalex.org/W3163738228","https://openalex.org/W3168542456","https://openalex.org/W4213423981","https://openalex.org/W4287547221","https://openalex.org/W4291566970"],"related_works":["https://openalex.org/W2361861616","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W2218034408","https://openalex.org/W2392921965","https://openalex.org/W2355553914","https://openalex.org/W2358755282","https://openalex.org/W149862513","https://openalex.org/W2347684782","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Prosodic":[0],"boundary":[1,20,39,103],"plays":[2],"an":[3],"important":[4],"role":[5],"in":[6,10,68],"text-to-speech":[7],"synthesis":[8],"(TTS)":[9],"terms":[11],"of":[12,18,100],"naturalness":[13],"and":[14,29,58,62,81],"readability.However,":[15],"the":[16,87,98],"acquisition":[17],"prosodic":[19,38,102],"labels":[21,40],"relies":[22],"on":[23,56,65,77],"manual":[24,124],"annotation,":[25],"which":[26],"is":[27,54,105,126],"costly":[28],"time-consuming.In":[30],"this":[31],"paper,":[32],"we":[33],"propose":[34],"to":[35,107],"automatically":[36],"extract":[37],"from":[41],"text-audio":[42],"data":[43,60,67],"via":[44],"a":[45,69],"neural":[46],"text-speech":[47,89],"model":[48,53],"with":[49,114],"pre-trained":[50,55],"audio":[51],"encoders.This":[52],"text":[57],"speech":[59],"separately":[61],"jointly":[63],"fine-tuned":[64],"TTS":[66,111],"triplet":[70],"format:":[71],"{speech,":[72],"text,":[73],"prosody}.The":[74],"experimental":[75],"results":[76],"both":[78],"automatic":[79,101],"evaluation":[80,83],"human":[82,108],"demonstrate":[84],"that:":[85],"1)":[86],"proposed":[88],"prosody":[90],"annotation":[91],"framework":[92],"significantly":[93],"outperforms":[94],"text-only":[95],"baselines;":[96],"2)":[97],"quality":[99],"annotations":[104],"comparable":[106],"annotations;":[109],"3)":[110],"systems":[112,121],"trained":[113],"model-annotated":[115],"boundaries":[116],"are":[117],"slightly":[118],"better":[119],"than":[120],"that":[122],"use":[123],"ones.Code":[125],"released":[127],"1":[128],".":[129]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}