{"id":"https://openalex.org/W4372183701","doi":"https://doi.org/10.1109/icassp49357.2023.10096402","title":"Duration-Aware Pause Insertion Using Pre-Trained Language Model for Multi-Speaker Text-To-Speech","display_name":"Duration-Aware Pause Insertion Using Pre-Trained Language Model for Multi-Speaker Text-To-Speech","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372183701","doi":"https://doi.org/10.1109/icassp49357.2023.10096402"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096402","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096402","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100432277","display_name":"Dong Yang","orcid":"https://orcid.org/0000-0002-9907-395X"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Dong Yang","raw_affiliation_strings":["The University of Tokyo,Japan","The University of Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024181978","display_name":"Tomoki Koriyama","orcid":"https://orcid.org/0000-0002-8347-5604"},"institutions":[{"id":"https://openalex.org/I4210089607","display_name":"CyberAgent (Japan)","ror":"https://ror.org/0060jg679","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210089607"]},{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Koriyama","raw_affiliation_strings":["CyberAgent, Inc.,Japan","The University of Tokyo, Japan","CyberAgent, Inc., Japan"],"affiliations":[{"raw_affiliation_string":"CyberAgent, Inc.,Japan","institution_ids":["https://openalex.org/I4210089607"]},{"raw_affiliation_string":"The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"CyberAgent, Inc., Japan","institution_ids":["https://openalex.org/I4210089607"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042731264","display_name":"Yuki Saito","orcid":"https://orcid.org/0000-0002-4825-7783"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuki Saito","raw_affiliation_strings":["The University of Tokyo,Japan","The University of Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025983709","display_name":"Takaaki Saeki","orcid":"https://orcid.org/0000-0001-6003-768X"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takaaki Saeki","raw_affiliation_strings":["The University of Tokyo,Japan","The University of Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072398606","display_name":"Detai Xin","orcid":"https://orcid.org/0009-0007-1908-1137"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Detai Xin","raw_affiliation_strings":["The University of Tokyo,Japan","The University of Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003814223","display_name":"Hiroshi Saruwatari","orcid":"https://orcid.org/0000-0003-0876-5617"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Saruwatari","raw_affiliation_strings":["The University of Tokyo,Japan","The University of Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100432277"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.8741,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.77866662,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9994000196456909,"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":0.9983999729156494,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8083292245864868},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6880438327789307},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.532952606678009},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.48345550894737244},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.47510966658592224},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4323955178260803},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41416794061660767},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4054710268974304}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8083292245864868},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6880438327789307},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.532952606678009},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.48345550894737244},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.47510966658592224},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4323955178260803},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41416794061660767},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4054710268974304},{"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","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},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096402","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096402","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5699999928474426,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W21613951","https://openalex.org/W1522301498","https://openalex.org/W1522966007","https://openalex.org/W1566289585","https://openalex.org/W1614298861","https://openalex.org/W2079735306","https://openalex.org/W2086372363","https://openalex.org/W2153074916","https://openalex.org/W2162433174","https://openalex.org/W2176828964","https://openalex.org/W2293634267","https://openalex.org/W2395569613","https://openalex.org/W2395672826","https://openalex.org/W2512850563","https://openalex.org/W2513821485","https://openalex.org/W2526838772","https://openalex.org/W2747874407","https://openalex.org/W2749434195","https://openalex.org/W2896457183","https://openalex.org/W2963078821","https://openalex.org/W2972359262","https://openalex.org/W3026874504","https://openalex.org/W3033411150","https://openalex.org/W3092028330","https://openalex.org/W3197632081","https://openalex.org/W4296068767","https://openalex.org/W4390911892","https://openalex.org/W6603984341","https://openalex.org/W6631190155","https://openalex.org/W6636510571","https://openalex.org/W6682644134","https://openalex.org/W6696934422","https://openalex.org/W6755207826","https://openalex.org/W6777694618","https://openalex.org/W6778823374","https://openalex.org/W6783867762"],"related_works":["https://openalex.org/W3049463507","https://openalex.org/W2936497627","https://openalex.org/W4288365749","https://openalex.org/W3013624417","https://openalex.org/W4287826556","https://openalex.org/W4287598411","https://openalex.org/W3098382480","https://openalex.org/W3198458223","https://openalex.org/W4288267738","https://openalex.org/W3126642501"],"abstract_inverted_index":{"Pause":[0],"insertion,":[1,174],"also":[2,99],"known":[3],"as":[4],"phrase":[5],"break":[6],"prediction":[7,126,143],"and":[8,27,111,147,170,178,197,202],"phrasing,":[9],"is":[10,148,163],"an":[11],"essential":[12],"part":[13],"of":[14,29,41,50,115,127,154,199,205],"TTS":[15,168],"systems":[16],"because":[17],"proper":[18],"pauses":[19,129,133,180],"with":[20],"natural":[21,106],"duration":[22],"significantly":[23],"enhance":[24],"the":[25,48,51,124,152,158,195,203],"rhythm":[26,204],"intelligibility":[28],"synthetic":[30,206],"speech.":[31,207],"However,":[32],"conventional":[33,120],"phrasing":[34,121],"models":[35,122,169,193],"ignore":[36],"various":[37,95],"speakers\u2019":[38],"different":[39],"styles":[40],"inserting":[42],"silent":[43,132],"pauses,":[44],"which":[45],"can":[46],"degrade":[47],"performance":[49],"model":[52,162],"trained":[53],"on":[54,70,85,123,157],"a":[55,71,86],"multi-speaker":[56,107],"speech":[57],"corpus.":[58],"To":[59],"this":[60],"end,":[61],"we":[62],"propose":[63],"more":[64,105],"powerful":[65],"pause":[66,102,173,200],"insertion":[67,103,201],"frameworks":[68],"based":[69],"pre-trained":[72,84],"language":[73],"model.":[74],"Our":[75],"approach":[76],"uses":[77],"bidirectional":[78],"encoder":[79],"representations":[80],"from":[81],"transformers":[82],"(BERT)":[83],"large-scale":[87],"text":[88],"corpus,":[89],"injecting":[90],"speaker":[91,96,155],"embeddings":[92],"to":[93,150],"capture":[94],"characteristics.":[97],"We":[98,109],"leverage":[100],"duration-aware":[101,172],"for":[104,166],"TTS.":[108],"develop":[110],"evaluate":[112],"two":[113],"types":[114],"models.":[116],"The":[117,160,187],"first":[118],"improves":[119],"position":[125],"respiratory":[128],"(RPs),":[130],"i.e.,":[131],"at":[134],"word":[135],"transitions":[136],"without":[137],"punctuation.":[138],"It":[139],"performs":[140,171],"speaker-conditioned":[141],"RP":[142],"considering":[144],"contextual":[145],"information":[146,156],"used":[149],"demonstrate":[151],"effect":[153],"prediction.":[159],"second":[161],"further":[164],"designed":[165],"phoneme-based":[167],"predicting":[175],"both":[176],"RPs":[177],"punctuation-indicated":[179],"(PIPs)":[181],"that":[182,191],"are":[183],"categorized":[184],"by":[185],"duration.":[186],"evaluation":[188],"results":[189],"show":[190],"our":[192],"improve":[194],"precision":[196],"recall":[198]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}