{"id":"https://openalex.org/W4415432840","doi":"https://doi.org/10.21437/interspeech.2025-2171","title":"Towards Source Attribution of Singing Voice Deepfake with Multimodal Foundation Models","display_name":"Towards Source Attribution of Singing Voice Deepfake with Multimodal Foundation Models","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415432840","doi":"https://doi.org/10.21437/interspeech.2025-2171"},"language":null,"primary_location":{"id":"doi:10.21437/interspeech.2025-2171","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2171","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","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/A5076790933","display_name":"Orchid Chetia Phukan","orcid":"https://orcid.org/0000-0002-2542-8084"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Orchid Chetia Phukan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099056916","display_name":"Girish","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"- Girish","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113394151","display_name":"Mohd Mujtaba Akhtar","orcid":"https://orcid.org/0009-0000-1982-7110"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohd Mujtaba Akhtar","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014658425","display_name":"Swarup Ranjan Behera","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Swarup Ranjan Behera","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111310826","display_name":"Priyabrata Mallick","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Priyabrata Mallick","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025920434","display_name":"Pailla Balakrishna Reddy","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pailla Balakrishna Reddy","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014100784","display_name":"Arun Balaji Buduru","orcid":"https://orcid.org/0000-0002-6267-8138"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arun Balaji Buduru","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100715708","display_name":"Rajesh Kumar Sharma","orcid":"https://orcid.org/0000-0002-2288-5538"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rajesh Sharma","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5076790933"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4253,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.91728908,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1673","last_page":"1677"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.996999979019165,"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":0.996999979019165,"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/T10860","display_name":"Speech and Audio Processing","score":0.9889000058174133,"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":0.9886999726295471,"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/foundation","display_name":"Foundation (evidence)","score":0.6327999830245972},{"id":"https://openalex.org/keywords/attribution","display_name":"Attribution","score":0.5965999960899353},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.477400004863739},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.30889999866485596},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.2856999933719635}],"concepts":[{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.6327999830245972},{"id":"https://openalex.org/C143299363","wikidata":"https://www.wikidata.org/wiki/Q900584","display_name":"Attribution","level":2,"score":0.5965999960899353},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.477400004863739},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4754999876022339},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.367900013923645},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.35260000824928284},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3158999979496002},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.30889999866485596},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.305400013923645},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2750000059604645},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.27469998598098755},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.26339998841285706},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2531000077724457}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2025-2171","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2171","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-24T00:00:00"}