{"id":"https://openalex.org/W3202510435","doi":"https://doi.org/10.21437/interspeech.2022-411","title":"Emphasis Control for Parallel Neural TTS","display_name":"Emphasis Control for Parallel Neural TTS","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W3202510435","doi":"https://doi.org/10.21437/interspeech.2022-411","mag":"3202510435"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-411","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-411","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":"conference-paper","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/A5048838330","display_name":"Shreyas Seshadri","orcid":"https://orcid.org/0000-0003-1731-3129"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shreyas Seshadri","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000571465","display_name":"Tuomo Raitio","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tuomo Raitio","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087024713","display_name":"Dan Castellani","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dan Castellani","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5005526135","display_name":"Jiangchuan Li","orcid":"https://orcid.org/0000-0002-6489-4766"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiangchuan Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1808,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.79811018,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3378","last_page":"3382"},"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":0.9991000294685364,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9976999759674072,"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/emphasis","display_name":"Emphasis (telecommunications)","score":0.7310130000114441},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6436883211135864},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.518545925617218},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.342267245054245},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2683870196342468},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1624279022216797}],"concepts":[{"id":"https://openalex.org/C177454536","wikidata":"https://www.wikidata.org/wiki/Q578290","display_name":"Emphasis (telecommunications)","level":2,"score":0.7310130000114441},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6436883211135864},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.518545925617218},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.342267245054245},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2683870196342468},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1624279022216797}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-411","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-411","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":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1581480663","https://openalex.org/W2095705004","https://openalex.org/W2106714505","https://openalex.org/W2405833831","https://openalex.org/W2406743117","https://openalex.org/W2515780670","https://openalex.org/W2550497374","https://openalex.org/W2605762339","https://openalex.org/W2613904329","https://openalex.org/W2626778328","https://openalex.org/W2767052532","https://openalex.org/W2794490148","https://openalex.org/W2807833558","https://openalex.org/W2897548994","https://openalex.org/W2946200149","https://openalex.org/W2954099406","https://openalex.org/W2962691331","https://openalex.org/W2962850167","https://openalex.org/W2963927338","https://openalex.org/W2963945466","https://openalex.org/W2964243274","https://openalex.org/W2972484110","https://openalex.org/W3028143998","https://openalex.org/W3033411150","https://openalex.org/W3033913438","https://openalex.org/W3086296097","https://openalex.org/W3097892637","https://openalex.org/W3100400819","https://openalex.org/W3101882441","https://openalex.org/W3130016944","https://openalex.org/W3144044466","https://openalex.org/W3144667183","https://openalex.org/W3169214411","https://openalex.org/W3197957589","https://openalex.org/W3199015956","https://openalex.org/W3202098869","https://openalex.org/W4210684870","https://openalex.org/W4285881128","https://openalex.org/W4287761884","https://openalex.org/W4289383906","https://openalex.org/W4295731579","https://openalex.org/W4298580827","https://openalex.org/W4385245566","https://openalex.org/W4394666973"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2153819599","https://openalex.org/W2255426644","https://openalex.org/W2072124641","https://openalex.org/W2018956713","https://openalex.org/W1971573522","https://openalex.org/W2081479354","https://openalex.org/W2113107605","https://openalex.org/W3204693335"],"abstract_inverted_index":{"Recent":[0],"parallel":[1,42],"neural":[2,43],"text-to-speech":[3],"(TTS)":[4],"synthesis":[5],"methods":[6,125],"are":[7,69,126],"able":[8,127],"to":[9,58,128],"generate":[10],"speech":[11],"with":[12,135],"high":[13,17],"fidelity":[14],"while":[15],"maintaining":[16],"performance.However,":[18],"these":[19],"systems":[20],"often":[21],"lack":[22],"control":[23,49],"over":[24,150],"the":[25,30,66,96,109,113,117,123,130,151],"output":[26],"prosody,":[27],"thus":[28],"restricting":[29],"semantic":[31],"information":[32],"conveyable":[33],"for":[34,46,65,116,156],"a":[35,40,52,59,80,146],"given":[36,118],"text.This":[37],"paper":[38],"proposes":[39],"hierarchical":[41],"TTS":[44],"system":[45],"prosodic":[47,103],"emphasis":[48,104,134],"by":[50,107],"learning":[51],"latent":[53,67,114],"space":[54,68,115],"that":[55,121],"directly":[56],"corresponds":[57],"change":[60],"in":[61,79,138,145],"emphasis.Three":[62],"candidate":[63],"features":[64],"compared:":[70],"1)":[71],"Variance":[72],"of":[73,95,112,132],"pitch":[74],"and":[75,89,91],"duration":[76],"within":[77],"words":[78],"sentence,":[81],"2)":[82],"Wavelet-based":[83],"feature":[84,110],"computed":[85],"from":[86],"pitch,":[87],"energy,":[88],"duration,":[90],"3)":[92],"Learned":[93],"combination":[94],"two":[97],"aforementioned":[98],"approaches.At":[99],"inference":[100],"time,":[101],"word-level":[102],"is":[105],"achieved":[106],"increasing":[108],"values":[111],"words.Experiments":[119],"show":[120],"all":[122],"proposed":[124],"achieve":[129],"perception":[131],"increased":[133],"little":[136],"loss":[137],"overall":[139],"quality.Moreover,":[140],"emphasized":[141],"utterances":[142],"were":[143],"preferred":[144],"pairwise":[147],"comparison":[148],"test":[149],"non-emphasized":[152],"utterances,":[153],"indicating":[154],"promise":[155],"real-world":[157],"applications.":[158]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}