{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:BCVWXPWNOWCYJGGGHLJBJWMVVK","short_pith_number":"pith:BCVWXPWN","schema_version":"1.0","canonical_sha256":"08ab6bbecd75858498c63ad214d995aa9d8265ab797b65a5c9c7ff0c46658d2e","source":{"kind":"arxiv","id":"2110.05777","version":2},"attestation_state":"computed","paper":{"title":"Large-scale Self-Supervised Speech Representation Learning for Automatic Speaker Verification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Chengyi Wang, Michael Zeng, Sanyuan Chen, Shujie Liu, Yanmin Qian, Yao Qian, Yu Wu, Zhengyang Chen","submitted_at":"2021-10-12T07:15:21Z","abstract_excerpt":"The speech representations learned from large-scale unlabeled data have shown better generalizability than those from supervised learning and thus attract a lot of interest to be applied for various downstream tasks. In this paper, we explore the limits of speech representations learned by different self-supervised objectives and datasets for automatic speaker verification (ASV), especially with a well-recognized SOTA ASV model, ECAPA-TDNN [1], as a downstream model. The representations from all hidden layers of the pre-trained model are firstly averaged with learnable weights and then fed int"},"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":"2110.05777","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-10-12T07:15:21Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"aa9031f41cd2648929ec68aa3df0185efc1e45cdaa25cf02db3f842fb6f170b7","abstract_canon_sha256":"cf0c53cbfd86ea2e9c42a34e1f9dabcb01a59620492d9c6f72e1995fbf795bfc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:50:51.605913Z","signature_b64":"QNrmXYFRG2xBW/8RGdP+H/3KatfQdjDJHe7yLonkPgwsTIxZ8MfkBTNTleJl5BCE+4otW7em7AKMyTjVUlwFCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08ab6bbecd75858498c63ad214d995aa9d8265ab797b65a5c9c7ff0c46658d2e","last_reissued_at":"2026-07-05T03:50:51.605471Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:50:51.605471Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large-scale Self-Supervised Speech Representation Learning for Automatic Speaker Verification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Chengyi Wang, Michael Zeng, Sanyuan Chen, Shujie Liu, Yanmin Qian, Yao Qian, Yu Wu, Zhengyang Chen","submitted_at":"2021-10-12T07:15:21Z","abstract_excerpt":"The speech representations learned from large-scale unlabeled data have shown better generalizability than those from supervised learning and thus attract a lot of interest to be applied for various downstream tasks. In this paper, we explore the limits of speech representations learned by different self-supervised objectives and datasets for automatic speaker verification (ASV), especially with a well-recognized SOTA ASV model, ECAPA-TDNN [1], as a downstream model. The representations from all hidden layers of the pre-trained model are firstly averaged with learnable weights and then fed int"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.05777","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/2110.05777/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":"2110.05777","created_at":"2026-07-05T03:50:51.605527+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.05777v2","created_at":"2026-07-05T03:50:51.605527+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.05777","created_at":"2026-07-05T03:50:51.605527+00:00"},{"alias_kind":"pith_short_12","alias_value":"BCVWXPWNOWCY","created_at":"2026-07-05T03:50:51.605527+00:00"},{"alias_kind":"pith_short_16","alias_value":"BCVWXPWNOWCYJGGG","created_at":"2026-07-05T03:50:51.605527+00:00"},{"alias_kind":"pith_short_8","alias_value":"BCVWXPWN","created_at":"2026-07-05T03:50:51.605527+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/BCVWXPWNOWCYJGGGHLJBJWMVVK","json":"https://pith.science/pith/BCVWXPWNOWCYJGGGHLJBJWMVVK.json","graph_json":"https://pith.science/api/pith-number/BCVWXPWNOWCYJGGGHLJBJWMVVK/graph.json","events_json":"https://pith.science/api/pith-number/BCVWXPWNOWCYJGGGHLJBJWMVVK/events.json","paper":"https://pith.science/paper/BCVWXPWN"},"agent_actions":{"view_html":"https://pith.science/pith/BCVWXPWNOWCYJGGGHLJBJWMVVK","download_json":"https://pith.science/pith/BCVWXPWNOWCYJGGGHLJBJWMVVK.json","view_paper":"https://pith.science/paper/BCVWXPWN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.05777&json=true","fetch_graph":"https://pith.science/api/pith-number/BCVWXPWNOWCYJGGGHLJBJWMVVK/graph.json","fetch_events":"https://pith.science/api/pith-number/BCVWXPWNOWCYJGGGHLJBJWMVVK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BCVWXPWNOWCYJGGGHLJBJWMVVK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BCVWXPWNOWCYJGGGHLJBJWMVVK/action/storage_attestation","attest_author":"https://pith.science/pith/BCVWXPWNOWCYJGGGHLJBJWMVVK/action/author_attestation","sign_citation":"https://pith.science/pith/BCVWXPWNOWCYJGGGHLJBJWMVVK/action/citation_signature","submit_replication":"https://pith.science/pith/BCVWXPWNOWCYJGGGHLJBJWMVVK/action/replication_record"}},"created_at":"2026-07-05T03:50:51.605527+00:00","updated_at":"2026-07-05T03:50:51.605527+00:00"}