{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:3RHEBHWL433TH3QF3NBBTF37OB","short_pith_number":"pith:3RHEBHWL","schema_version":"1.0","canonical_sha256":"dc4e409ecbe6f733ee05db4219977f7052b4a97c72c39665d34094e90439d841","source":{"kind":"arxiv","id":"2210.04062","version":3},"attestation_state":"computed","paper":{"title":"CoBERT: Self-Supervised Speech Representation Learning Through Code Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Chutong Meng, Haizhou Li, Junyi Ao, Mingxuan Wang, Tom Ko","submitted_at":"2022-10-08T17:15:46Z","abstract_excerpt":"Speech is the surface form of a finite set of phonetic units, which can be represented by discrete codes. We propose the Code BERT (CoBERT) approach for self-supervised speech representation learning. The idea is to convert an utterance to a sequence of discrete codes, and perform code representation learning, where we predict the code representations based on a masked view of the original speech input. Unlike the prior self-distillation approaches of which the teacher and the student are of the same modality, our target model predicts representations from a different modality. CoBERT outperfo"},"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":"2210.04062","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-10-08T17:15:46Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"db4856cb2a5beed9a69a0771f0b2382625cc3e3a49ffa762cf26d76f1a07583f","abstract_canon_sha256":"c021e9bb88d314470657d6202ff5182b079d5f0c98b1d7a52f0a1c5dc33dc990"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:27:42.625532Z","signature_b64":"j6Womz7wLIqASEXDmCLbUwexyT7rTJU4xSrvqZh0iFV1M24nZFhLMdhIV5Cx5zxa/Spcqps7ybKyTPvk3ZrJAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc4e409ecbe6f733ee05db4219977f7052b4a97c72c39665d34094e90439d841","last_reissued_at":"2026-07-05T06:27:42.625030Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:27:42.625030Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CoBERT: Self-Supervised Speech Representation Learning Through Code Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Chutong Meng, Haizhou Li, Junyi Ao, Mingxuan Wang, Tom Ko","submitted_at":"2022-10-08T17:15:46Z","abstract_excerpt":"Speech is the surface form of a finite set of phonetic units, which can be represented by discrete codes. We propose the Code BERT (CoBERT) approach for self-supervised speech representation learning. The idea is to convert an utterance to a sequence of discrete codes, and perform code representation learning, where we predict the code representations based on a masked view of the original speech input. Unlike the prior self-distillation approaches of which the teacher and the student are of the same modality, our target model predicts representations from a different modality. CoBERT outperfo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.04062","kind":"arxiv","version":3},"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/2210.04062/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":"2210.04062","created_at":"2026-07-05T06:27:42.625097+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.04062v3","created_at":"2026-07-05T06:27:42.625097+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.04062","created_at":"2026-07-05T06:27:42.625097+00:00"},{"alias_kind":"pith_short_12","alias_value":"3RHEBHWL433T","created_at":"2026-07-05T06:27:42.625097+00:00"},{"alias_kind":"pith_short_16","alias_value":"3RHEBHWL433TH3QF","created_at":"2026-07-05T06:27:42.625097+00:00"},{"alias_kind":"pith_short_8","alias_value":"3RHEBHWL","created_at":"2026-07-05T06:27:42.625097+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/3RHEBHWL433TH3QF3NBBTF37OB","json":"https://pith.science/pith/3RHEBHWL433TH3QF3NBBTF37OB.json","graph_json":"https://pith.science/api/pith-number/3RHEBHWL433TH3QF3NBBTF37OB/graph.json","events_json":"https://pith.science/api/pith-number/3RHEBHWL433TH3QF3NBBTF37OB/events.json","paper":"https://pith.science/paper/3RHEBHWL"},"agent_actions":{"view_html":"https://pith.science/pith/3RHEBHWL433TH3QF3NBBTF37OB","download_json":"https://pith.science/pith/3RHEBHWL433TH3QF3NBBTF37OB.json","view_paper":"https://pith.science/paper/3RHEBHWL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.04062&json=true","fetch_graph":"https://pith.science/api/pith-number/3RHEBHWL433TH3QF3NBBTF37OB/graph.json","fetch_events":"https://pith.science/api/pith-number/3RHEBHWL433TH3QF3NBBTF37OB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3RHEBHWL433TH3QF3NBBTF37OB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3RHEBHWL433TH3QF3NBBTF37OB/action/storage_attestation","attest_author":"https://pith.science/pith/3RHEBHWL433TH3QF3NBBTF37OB/action/author_attestation","sign_citation":"https://pith.science/pith/3RHEBHWL433TH3QF3NBBTF37OB/action/citation_signature","submit_replication":"https://pith.science/pith/3RHEBHWL433TH3QF3NBBTF37OB/action/replication_record"}},"created_at":"2026-07-05T06:27:42.625097+00:00","updated_at":"2026-07-05T06:27:42.625097+00:00"}