{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:FVXGPRTCA6CEBTX3RZPDG4RBKM","short_pith_number":"pith:FVXGPRTC","schema_version":"1.0","canonical_sha256":"2d6e67c662078440cefb8e5e337221532331b5892b473f7e4e848055bcab6790","source":{"kind":"arxiv","id":"2106.02170","version":1},"attestation_state":"computed","paper":{"title":"Segmental Contrastive Predictive Coding for Unsupervised Word Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Jes\\'us Villalba, Laureano Moro-Velazquez, Najim Dehak, Piotr \\.Zelasko, Saurabhchand Bhati","submitted_at":"2021-06-03T23:12:05Z","abstract_excerpt":"Automatic detection of phoneme or word-like units is one of the core objectives in zero-resource speech processing. Recent attempts employ self-supervised training methods, such as contrastive predictive coding (CPC), where the next frame is predicted given past context. However, CPC only looks at the audio signal's frame-level structure. We overcome this limitation with a segmental contrastive predictive coding (SCPC) framework that can model the signal structure at a higher level e.g. at the phoneme level. In this framework, a convolutional neural network learns frame-level representation fr"},"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":"2106.02170","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-06-03T23:12:05Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"5d2dead7e5bcf41b41a253eecf88e83cafe66d68f7f2258ddc85d83bf356298d","abstract_canon_sha256":"dc50977d24d6c6f6eb91c908b5165c07733cca61f38bfda540f29f57df64cd86"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:46:16.107715Z","signature_b64":"tHCwKoFTGXYPNq+uIhi8UbFhyk6OM4TxDz4pM3XKa1URnedYZl9blnSFa8cIuuVP/OlrrTBv0Uhe99bxxUxDBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d6e67c662078440cefb8e5e337221532331b5892b473f7e4e848055bcab6790","last_reissued_at":"2026-07-05T02:46:16.107327Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:46:16.107327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Segmental Contrastive Predictive Coding for Unsupervised Word Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Jes\\'us Villalba, Laureano Moro-Velazquez, Najim Dehak, Piotr \\.Zelasko, Saurabhchand Bhati","submitted_at":"2021-06-03T23:12:05Z","abstract_excerpt":"Automatic detection of phoneme or word-like units is one of the core objectives in zero-resource speech processing. Recent attempts employ self-supervised training methods, such as contrastive predictive coding (CPC), where the next frame is predicted given past context. However, CPC only looks at the audio signal's frame-level structure. We overcome this limitation with a segmental contrastive predictive coding (SCPC) framework that can model the signal structure at a higher level e.g. at the phoneme level. In this framework, a convolutional neural network learns frame-level representation fr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.02170","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/2106.02170/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":"2106.02170","created_at":"2026-07-05T02:46:16.107381+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.02170v1","created_at":"2026-07-05T02:46:16.107381+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.02170","created_at":"2026-07-05T02:46:16.107381+00:00"},{"alias_kind":"pith_short_12","alias_value":"FVXGPRTCA6CE","created_at":"2026-07-05T02:46:16.107381+00:00"},{"alias_kind":"pith_short_16","alias_value":"FVXGPRTCA6CEBTX3","created_at":"2026-07-05T02:46:16.107381+00:00"},{"alias_kind":"pith_short_8","alias_value":"FVXGPRTC","created_at":"2026-07-05T02:46:16.107381+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/FVXGPRTCA6CEBTX3RZPDG4RBKM","json":"https://pith.science/pith/FVXGPRTCA6CEBTX3RZPDG4RBKM.json","graph_json":"https://pith.science/api/pith-number/FVXGPRTCA6CEBTX3RZPDG4RBKM/graph.json","events_json":"https://pith.science/api/pith-number/FVXGPRTCA6CEBTX3RZPDG4RBKM/events.json","paper":"https://pith.science/paper/FVXGPRTC"},"agent_actions":{"view_html":"https://pith.science/pith/FVXGPRTCA6CEBTX3RZPDG4RBKM","download_json":"https://pith.science/pith/FVXGPRTCA6CEBTX3RZPDG4RBKM.json","view_paper":"https://pith.science/paper/FVXGPRTC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.02170&json=true","fetch_graph":"https://pith.science/api/pith-number/FVXGPRTCA6CEBTX3RZPDG4RBKM/graph.json","fetch_events":"https://pith.science/api/pith-number/FVXGPRTCA6CEBTX3RZPDG4RBKM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FVXGPRTCA6CEBTX3RZPDG4RBKM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FVXGPRTCA6CEBTX3RZPDG4RBKM/action/storage_attestation","attest_author":"https://pith.science/pith/FVXGPRTCA6CEBTX3RZPDG4RBKM/action/author_attestation","sign_citation":"https://pith.science/pith/FVXGPRTCA6CEBTX3RZPDG4RBKM/action/citation_signature","submit_replication":"https://pith.science/pith/FVXGPRTCA6CEBTX3RZPDG4RBKM/action/replication_record"}},"created_at":"2026-07-05T02:46:16.107381+00:00","updated_at":"2026-07-05T02:46:16.107381+00:00"}