{"id":"https://openalex.org/W3197069320","doi":"https://doi.org/10.21437/interspeech.2021-1123","title":"A Prototypical Network Approach for Evaluating Generated Emotional Speech","display_name":"A Prototypical Network Approach for Evaluating Generated Emotional Speech","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3197069320","doi":"https://doi.org/10.21437/interspeech.2021-1123","mag":"3197069320"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1123","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1123","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":true,"oa_status":"green","oa_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/89688/baird21_interspeech.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030891676","display_name":"Alice Baird","orcid":"https://orcid.org/0000-0002-7003-5650"},"institutions":[{"id":"https://openalex.org/I179225836","display_name":"University of Augsburg","ror":"https://ror.org/03p14d497","country_code":"DE","type":"education","lineage":["https://openalex.org/I179225836"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Alice Baird","raw_affiliation_strings":["Chair of Embedded Intelligence for Health Care & Wellbeing, University of Augsburg, Germany"],"affiliations":[{"raw_affiliation_string":"Chair of Embedded Intelligence for Health Care & Wellbeing, University of Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043580137","display_name":"Silvan Mertes","orcid":"https://orcid.org/0000-0001-5230-5218"},"institutions":[{"id":"https://openalex.org/I179225836","display_name":"University of Augsburg","ror":"https://ror.org/03p14d497","country_code":"DE","type":"education","lineage":["https://openalex.org/I179225836"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Silvan Mertes","raw_affiliation_strings":["Chair of Human-Centered Artificial Intelligence, University of Augsburg, Germany"],"affiliations":[{"raw_affiliation_string":"Chair of Human-Centered Artificial Intelligence, University of Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037647437","display_name":"Manuel Milling","orcid":"https://orcid.org/0000-0002-8842-2958"},"institutions":[{"id":"https://openalex.org/I179225836","display_name":"University of Augsburg","ror":"https://ror.org/03p14d497","country_code":"DE","type":"education","lineage":["https://openalex.org/I179225836"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Manuel Milling","raw_affiliation_strings":["Chair of Embedded Intelligence for Health Care & Wellbeing, University of Augsburg, Germany"],"affiliations":[{"raw_affiliation_string":"Chair of Embedded Intelligence for Health Care & Wellbeing, University of Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023099133","display_name":"Lukas Stappen","orcid":"https://orcid.org/0000-0002-3761-2225"},"institutions":[{"id":"https://openalex.org/I179225836","display_name":"University of Augsburg","ror":"https://ror.org/03p14d497","country_code":"DE","type":"education","lineage":["https://openalex.org/I179225836"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Lukas Stappen","raw_affiliation_strings":["Chair of Embedded Intelligence for Health Care & Wellbeing, University of Augsburg, Germany"],"affiliations":[{"raw_affiliation_string":"Chair of Embedded Intelligence for Health Care & Wellbeing, University of Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037682307","display_name":"Thomas Wiest","orcid":null},"institutions":[{"id":"https://openalex.org/I179225836","display_name":"University of Augsburg","ror":"https://ror.org/03p14d497","country_code":"DE","type":"education","lineage":["https://openalex.org/I179225836"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomas Wiest","raw_affiliation_strings":["Chair of Embedded Intelligence for Health Care & Wellbeing, University of Augsburg, Germany"],"affiliations":[{"raw_affiliation_string":"Chair of Embedded Intelligence for Health Care & Wellbeing, University of Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056684559","display_name":"Elisabeth Andr\u00e9","orcid":"https://orcid.org/0000-0002-2367-162X"},"institutions":[{"id":"https://openalex.org/I179225836","display_name":"University of Augsburg","ror":"https://ror.org/03p14d497","country_code":"DE","type":"education","lineage":["https://openalex.org/I179225836"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Elisabeth Andr\u00e9","raw_affiliation_strings":["Chair of Human-Centered Artificial Intelligence, University of Augsburg, Germany"],"affiliations":[{"raw_affiliation_string":"Chair of Human-Centered Artificial Intelligence, University of Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043060302","display_name":"Bj\u00f6rn W. Schuller","orcid":"https://orcid.org/0000-0002-6478-8699"},"institutions":[{"id":"https://openalex.org/I179225836","display_name":"University of Augsburg","ror":"https://ror.org/03p14d497","country_code":"DE","type":"education","lineage":["https://openalex.org/I179225836"]},{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["DE","GB"],"is_corresponding":false,"raw_author_name":"Bj\u00f6rn W. Schuller","raw_affiliation_strings":["GLAM -Group on Language, Audio, & Music, Imperial College London, UK","Chair of Embedded Intelligence for Health Care & Wellbeing, University of Augsburg, Germany"],"affiliations":[{"raw_affiliation_string":"GLAM -Group on Language, Audio, & Music, Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Chair of Embedded Intelligence for Health Care & Wellbeing, University of Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5030891676"],"corresponding_institution_ids":["https://openalex.org/I179225836"],"apc_list":null,"apc_paid":null,"fwci":0.3078,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.54470999,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3161","last_page":"3165"},"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/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7804253101348877},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6502395272254944},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5637338161468506},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5335783362388611},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5278798341751099},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5080137252807617},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49872756004333496},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.48565852642059326},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4764987826347351},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4484423100948334},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3735305368900299},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37208667397499084}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7804253101348877},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6502395272254944},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5637338161468506},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5335783362388611},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5278798341751099},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5080137252807617},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49872756004333496},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.48565852642059326},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4764987826347351},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4484423100948334},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3735305368900299},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37208667397499084},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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":2,"locations":[{"id":"doi:10.21437/interspeech.2021-1123","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1123","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:89688","is_oa":true,"landing_page_url":"https://nbn-resolving.org/urn:nbn:de:bvb:384-opus4-896886","pdf_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/89688/baird21_interspeech.pdf","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":null,"raw_type":"doc-type:bookpart"}],"best_oa_location":{"id":"pmh:oai:uni-augsburg.opus-bayern.de:89688","is_oa":true,"landing_page_url":"https://nbn-resolving.org/urn:nbn:de:bvb:384-opus4-896886","pdf_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/89688/baird21_interspeech.pdf","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":null,"raw_type":"doc-type:bookpart"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3197069320.pdf","grobid_xml":"https://content.openalex.org/works/W3197069320.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W414188911","https://openalex.org/W1552314771","https://openalex.org/W2144005487","https://openalex.org/W2601450892","https://openalex.org/W2734358244","https://openalex.org/W2742542661","https://openalex.org/W2777468850","https://openalex.org/W2936774411","https://openalex.org/W2942077508","https://openalex.org/W2962845248","https://openalex.org/W2963185411","https://openalex.org/W2963373786","https://openalex.org/W2963684088","https://openalex.org/W2963777632","https://openalex.org/W2972640480","https://openalex.org/W2984972638","https://openalex.org/W3039350292","https://openalex.org/W3082892415","https://openalex.org/W3116986826","https://openalex.org/W3118608800","https://openalex.org/W3152478832","https://openalex.org/W3160506022","https://openalex.org/W4297817572","https://openalex.org/W4301206121","https://openalex.org/W4302023197"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W2897924318","https://openalex.org/W2138997758","https://openalex.org/W2589961920"],"abstract_inverted_index":{"The":[0],"collection":[1],"of":[2,51,59,161],"emotional":[3,61],"speech":[4],"data":[5,21,132,138,158,181],"is":[6,24,133,173],"a":[7,52,104,136,174],"time-consuming":[8],"and":[9,75,86,102,115,143],"costly":[10],"endeavour.Generative":[11],"networks":[12],"can":[13,117],"be":[14,118],"applied":[15],"to":[16,26,33,44,55,82,106,155,168],"augment":[17,93],"the":[18,45,49,83,89,94,108,124,144,162,179],"limited":[19],"audio":[20,29,46,62,74,77,110],"artificially.However,":[22],"it":[23],"challenging":[25],"evaluate":[27,56],"generated":[28,60,73,109,131],"for":[30,159],"its":[31],"similarity":[32,81],"source":[34,95,137,151,163,180],"data,":[35],"as":[36,135,149],"current":[37],"quantitative":[38],"metrics":[39],"are":[40],"not":[41],"necessarily":[42],"suited":[43],"domain.We":[47],"explore":[48,107],"use":[50],"prototypical":[53],"network":[54],"four":[57],"classes":[58],"with":[63,98,121],"this":[64,122],"in":[65],"mind.We":[66],"first":[67],"extract":[68],"spectrogram":[69],"images":[70],"from":[71],"WAVEGAN":[72,130],"other":[76],"augmentation":[78,100,160],"approaches,":[79],"comparing":[80],"class":[84,139],"prototype":[85],"diversity":[87,116,148],"within":[88],"embedding":[90],"space.Furthermore,":[91],"we":[92,127],"training":[96,164],"set":[97,165],"each":[99],"type":[101],"perform":[103],"classification":[105],"plausibility.Results":[111],"suggest":[112],"that":[113,129],"quality":[114],"quantitatively":[119],"observed":[120],"approach.In":[123],"chosen":[125],"context,":[126],"see":[128],"recognisable":[134],"(F1-score":[140],"43.6":[141],"%),":[142],"samples":[145],"add":[146],"similar":[147],"unseen":[150],"data.This":[152],"result":[153],"leads":[154],"more":[156],"plausible":[157],"-achieving":[166],"up":[167],"63.9":[169],"%":[170,176],"F1":[171],"which":[172],"3.5":[175],"improvement":[177],"over":[178],"baseline.":[182]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}
