{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FGAED6GVH3RZM2WC5QEEKYDMUP","short_pith_number":"pith:FGAED6GV","schema_version":"1.0","canonical_sha256":"298041f8d53ee3966ac2ec0845606ca3fafc1342d65739d87062d8f1f3890bad","source":{"kind":"arxiv","id":"2412.04425","version":1},"attestation_state":"computed","paper":{"title":"CA-SSLR: Condition-Aware Self-Supervised Learning Representation for Generalized Speech Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Ariya Rastrow, Jesus Villalba, Jing Liu, Laureano Moro-Velazquez, Najim Dehak, Thomas Thebaud, Yen-Ju Lu","submitted_at":"2024-12-05T18:51:10Z","abstract_excerpt":"We introduce Condition-Aware Self-Supervised Learning Representation (CA-SSLR), a generalist conditioning model broadly applicable to various speech-processing tasks. Compared to standard fine-tuning methods that optimize for downstream models, CA-SSLR integrates language and speaker embeddings from earlier layers, making the SSL model aware of the current language and speaker context. This approach reduces the reliance on input audio features while preserving the integrity of the base SSLR. CA-SSLR improves the model's capabilities and demonstrates its generality on unseen tasks with minimal "},"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":"2412.04425","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-12-05T18:51:10Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"fdddea1352e01825cb85ed53761bc0e55e10a4ba6d337ce8b849a753d6227a93","abstract_canon_sha256":"c66599f3da9b0224d26400f09ae79cbb3a4e3f8c8dff8cf6c4e744b1492d1a94"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:03.776787Z","signature_b64":"U1dgYiYVlqVT6gVTz5pyMavi8G0Th8mY7ZMwhp52l3NxS5gVQmul24em11qtiihKHOImzvmzrbGOgtMBvaW/Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"298041f8d53ee3966ac2ec0845606ca3fafc1342d65739d87062d8f1f3890bad","last_reissued_at":"2026-07-05T09:45:03.776290Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:03.776290Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CA-SSLR: Condition-Aware Self-Supervised Learning Representation for Generalized Speech Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Ariya Rastrow, Jesus Villalba, Jing Liu, Laureano Moro-Velazquez, Najim Dehak, Thomas Thebaud, Yen-Ju Lu","submitted_at":"2024-12-05T18:51:10Z","abstract_excerpt":"We introduce Condition-Aware Self-Supervised Learning Representation (CA-SSLR), a generalist conditioning model broadly applicable to various speech-processing tasks. Compared to standard fine-tuning methods that optimize for downstream models, CA-SSLR integrates language and speaker embeddings from earlier layers, making the SSL model aware of the current language and speaker context. This approach reduces the reliance on input audio features while preserving the integrity of the base SSLR. CA-SSLR improves the model's capabilities and demonstrates its generality on unseen tasks with minimal "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04425","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/2412.04425/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":"2412.04425","created_at":"2026-07-05T09:45:03.776360+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.04425v1","created_at":"2026-07-05T09:45:03.776360+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04425","created_at":"2026-07-05T09:45:03.776360+00:00"},{"alias_kind":"pith_short_12","alias_value":"FGAED6GVH3RZ","created_at":"2026-07-05T09:45:03.776360+00:00"},{"alias_kind":"pith_short_16","alias_value":"FGAED6GVH3RZM2WC","created_at":"2026-07-05T09:45:03.776360+00:00"},{"alias_kind":"pith_short_8","alias_value":"FGAED6GV","created_at":"2026-07-05T09:45:03.776360+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FGAED6GVH3RZM2WC5QEEKYDMUP","json":"https://pith.science/pith/FGAED6GVH3RZM2WC5QEEKYDMUP.json","graph_json":"https://pith.science/api/pith-number/FGAED6GVH3RZM2WC5QEEKYDMUP/graph.json","events_json":"https://pith.science/api/pith-number/FGAED6GVH3RZM2WC5QEEKYDMUP/events.json","paper":"https://pith.science/paper/FGAED6GV"},"agent_actions":{"view_html":"https://pith.science/pith/FGAED6GVH3RZM2WC5QEEKYDMUP","download_json":"https://pith.science/pith/FGAED6GVH3RZM2WC5QEEKYDMUP.json","view_paper":"https://pith.science/paper/FGAED6GV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.04425&json=true","fetch_graph":"https://pith.science/api/pith-number/FGAED6GVH3RZM2WC5QEEKYDMUP/graph.json","fetch_events":"https://pith.science/api/pith-number/FGAED6GVH3RZM2WC5QEEKYDMUP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FGAED6GVH3RZM2WC5QEEKYDMUP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FGAED6GVH3RZM2WC5QEEKYDMUP/action/storage_attestation","attest_author":"https://pith.science/pith/FGAED6GVH3RZM2WC5QEEKYDMUP/action/author_attestation","sign_citation":"https://pith.science/pith/FGAED6GVH3RZM2WC5QEEKYDMUP/action/citation_signature","submit_replication":"https://pith.science/pith/FGAED6GVH3RZM2WC5QEEKYDMUP/action/replication_record"}},"created_at":"2026-07-05T09:45:03.776360+00:00","updated_at":"2026-07-05T09:45:03.776360+00:00"}