{"id":"https://openalex.org/W3196800575","doi":"https://doi.org/10.21437/interspeech.2021-1587","title":"Analysis by Synthesis: Using an Expressive TTS Model as Feature Extractor for Paralinguistic Speech Classification","display_name":"Analysis by Synthesis: Using an Expressive TTS Model as Feature Extractor for Paralinguistic Speech Classification","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3196800575","doi":"https://doi.org/10.21437/interspeech.2021-1587","mag":"3196800575"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1587","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1587","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/A5060629499","display_name":"Dominik Schiller","orcid":"https://orcid.org/0000-0001-7364-5772"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dominik Schiller","raw_affiliation_strings":["Human-Centered Artificial Intelligence, Augsburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human-Centered Artificial Intelligence, Augsburg, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043580137","display_name":"Silvan Mertes","orcid":"https://orcid.org/0000-0001-5230-5218"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Silvan Mertes","raw_affiliation_strings":["Human-Centered Artificial Intelligence, Augsburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human-Centered Artificial Intelligence, Augsburg, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045500067","display_name":"Pol van Rijn","orcid":"https://orcid.org/0000-0002-4044-9123"},"institutions":[{"id":"https://openalex.org/I4210086768","display_name":"Max Planck Institute for Empirical Aesthetics","ror":"https://ror.org/000rdbk18","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210086768"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Pol van Rijn","raw_affiliation_strings":["Max-Planck-Institute for Empirical Aesthetics, Frankfurt, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Max-Planck-Institute for Empirical Aesthetics, Frankfurt, Germany","institution_ids":["https://openalex.org/I4210086768"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056684559","display_name":"Elisabeth Andr\u00e9","orcid":"https://orcid.org/0000-0002-2367-162X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Elisabeth Andr\u00e9","raw_affiliation_strings":["Human-Centered Artificial Intelligence, Augsburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human-Centered Artificial Intelligence, Augsburg, Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5045500067"],"corresponding_institution_ids":["https://openalex.org/I4210086768"],"apc_list":null,"apc_paid":null,"fwci":0.2798,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.64229632,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.7555999755859375,"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":0.7555999755859375,"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/paralanguage","display_name":"Paralanguage","score":0.9830735921859741},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.830022931098938},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6966364979743958},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6496295928955078},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5890922546386719},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5061680674552917},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4934627115726471},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4789476990699768},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38508331775665283},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1249769926071167},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.11235901713371277},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10296240448951721},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.0681883692741394}],"concepts":[{"id":"https://openalex.org/C133378560","wikidata":"https://www.wikidata.org/wiki/Q1753225","display_name":"Paralanguage","level":2,"score":0.9830735921859741},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.830022931098938},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6966364979743958},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6496295928955078},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5890922546386719},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5061680674552917},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4934627115726471},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4789476990699768},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38508331775665283},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1249769926071167},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.11235901713371277},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10296240448951721},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0681883692741394},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2021-1587","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1587","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:uni-augsburg.opus-bayern.de:89687","is_oa":false,"landing_page_url":"https://nbn-resolving.org/urn:nbn:de:bvb:384-opus4-896877","pdf_url":null,"source":{"id":"https://openalex.org/S4306400930","display_name":"OPUS (Augsburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119916105","host_organization_name":"Augsburg University","host_organization_lineage":["https://openalex.org/I119916105"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"bookpart"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G4502817849","display_name":null,"funder_award_id":"856879","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W567437002","https://openalex.org/W1970906983","https://openalex.org/W1972825086","https://openalex.org/W2005374274","https://openalex.org/W2040467972","https://openalex.org/W2061760940","https://openalex.org/W2082927806","https://openalex.org/W2108827278","https://openalex.org/W2239141610","https://openalex.org/W2746419079","https://openalex.org/W2794490148","https://openalex.org/W2889467522","https://openalex.org/W2897065501","https://openalex.org/W2963194800","https://openalex.org/W2963609956","https://openalex.org/W2970641574","https://openalex.org/W3015645837","https://openalex.org/W3134945014","https://openalex.org/W3159045181","https://openalex.org/W4254896370"],"related_works":["https://openalex.org/W2064370490","https://openalex.org/W3166813893","https://openalex.org/W2910013580","https://openalex.org/W2391900574","https://openalex.org/W3200958703","https://openalex.org/W1990078780","https://openalex.org/W2778981579","https://openalex.org/W2376619307","https://openalex.org/W4250647969","https://openalex.org/W3108667266"],"abstract_inverted_index":{"Modeling":[0],"adequate":[1],"features":[2,123],"of":[3,58,80,145],"speech":[4,15,94,102,126],"prosody":[5,21,35,87],"is":[6,23,28,37,41,47,89,97],"one":[7],"key":[8],"factor":[9],"to":[10,104,121],"good":[11],"performance":[12,79],"in":[13,49,55,92,100,140],"affective":[14,31,72,93],"classification.However,":[16],"the":[17,20,34,59,70,78,81,113,131,141],"distinction":[18,84],"between":[19,85],"that":[22,36,66,130],"induced":[24,38],"by":[25,39],"'how'":[26],"something":[27],"said":[29,43],"(i.e.,":[30,44],"prosody)":[32,46],"and":[33],"'what'":[40],"being":[42],"linguistic":[45],"neglected":[48,91],"state-of-the-art":[50,136],"feature":[51,61,137],"extraction":[52,138],"systems.This":[53],"results":[54],"high":[56],"variability":[57],"calculated":[60],"values":[62],"for":[63,124],"different":[64,86],"sentences":[65],"are":[67],"spoken":[68],"with":[69],"same":[71],"intent,":[73],"which":[74],"might":[75],"negatively":[76],"impact":[77],"classification.While":[82],"this":[83,109],"types":[88],"mostly":[90],"recognition,":[95],"it":[96],"explicitly":[98],"modeled":[99],"expressive":[101,114],"synthesis":[103],"create":[105],"controlled":[106],"prosodic":[107,133],"variation.In":[108],"work,":[110],"we":[111],"use":[112,143],"Text-To-Speech":[115],"model":[116],"Global":[117],"Style":[118],"Token":[119],"Tacotron":[120],"extract":[122],"a":[125],"analysis":[127],"task.We":[128],"show":[129],"learned":[132],"representations":[134],"outperform":[135],"systems":[139],"exemplary":[142],"case":[144],"Escalation":[146],"Level":[147],"Classification.":[148]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-05-23T08:51:43.019350","created_date":"2025-10-10T00:00:00"}