{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZAN2G3SADG6OQUTCN57TW2EJEE","short_pith_number":"pith:ZAN2G3SA","schema_version":"1.0","canonical_sha256":"c81ba36e4019bce852626f7f3b68892135f2728d732b8450b0804b629a1b1a69","source":{"kind":"arxiv","id":"2402.00340","version":2},"attestation_state":"computed","paper":{"title":"Can you Remove the Downstream Model for Speaker Recognition with Self-Supervised Speech Features?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Ahmed Hussen Abdelaziz, Barry-John Theobald, Jee-weon Jung, Shinji Watanabe, Skyler Seto, Stephen Shum, Takuya Higuchi, Tatiana Likhomanenko, Zakaria Aldeneh","submitted_at":"2024-02-01T05:03:05Z","abstract_excerpt":"Self-supervised features are typically used in place of filter-bank features in speaker verification models. However, these models were originally designed to ingest filter-bank features as inputs, and thus, training them on top of self-supervised features assumes that both feature types require the same amount of learning for the task. In this work, we observe that pre-trained self-supervised speech features inherently include information required for downstream speaker verification task, and therefore, we can simplify the downstream model without sacrificing performance. To this end, we revi"},"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":"2402.00340","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-02-01T05:03:05Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"d5f343ca448dc347a2cd0e7d2b85540879563eb4c479a03a896b8d6bc98845ad","abstract_canon_sha256":"7e13c45edbf183ed0fbbef11d33e055fbc4ff9beb7e5d752db813157ebf1d4fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:11.146650Z","signature_b64":"Krkcckspm5jDssUsmXgVTdhAb1JGqKYZwKXkdHIuJrh2HDydr1eackvqBfGHcCORnVYtRKlOR9XhYqfA+NwHDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c81ba36e4019bce852626f7f3b68892135f2728d732b8450b0804b629a1b1a69","last_reissued_at":"2026-07-05T08:31:11.146134Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:11.146134Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can you Remove the Downstream Model for Speaker Recognition with Self-Supervised Speech Features?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Ahmed Hussen Abdelaziz, Barry-John Theobald, Jee-weon Jung, Shinji Watanabe, Skyler Seto, Stephen Shum, Takuya Higuchi, Tatiana Likhomanenko, Zakaria Aldeneh","submitted_at":"2024-02-01T05:03:05Z","abstract_excerpt":"Self-supervised features are typically used in place of filter-bank features in speaker verification models. However, these models were originally designed to ingest filter-bank features as inputs, and thus, training them on top of self-supervised features assumes that both feature types require the same amount of learning for the task. In this work, we observe that pre-trained self-supervised speech features inherently include information required for downstream speaker verification task, and therefore, we can simplify the downstream model without sacrificing performance. To this end, we revi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.00340","kind":"arxiv","version":2},"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/2402.00340/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":"2402.00340","created_at":"2026-07-05T08:31:11.146195+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.00340v2","created_at":"2026-07-05T08:31:11.146195+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.00340","created_at":"2026-07-05T08:31:11.146195+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZAN2G3SADG6O","created_at":"2026-07-05T08:31:11.146195+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZAN2G3SADG6OQUTC","created_at":"2026-07-05T08:31:11.146195+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZAN2G3SA","created_at":"2026-07-05T08:31:11.146195+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/ZAN2G3SADG6OQUTCN57TW2EJEE","json":"https://pith.science/pith/ZAN2G3SADG6OQUTCN57TW2EJEE.json","graph_json":"https://pith.science/api/pith-number/ZAN2G3SADG6OQUTCN57TW2EJEE/graph.json","events_json":"https://pith.science/api/pith-number/ZAN2G3SADG6OQUTCN57TW2EJEE/events.json","paper":"https://pith.science/paper/ZAN2G3SA"},"agent_actions":{"view_html":"https://pith.science/pith/ZAN2G3SADG6OQUTCN57TW2EJEE","download_json":"https://pith.science/pith/ZAN2G3SADG6OQUTCN57TW2EJEE.json","view_paper":"https://pith.science/paper/ZAN2G3SA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.00340&json=true","fetch_graph":"https://pith.science/api/pith-number/ZAN2G3SADG6OQUTCN57TW2EJEE/graph.json","fetch_events":"https://pith.science/api/pith-number/ZAN2G3SADG6OQUTCN57TW2EJEE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZAN2G3SADG6OQUTCN57TW2EJEE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZAN2G3SADG6OQUTCN57TW2EJEE/action/storage_attestation","attest_author":"https://pith.science/pith/ZAN2G3SADG6OQUTCN57TW2EJEE/action/author_attestation","sign_citation":"https://pith.science/pith/ZAN2G3SADG6OQUTCN57TW2EJEE/action/citation_signature","submit_replication":"https://pith.science/pith/ZAN2G3SADG6OQUTCN57TW2EJEE/action/replication_record"}},"created_at":"2026-07-05T08:31:11.146195+00:00","updated_at":"2026-07-05T08:31:11.146195+00:00"}