{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:VDXAFL3BVS2522QSCOSQQ7MBT5","short_pith_number":"pith:VDXAFL3B","schema_version":"1.0","canonical_sha256":"a8ee02af61acb5dd6a1213a5087d819f7dccca96d31876c5f0a3558405e1c55d","source":{"kind":"arxiv","id":"2012.06185","version":2},"attestation_state":"computed","paper":{"title":"Exploring wav2vec 2.0 on speaker verification and language identification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Bo Xu, Meng Li, Shiyu Zhou, Zhiyun Fan","submitted_at":"2020-12-11T08:22:23Z","abstract_excerpt":"Wav2vec 2.0 is a recently proposed self-supervised framework for speech representation learning. It follows a two-stage training process of pre-training and fine-tuning, and performs well in speech recognition tasks especially ultra-low resource cases. In this work, we attempt to extend self-supervised framework to speaker verification and language identification. First, we use some preliminary experiments to indicate that wav2vec 2.0 can capture the information about the speaker and language. Then we demonstrate the effectiveness of wav2vec 2.0 on the two tasks respectively. For speaker verif"},"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":"2012.06185","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-12-11T08:22:23Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"8123414023bef81efd6ed56950a255268382a18bde3527fdddecf04154256de7","abstract_canon_sha256":"34e4036044cef488210cdabafdf0566bfef5ff3cb57b9578742e2f31db9d0ccb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:06:53.324292Z","signature_b64":"bySOcx/+BH7OTT7L1PwJL4CZotyVYFpddlUJNig0F9MkuoZRl16IrlNulHd94HrolRGZfpN0CtLRWW23sQbLBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8ee02af61acb5dd6a1213a5087d819f7dccca96d31876c5f0a3558405e1c55d","last_reissued_at":"2026-07-05T02:06:53.323800Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:06:53.323800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring wav2vec 2.0 on speaker verification and language identification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Bo Xu, Meng Li, Shiyu Zhou, Zhiyun Fan","submitted_at":"2020-12-11T08:22:23Z","abstract_excerpt":"Wav2vec 2.0 is a recently proposed self-supervised framework for speech representation learning. It follows a two-stage training process of pre-training and fine-tuning, and performs well in speech recognition tasks especially ultra-low resource cases. In this work, we attempt to extend self-supervised framework to speaker verification and language identification. First, we use some preliminary experiments to indicate that wav2vec 2.0 can capture the information about the speaker and language. Then we demonstrate the effectiveness of wav2vec 2.0 on the two tasks respectively. For speaker verif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.06185","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/2012.06185/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":"2012.06185","created_at":"2026-07-05T02:06:53.323857+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.06185v2","created_at":"2026-07-05T02:06:53.323857+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.06185","created_at":"2026-07-05T02:06:53.323857+00:00"},{"alias_kind":"pith_short_12","alias_value":"VDXAFL3BVS25","created_at":"2026-07-05T02:06:53.323857+00:00"},{"alias_kind":"pith_short_16","alias_value":"VDXAFL3BVS2522QS","created_at":"2026-07-05T02:06:53.323857+00:00"},{"alias_kind":"pith_short_8","alias_value":"VDXAFL3B","created_at":"2026-07-05T02:06:53.323857+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06392","citing_title":"InsideSSL: Understanding Self-Supervised Speech Representations using a Model-Centric Perspective","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VDXAFL3BVS2522QSCOSQQ7MBT5","json":"https://pith.science/pith/VDXAFL3BVS2522QSCOSQQ7MBT5.json","graph_json":"https://pith.science/api/pith-number/VDXAFL3BVS2522QSCOSQQ7MBT5/graph.json","events_json":"https://pith.science/api/pith-number/VDXAFL3BVS2522QSCOSQQ7MBT5/events.json","paper":"https://pith.science/paper/VDXAFL3B"},"agent_actions":{"view_html":"https://pith.science/pith/VDXAFL3BVS2522QSCOSQQ7MBT5","download_json":"https://pith.science/pith/VDXAFL3BVS2522QSCOSQQ7MBT5.json","view_paper":"https://pith.science/paper/VDXAFL3B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.06185&json=true","fetch_graph":"https://pith.science/api/pith-number/VDXAFL3BVS2522QSCOSQQ7MBT5/graph.json","fetch_events":"https://pith.science/api/pith-number/VDXAFL3BVS2522QSCOSQQ7MBT5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VDXAFL3BVS2522QSCOSQQ7MBT5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VDXAFL3BVS2522QSCOSQQ7MBT5/action/storage_attestation","attest_author":"https://pith.science/pith/VDXAFL3BVS2522QSCOSQQ7MBT5/action/author_attestation","sign_citation":"https://pith.science/pith/VDXAFL3BVS2522QSCOSQQ7MBT5/action/citation_signature","submit_replication":"https://pith.science/pith/VDXAFL3BVS2522QSCOSQQ7MBT5/action/replication_record"}},"created_at":"2026-07-05T02:06:53.323857+00:00","updated_at":"2026-07-05T02:06:53.323857+00:00"}