{"id":"https://openalex.org/W4385822778","doi":"https://doi.org/10.21437/interspeech.2023-858","title":"Controllable Generation of Artificial Speaker Embeddings through Discovery of Principal Directions","display_name":"Controllable Generation of Artificial Speaker Embeddings through Discovery of Principal Directions","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385822778","doi":"https://doi.org/10.21437/interspeech.2023-858"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-858","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2023-858","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2310.17502","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078880407","display_name":"Florian Lux","orcid":"https://orcid.org/0000-0003-4325-5129"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Florian Lux","raw_affiliation_strings":["University of Stuttgart, Institute for Natural Language Processing, Germany"],"affiliations":[{"raw_affiliation_string":"University of Stuttgart, Institute for Natural Language Processing, Germany","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091791731","display_name":"Pascal Tilli","orcid":"https://orcid.org/0009-0001-7503-1413"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Pascal Tilli","raw_affiliation_strings":["University of Stuttgart, Institute for Natural Language Processing, Germany"],"affiliations":[{"raw_affiliation_string":"University of Stuttgart, Institute for Natural Language Processing, Germany","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064340157","display_name":"Sarina Meyer","orcid":"https://orcid.org/0009-0004-1117-4783"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sarina Meyer","raw_affiliation_strings":["University of Stuttgart, Institute for Natural Language Processing, Germany"],"affiliations":[{"raw_affiliation_string":"University of Stuttgart, Institute for Natural Language Processing, Germany","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020700841","display_name":"Ngoc Thang Vu","orcid":"https://orcid.org/0000-0001-7893-9147"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ngoc Thang Vu","raw_affiliation_strings":["University of Stuttgart, Institute for Natural Language Processing, Germany"],"affiliations":[{"raw_affiliation_string":"University of Stuttgart, Institute for Natural Language Processing, Germany","institution_ids":["https://openalex.org/I100066346"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5078880407"],"corresponding_institution_ids":["https://openalex.org/I100066346"],"apc_list":null,"apc_paid":null,"fwci":0.1758,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.55994265,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"4788","last_page":"4792"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9980000257492065,"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/T10860","display_name":"Speech and Audio Processing","score":0.9973000288009644,"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/computer-science","display_name":"Computer science","score":0.7763780355453491},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6610206365585327},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6035441756248474},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5638686418533325},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.514549195766449},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4931125342845917},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4813176393508911},{"id":"https://openalex.org/keywords/human-voice","display_name":"Human voice","score":0.4755418300628662},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4505886137485504},{"id":"https://openalex.org/keywords/principal","display_name":"Principal (computer security)","score":0.44490107893943787},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4440036714076996},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33462172746658325}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7763780355453491},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6610206365585327},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6035441756248474},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5638686418533325},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.514549195766449},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4931125342845917},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4813176393508911},{"id":"https://openalex.org/C20766975","wikidata":"https://www.wikidata.org/wiki/Q7390","display_name":"Human voice","level":2,"score":0.4755418300628662},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4505886137485504},{"id":"https://openalex.org/C144559511","wikidata":"https://www.wikidata.org/wiki/Q2986279","display_name":"Principal (computer security)","level":2,"score":0.44490107893943787},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4440036714076996},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33462172746658325},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2023-858","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2023-858","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2310.17502","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.17502","pdf_url":"https://arxiv.org/pdf/2310.17502","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2310.17502","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.17502","pdf_url":"https://arxiv.org/pdf/2310.17502","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385822778.pdf","grobid_xml":"https://content.openalex.org/works/W4385822778.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2527729766","https://openalex.org/W2739748921","https://openalex.org/W2788357188","https://openalex.org/W2794490148","https://openalex.org/W2807627734","https://openalex.org/W2808706139","https://openalex.org/W2972359262","https://openalex.org/W2972802841","https://openalex.org/W2972848589","https://openalex.org/W2991440249","https://openalex.org/W3011956469","https://openalex.org/W3015826515","https://openalex.org/W3024869864","https://openalex.org/W3033411150","https://openalex.org/W3081192838","https://openalex.org/W3092028330","https://openalex.org/W3094002217","https://openalex.org/W3095410713","https://openalex.org/W3134652006","https://openalex.org/W3150572638","https://openalex.org/W3161704465","https://openalex.org/W3167533889","https://openalex.org/W3198020407","https://openalex.org/W3204379680","https://openalex.org/W3205034290","https://openalex.org/W3212077957","https://openalex.org/W4205742757","https://openalex.org/W4206596421","https://openalex.org/W4225680573","https://openalex.org/W4225746985","https://openalex.org/W4231807801","https://openalex.org/W4280561221","https://openalex.org/W4285189120","https://openalex.org/W4286905415","https://openalex.org/W4286950013","https://openalex.org/W4287817254","https://openalex.org/W4289383906","https://openalex.org/W4295521014","https://openalex.org/W4297841819","https://openalex.org/W4298174729","https://openalex.org/W4319862433","https://openalex.org/W4320013936","https://openalex.org/W4382202681","https://openalex.org/W4395957972","https://openalex.org/W4395961059","https://openalex.org/W4404752329"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2938358845","https://openalex.org/W2997340161"],"abstract_inverted_index":{"Customizing":[0],"voice":[1,31,65],"and":[2,12,60,66,82],"speaking":[3,67],"style":[4,68],"in":[5],"a":[6,42,54,89],"speech":[7,90],"synthesis":[8,91],"system":[9],"with":[10,21,34],"intuitive":[11,59],"fine-grained":[13,61],"controls":[14],"is":[15,24],"challenging,":[16],"given":[17],"that":[18,49],"little":[19],"data":[20],"appropriate":[22],"labels":[23,75],"available.":[25],"Furthermore,":[26],"editing":[27],"an":[28],"existing":[29],"human's":[30],"also":[32],"comes":[33],"ethical":[35],"concerns.":[36],"In":[37],"this":[38],"paper,":[39],"we":[40],"propose":[41],"method":[43],"to":[44,53,88],"generate":[45],"artificial":[46,81],"speaker":[47,77],"embeddings":[48,84,95],"cannot":[50],"be":[51,86],"linked":[52],"real":[55,97],"human":[56],"while":[57],"offering":[58],"control":[62],"over":[63],"the":[64,70],"of":[69,96],"embeddings,":[71],"without":[72,101],"requiring":[73],"any":[74],"for":[76],"or":[78],"style.":[79],"The":[80],"controllable":[83],"can":[85],"fed":[87],"system,":[92],"conditioned":[93],"on":[94],"humans":[98],"during":[99,104],"training,":[100],"sacrificing":[102],"privacy":[103],"inference.":[105]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2023-08-15T00:00:00"}
