{"id":"https://openalex.org/W4402112376","doi":"https://doi.org/10.21437/interspeech.2024-328","title":"Anonymising Elderly and Pathological Speech: Voice Conversion Using DDSP and Query-by-Example","display_name":"Anonymising Elderly and Pathological Speech: Voice Conversion Using DDSP and Query-by-Example","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402112376","doi":"https://doi.org/10.21437/interspeech.2024-328"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-328","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-328","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2410.15500","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041024295","display_name":"Suhita Ghosh","orcid":"https://orcid.org/0000-0002-5553-585X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Suhita Ghosh","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050326510","display_name":"M\u00e9lanie Jouaiti","orcid":"https://orcid.org/0000-0001-6402-0623"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Melanie Jouaiti","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103205617","display_name":"Arnab Das","orcid":"https://orcid.org/0000-0001-9715-1435"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arnab Das","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089816799","display_name":"Yamini Sinha","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yamini Sinha","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034570279","display_name":"Tim Polzehl","orcid":"https://orcid.org/0000-0001-9592-0296"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tim Polzehl","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033995312","display_name":"Ingo Siegert","orcid":"https://orcid.org/0000-0001-7447-7141"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ingo Siegert","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5034558147","display_name":"Sebastian Stober","orcid":"https://orcid.org/0000-0002-1717-4133"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sebastian Stober","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5041024295"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3379,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.8389539,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4438","last_page":"4442"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.982699990272522,"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":0.982699990272522,"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/T10863","display_name":"Voice and Speech Disorders","score":0.9807999730110168,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9132999777793884,"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/computer-science","display_name":"Computer science","score":0.757746696472168},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.6826918721199036},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5092612504959106},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.48858460783958435},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.45712536573410034},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4559318721294403},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3280220031738281}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.757746696472168},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.6826918721199036},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5092612504959106},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.48858460783958435},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.45712536573410034},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4559318721294403},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3280220031738281},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2024-328","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-328","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2410.15500","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.15500","pdf_url":"https://arxiv.org/pdf/2410.15500","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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/ec583aeb-315f-4616-94f2-fc3bcb96f777","is_oa":false,"landing_page_url":"https://research.birmingham.ac.uk/en/publications/ec583aeb-315f-4616-94f2-fc3bcb96f777","pdf_url":null,"source":{"id":"https://openalex.org/S4306402634","display_name":"University of Birmingham Research Portal (University of Birmingham)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79619799","host_organization_name":"University of Birmingham","host_organization_lineage":["https://openalex.org/I79619799"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Ghosh, S, Jouaiti, M, Das, A, Sinha, Y, Polzehl, T, Siegert, I & Stober, S 2024, Anonymising Elderly and Pathological Speech : Voice Conversion Using DDSP and Query-by-Example. in Interspeech 2024. Interspeech, ISCA, pp. 4438-4442, 25th Interspeech Conferece 2024, Kos Island, Greece, 1/09/24. https://doi.org/10.21437/Interspeech.2024-328","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2410.15500","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.15500","pdf_url":"https://arxiv.org/pdf/2410.15500","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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402112376.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2355553914","https://openalex.org/W149862513","https://openalex.org/W2347684782","https://openalex.org/W187117048","https://openalex.org/W4320472397","https://openalex.org/W2401269021","https://openalex.org/W3008088358","https://openalex.org/W3130133758","https://openalex.org/W2127461790","https://openalex.org/W2069324367"],"abstract_inverted_index":{"Speech":[0],"anonymisation":[1],"aims":[2],"to":[3,20,77,79],"protect":[4],"speaker":[5,112],"identity":[6],"by":[7,118],"changing":[8],"personal":[9],"identifiers":[10],"in":[11,28,67],"speech":[12,25,32,81],"while":[13,108],"retaining":[14],"linguistic":[15],"content.":[16],"Current":[17],"methods":[18],"fail":[19],"retain":[21],"prosody":[22],"and":[23,30,57,71,84,99,106,111],"unique":[24],"patterns":[26],"found":[27],"elderly":[29],"pathological":[31],"domains,":[33],"which":[34],"is":[35],"essential":[36],"for":[37],"remote":[38],"health":[39],"monitoring.":[40],"To":[41],"address":[42],"this":[43],"gap,":[44],"we":[45],"propose":[46],"a":[47],"voice":[48,93],"conversion-based":[49],"method":[50],"(DDSP-QbE)":[51],"using":[52],"differentiable":[53],"digital":[54],"signal":[55],"processing":[56],"query-by-example.":[58],"The":[59],"proposed":[60],"method,":[61],"trained":[62],"with":[63],"novel":[64],"losses,":[65],"aids":[66],"disentangling":[68],"linguistic,":[69],"prosodic,":[70],"domain":[72,100,116,123],"representations,":[73],"enabling":[74],"the":[75,92],"model":[76],"adapt":[78],"uncommon":[80],"patterns.":[82],"Objective":[83],"subjective":[85],"evaluations":[86],"show":[87],"that":[88],"DDSP-QbE":[89],"significantly":[90],"outperforms":[91],"conversion":[94],"state-of-the-art":[95],"concerning":[96],"intelligibility,":[97],"prosody,":[98],"preservation":[101,117],"across":[102],"diverse":[103],"datasets,":[104],"pathologies,":[105],"speakers":[107],"maintaining":[109],"quality":[110],"anonymity.":[113],"Experts":[114],"validate":[115],"analysing":[119],"twelve":[120],"clinically":[121],"pertinent":[122],"attributes.":[124]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2024-09-02T00:00:00"}
