{"id":"https://openalex.org/W4297841376","doi":"https://doi.org/10.21437/interspeech.2022-825","title":"Vocal effort modeling in neural TTS for improving the intelligibility of synthetic speech in noise","display_name":"Vocal effort modeling in neural TTS for improving the intelligibility of synthetic speech in noise","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4297841376","doi":"https://doi.org/10.21437/interspeech.2022-825"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-825","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-825","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/A5000571465","display_name":"Tuomo Raitio","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Tuomo Raitio","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065184308","display_name":"Petko H. Petkov","orcid":"https://orcid.org/0000-0003-0334-0900"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Petko Petkov","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041250635","display_name":"Jiangchuan Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiangchuan Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001143396","display_name":"Muhammed Shifas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Muhammed Shifas","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102498800","display_name":"Andrea Davis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrea Davis","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5035745788","display_name":"Yannis Stylianou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yannis Stylianou","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5000571465"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4909,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.59241706,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1936","last_page":"1940"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10860","display_name":"Speech and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9997000098228455,"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/T11309","display_name":"Music and Audio Processing","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/intelligibility","display_name":"Intelligibility (philosophy)","score":0.7100843787193298},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7055279016494751},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6605855822563171},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.48008209466934204},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4686756730079651},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.46101346611976624},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26014986634254456},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07343682646751404}],"concepts":[{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7100843787193298},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7055279016494751},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6605855822563171},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.48008209466934204},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4686756730079651},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.46101346611976624},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26014986634254456},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07343682646751404},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-825","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-825","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":0.5,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W65497148","https://openalex.org/W1968637674","https://openalex.org/W1997307245","https://openalex.org/W1999690732","https://openalex.org/W2004826498","https://openalex.org/W2015787642","https://openalex.org/W2026024822","https://openalex.org/W2033321754","https://openalex.org/W2048653958","https://openalex.org/W2075510576","https://openalex.org/W2098930980","https://openalex.org/W2104387086","https://openalex.org/W2109138290","https://openalex.org/W2118258949","https://openalex.org/W2128631678","https://openalex.org/W2129387557","https://openalex.org/W2135512340","https://openalex.org/W2153185504","https://openalex.org/W2154825638","https://openalex.org/W2163010125","https://openalex.org/W2168554752","https://openalex.org/W2401725871","https://openalex.org/W2404548911","https://openalex.org/W2485688913","https://openalex.org/W2519091744","https://openalex.org/W2766812927","https://openalex.org/W2964243274","https://openalex.org/W3033411150","https://openalex.org/W3034443407","https://openalex.org/W3096795913","https://openalex.org/W3097587372","https://openalex.org/W3097892637","https://openalex.org/W3146104336","https://openalex.org/W3202098869","https://openalex.org/W4234195863","https://openalex.org/W4240819301","https://openalex.org/W4298580827","https://openalex.org/W4299687266","https://openalex.org/W4399639995"],"related_works":["https://openalex.org/W2373674497","https://openalex.org/W2768478174","https://openalex.org/W2010050186","https://openalex.org/W2027206961","https://openalex.org/W2081919107","https://openalex.org/W2127461790","https://openalex.org/W2069324367","https://openalex.org/W3115948027","https://openalex.org/W2405110677","https://openalex.org/W2811496854"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,41],"neural":[3,42],"text-to-speech":[4],"(TTS)":[5],"method":[6,25,147],"that":[7,144],"models":[8],"natural":[9],"vocal":[10,65,97,124],"effort":[11,66,98,125],"variation":[12],"to":[13,137],"improve":[14,149],"the":[15,21,30,53,78,88,102,107,113,127,145,150],"intelligibility":[16,103,114,151],"of":[17,23,27,33,72,77,104,109,117,129,152],"synthetic":[18,153],"speech":[19,36,94,105,119,121,139,154,159],"in":[20,87,106,126,158],"presence":[22,108,128],"noise.The":[24],"consists":[26],"first":[28],"measuring":[29],"spectral":[31,47,54,79],"tilt":[32,48,55,80],"unlabeled":[34],"conventional":[35],"data,":[37,90],"and":[38,57,115,120,134],"then":[39],"conditioning":[40],"TTS":[43],"model":[44],"with":[45,95,122,155],"normalized":[46],"among":[49],"other":[50,59,73],"prosodic":[51,60,74],"factors.Changing":[52],"parameter":[56],"keeping":[58],"factors":[61],"unchanged":[62],"enables":[63],"effective":[64],"control":[67],"at":[68],"synthesis":[69],"time":[70],"independent":[71],"factors.By":[75],"extrapolation":[76],"values":[81],"beyond":[82],"what":[83],"has":[84],"been":[85],"seen":[86],"original":[89],"we":[91],"can":[92,148],"generate":[93],"high":[96],"levels,":[99],"thus":[100],"improving":[101],"masking":[110,131],"noise.We":[111],"evaluate":[112],"quality":[116],"normal":[118],"increased":[123],"various":[130],"noise":[132],"conditions,":[133],"compare":[135],"these":[136],"well-known":[138],"intelligibility-enhancing":[140],"algorithms.The":[141],"evaluations":[142],"show":[143],"proposed":[146],"little":[156],"loss":[157],"quality.":[160]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}