{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WMHWQFNFWCPVWMCZRJY33I5QDR","short_pith_number":"pith:WMHWQFNF","schema_version":"1.0","canonical_sha256":"b30f6815a5b09f5b30598a71bda3b01c63726ab423e35a285f1f4ae055f6e309","source":{"kind":"arxiv","id":"2507.12595","version":1},"attestation_state":"computed","paper":{"title":"Enhancing In-Domain and Out-Domain EmoFake Detection via Cooperative Multilingual Speech Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Arun Balaji Buduru, Girish, Mohd Mujtaba Akhtar, Orchid Chetia Phukan","submitted_at":"2025-07-16T19:30:51Z","abstract_excerpt":"In this work, we address EmoFake Detection (EFD). We hypothesize that multilingual speech foundation models (SFMs) will be particularly effective for EFD due to their pre-training across diverse languages, enabling a nuanced understanding of variations in pitch, tone, and intensity. To validate this, we conduct a comprehensive comparative analysis of state-of-the-art (SOTA) SFMs. Our results shows the superiority of multilingual SFMs for same language (in-domain) as well as cross-lingual (out-domain) evaluation. To our end, we also propose, THAMA for fusion of foundation models (FMs) motivated"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2507.12595","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-07-16T19:30:51Z","cross_cats_sorted":[],"title_canon_sha256":"19be87bae960c8b4fcb39465a37b29c2a58f724c05e484d66c6ea80eb5847573","abstract_canon_sha256":"d4f47de6366b06074eeb3c41cf110121ae43d3b4f3fc4996e5dc3722c268be19"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:35.416914Z","signature_b64":"bcCt/XeUoDA9E6jNNeOGWmeaQ4235NiH0INssGV4pb3af6ZjcJGKi/ZaEZL6vKLUcfYBARAuPNwgcRIJlb5LDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b30f6815a5b09f5b30598a71bda3b01c63726ab423e35a285f1f4ae055f6e309","last_reissued_at":"2026-07-05T11:38:35.416401Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:35.416401Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing In-Domain and Out-Domain EmoFake Detection via Cooperative Multilingual Speech Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Arun Balaji Buduru, Girish, Mohd Mujtaba Akhtar, Orchid Chetia Phukan","submitted_at":"2025-07-16T19:30:51Z","abstract_excerpt":"In this work, we address EmoFake Detection (EFD). We hypothesize that multilingual speech foundation models (SFMs) will be particularly effective for EFD due to their pre-training across diverse languages, enabling a nuanced understanding of variations in pitch, tone, and intensity. To validate this, we conduct a comprehensive comparative analysis of state-of-the-art (SOTA) SFMs. Our results shows the superiority of multilingual SFMs for same language (in-domain) as well as cross-lingual (out-domain) evaluation. To our end, we also propose, THAMA for fusion of foundation models (FMs) motivated"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.12595","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2507.12595/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2507.12595","created_at":"2026-07-05T11:38:35.416456+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.12595v1","created_at":"2026-07-05T11:38:35.416456+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.12595","created_at":"2026-07-05T11:38:35.416456+00:00"},{"alias_kind":"pith_short_12","alias_value":"WMHWQFNFWCPV","created_at":"2026-07-05T11:38:35.416456+00:00"},{"alias_kind":"pith_short_16","alias_value":"WMHWQFNFWCPVWMCZ","created_at":"2026-07-05T11:38:35.416456+00:00"},{"alias_kind":"pith_short_8","alias_value":"WMHWQFNF","created_at":"2026-07-05T11:38:35.416456+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.19949","citing_title":"Indic-CodecFake meets SATYAM: Towards Detecting Neural Audio Codec Synthesized Speech Deepfakes in Indic Languages","ref_index":152,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WMHWQFNFWCPVWMCZRJY33I5QDR","json":"https://pith.science/pith/WMHWQFNFWCPVWMCZRJY33I5QDR.json","graph_json":"https://pith.science/api/pith-number/WMHWQFNFWCPVWMCZRJY33I5QDR/graph.json","events_json":"https://pith.science/api/pith-number/WMHWQFNFWCPVWMCZRJY33I5QDR/events.json","paper":"https://pith.science/paper/WMHWQFNF"},"agent_actions":{"view_html":"https://pith.science/pith/WMHWQFNFWCPVWMCZRJY33I5QDR","download_json":"https://pith.science/pith/WMHWQFNFWCPVWMCZRJY33I5QDR.json","view_paper":"https://pith.science/paper/WMHWQFNF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.12595&json=true","fetch_graph":"https://pith.science/api/pith-number/WMHWQFNFWCPVWMCZRJY33I5QDR/graph.json","fetch_events":"https://pith.science/api/pith-number/WMHWQFNFWCPVWMCZRJY33I5QDR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WMHWQFNFWCPVWMCZRJY33I5QDR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WMHWQFNFWCPVWMCZRJY33I5QDR/action/storage_attestation","attest_author":"https://pith.science/pith/WMHWQFNFWCPVWMCZRJY33I5QDR/action/author_attestation","sign_citation":"https://pith.science/pith/WMHWQFNFWCPVWMCZRJY33I5QDR/action/citation_signature","submit_replication":"https://pith.science/pith/WMHWQFNFWCPVWMCZRJY33I5QDR/action/replication_record"}},"created_at":"2026-07-05T11:38:35.416456+00:00","updated_at":"2026-07-05T11:38:35.416456+00:00"}