{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DEGYV5YNHKHBVBFSQGF65UFYUZ","short_pith_number":"pith:DEGYV5YN","schema_version":"1.0","canonical_sha256":"190d8af70d3a8e1a84b2818beed0b8a6485b855a4c4ed38d7668d2cb6c89efb1","source":{"kind":"arxiv","id":"2503.10446","version":1},"attestation_state":"computed","paper":{"title":"Whisper Speaker Identification: Leveraging Pre-Trained Multilingual Transformers for Robust Speaker Embeddings","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jakaria Islam Emon, Kazi Tamanna Alam, Md Abu Salek","submitted_at":"2025-03-13T15:11:28Z","abstract_excerpt":"Speaker identification in multilingual settings presents unique challenges, particularly when conventional models are predominantly trained on English data. In this paper, we propose WSI (Whisper Speaker Identification), a framework that repurposes the encoder of the Whisper automatic speech recognition model pre trained on extensive multilingual data to generate robust speaker embeddings via a joint loss optimization strategy that leverages online hard triplet mining and self supervised Normalized Temperature-scaled Cross Entropy loss. By capitalizing on Whisper language-agnostic acoustic rep"},"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":"2503.10446","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-03-13T15:11:28Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"2ab95862016dd4c01e80b14d4cf6e0b31e84880a7cb81546eef4c701fddc8d76","abstract_canon_sha256":"e53f37a8e0df1d368f795dc83848a726cb1f756b0886c263c3119c67bb046cb6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:30:45.484098Z","signature_b64":"VBr4nhnY0VItaK+91DZqVu81fGTAX5o6uS11n6OxL2DUTOkWCIjBUBVFnB1lwbaXASMReOtgqvDTk4jl/ZK0DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"190d8af70d3a8e1a84b2818beed0b8a6485b855a4c4ed38d7668d2cb6c89efb1","last_reissued_at":"2026-07-05T10:30:45.483478Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:30:45.483478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Whisper Speaker Identification: Leveraging Pre-Trained Multilingual Transformers for Robust Speaker Embeddings","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jakaria Islam Emon, Kazi Tamanna Alam, Md Abu Salek","submitted_at":"2025-03-13T15:11:28Z","abstract_excerpt":"Speaker identification in multilingual settings presents unique challenges, particularly when conventional models are predominantly trained on English data. In this paper, we propose WSI (Whisper Speaker Identification), a framework that repurposes the encoder of the Whisper automatic speech recognition model pre trained on extensive multilingual data to generate robust speaker embeddings via a joint loss optimization strategy that leverages online hard triplet mining and self supervised Normalized Temperature-scaled Cross Entropy loss. By capitalizing on Whisper language-agnostic acoustic rep"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.10446","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/2503.10446/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":"2503.10446","created_at":"2026-07-05T10:30:45.483546+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.10446v1","created_at":"2026-07-05T10:30:45.483546+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.10446","created_at":"2026-07-05T10:30:45.483546+00:00"},{"alias_kind":"pith_short_12","alias_value":"DEGYV5YNHKHB","created_at":"2026-07-05T10:30:45.483546+00:00"},{"alias_kind":"pith_short_16","alias_value":"DEGYV5YNHKHBVBFS","created_at":"2026-07-05T10:30:45.483546+00:00"},{"alias_kind":"pith_short_8","alias_value":"DEGYV5YN","created_at":"2026-07-05T10:30:45.483546+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12495","citing_title":"Missing-Token Prompted Reliability-Aware Fusion for Robust Polyglot Speaker Identification","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DEGYV5YNHKHBVBFSQGF65UFYUZ","json":"https://pith.science/pith/DEGYV5YNHKHBVBFSQGF65UFYUZ.json","graph_json":"https://pith.science/api/pith-number/DEGYV5YNHKHBVBFSQGF65UFYUZ/graph.json","events_json":"https://pith.science/api/pith-number/DEGYV5YNHKHBVBFSQGF65UFYUZ/events.json","paper":"https://pith.science/paper/DEGYV5YN"},"agent_actions":{"view_html":"https://pith.science/pith/DEGYV5YNHKHBVBFSQGF65UFYUZ","download_json":"https://pith.science/pith/DEGYV5YNHKHBVBFSQGF65UFYUZ.json","view_paper":"https://pith.science/paper/DEGYV5YN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.10446&json=true","fetch_graph":"https://pith.science/api/pith-number/DEGYV5YNHKHBVBFSQGF65UFYUZ/graph.json","fetch_events":"https://pith.science/api/pith-number/DEGYV5YNHKHBVBFSQGF65UFYUZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DEGYV5YNHKHBVBFSQGF65UFYUZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DEGYV5YNHKHBVBFSQGF65UFYUZ/action/storage_attestation","attest_author":"https://pith.science/pith/DEGYV5YNHKHBVBFSQGF65UFYUZ/action/author_attestation","sign_citation":"https://pith.science/pith/DEGYV5YNHKHBVBFSQGF65UFYUZ/action/citation_signature","submit_replication":"https://pith.science/pith/DEGYV5YNHKHBVBFSQGF65UFYUZ/action/replication_record"}},"created_at":"2026-07-05T10:30:45.483546+00:00","updated_at":"2026-07-05T10:30:45.483546+00:00"}