{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:ZXDBTPFWO57IZGW6XNTQ7YV6OR","short_pith_number":"pith:ZXDBTPFW","schema_version":"1.0","canonical_sha256":"cdc619bcb6777e8c9adebb670fe2be744ff4ad32961d92b04b9d829cfb6e708e","source":{"kind":"arxiv","id":"2007.04134","version":1},"attestation_state":"computed","paper":{"title":"Learning Speech Representations from Raw Audio by Joint Audiovisual Self-Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.LG","cs.MM","cs.SD"],"primary_cat":"eess.AS","authors_text":"Abhinav Shukla, Maja Pantic, Stavros Petridis","submitted_at":"2020-07-08T14:07:06Z","abstract_excerpt":"The intuitive interaction between the audio and visual modalities is valuable for cross-modal self-supervised learning. This concept has been demonstrated for generic audiovisual tasks like video action recognition and acoustic scene classification. However, self-supervision remains under-explored for audiovisual speech. We propose a method to learn self-supervised speech representations from the raw audio waveform. We train a raw audio encoder by combining audio-only self-supervision (by predicting informative audio attributes) with visual self-supervision (by generating talking faces from au"},"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":"2007.04134","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-07-08T14:07:06Z","cross_cats_sorted":["cs.CL","cs.CV","cs.LG","cs.MM","cs.SD"],"title_canon_sha256":"c60546038ad8036ad42c2f13ccd3650b6f01ddd4d86420108237c7c794ce2647","abstract_canon_sha256":"16e1498c80f29741fe517e63f2af951188060fa7c7d7fb7e8e7193859c4ae03f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:18:04.807535Z","signature_b64":"0Pc/sQdj+bgGKW6jApk5KBoX4KpgP2oW/OOJ9x4bIPCNWuSFKpDNQumTqC9JpgoO9MF7LDuRg5Ir8NYl7JaLCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cdc619bcb6777e8c9adebb670fe2be744ff4ad32961d92b04b9d829cfb6e708e","last_reissued_at":"2026-07-05T01:18:04.807132Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:18:04.807132Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Speech Representations from Raw Audio by Joint Audiovisual Self-Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.LG","cs.MM","cs.SD"],"primary_cat":"eess.AS","authors_text":"Abhinav Shukla, Maja Pantic, Stavros Petridis","submitted_at":"2020-07-08T14:07:06Z","abstract_excerpt":"The intuitive interaction between the audio and visual modalities is valuable for cross-modal self-supervised learning. This concept has been demonstrated for generic audiovisual tasks like video action recognition and acoustic scene classification. However, self-supervision remains under-explored for audiovisual speech. We propose a method to learn self-supervised speech representations from the raw audio waveform. We train a raw audio encoder by combining audio-only self-supervision (by predicting informative audio attributes) with visual self-supervision (by generating talking faces from au"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.04134","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/2007.04134/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":"2007.04134","created_at":"2026-07-05T01:18:04.807189+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.04134v1","created_at":"2026-07-05T01:18:04.807189+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.04134","created_at":"2026-07-05T01:18:04.807189+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZXDBTPFWO57I","created_at":"2026-07-05T01:18:04.807189+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZXDBTPFWO57IZGW6","created_at":"2026-07-05T01:18:04.807189+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZXDBTPFW","created_at":"2026-07-05T01:18:04.807189+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.20838","citing_title":"USV: Towards Understanding the User-generated Short-form Videos","ref_index":64,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZXDBTPFWO57IZGW6XNTQ7YV6OR","json":"https://pith.science/pith/ZXDBTPFWO57IZGW6XNTQ7YV6OR.json","graph_json":"https://pith.science/api/pith-number/ZXDBTPFWO57IZGW6XNTQ7YV6OR/graph.json","events_json":"https://pith.science/api/pith-number/ZXDBTPFWO57IZGW6XNTQ7YV6OR/events.json","paper":"https://pith.science/paper/ZXDBTPFW"},"agent_actions":{"view_html":"https://pith.science/pith/ZXDBTPFWO57IZGW6XNTQ7YV6OR","download_json":"https://pith.science/pith/ZXDBTPFWO57IZGW6XNTQ7YV6OR.json","view_paper":"https://pith.science/paper/ZXDBTPFW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.04134&json=true","fetch_graph":"https://pith.science/api/pith-number/ZXDBTPFWO57IZGW6XNTQ7YV6OR/graph.json","fetch_events":"https://pith.science/api/pith-number/ZXDBTPFWO57IZGW6XNTQ7YV6OR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZXDBTPFWO57IZGW6XNTQ7YV6OR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZXDBTPFWO57IZGW6XNTQ7YV6OR/action/storage_attestation","attest_author":"https://pith.science/pith/ZXDBTPFWO57IZGW6XNTQ7YV6OR/action/author_attestation","sign_citation":"https://pith.science/pith/ZXDBTPFWO57IZGW6XNTQ7YV6OR/action/citation_signature","submit_replication":"https://pith.science/pith/ZXDBTPFWO57IZGW6XNTQ7YV6OR/action/replication_record"}},"created_at":"2026-07-05T01:18:04.807189+00:00","updated_at":"2026-07-05T01:18:04.807189+00:00"}