{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:XKGMJADAWSV4CNBLMYHDGC5PIE","short_pith_number":"pith:XKGMJADA","schema_version":"1.0","canonical_sha256":"ba8cc48060b4abc1342b660e330baf410c27f66a395eb0805e7241fea0d39e42","source":{"kind":"arxiv","id":"2204.05148","version":2},"attestation_state":"computed","paper":{"title":"Speech Sequence Embeddings using Nearest Neighbors Contrastive Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Adel Nabli, Benoit Sagot, Emmanuel Dupoux, Robin Algayres","submitted_at":"2022-04-11T14:28:01Z","abstract_excerpt":"We introduce a simple neural encoder architecture that can be trained using an unsupervised contrastive learning objective which gets its positive samples from data-augmented k-Nearest Neighbors search. We show that when built on top of recent self-supervised audio representations, this method can be applied iteratively and yield competitive SSE as evaluated on two tasks: query-by-example of random sequences of speech, and spoken term discovery. On both tasks our method pushes the state-of-the-art by a significant margin across 5 different languages. Finally, we establish a benchmark on a quer"},"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":"2204.05148","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2022-04-11T14:28:01Z","cross_cats_sorted":[],"title_canon_sha256":"f178462a6c6f87b7f93a114f50f74b8a5df22ecd289b6d48a0a6f7464811b7df","abstract_canon_sha256":"229c02667bf083b9eae7047f23907ed80b04dd466abc0c1ee5e040f3533e9328"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:03:17.350753Z","signature_b64":"TysCYKwCteW/dJzxQwJJjikLFJVnKEVqZiFzj/y93CDIJO5+IUH8gdpD8uS9OoNaHz+eo5aOQIWwXnPC9gCcBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba8cc48060b4abc1342b660e330baf410c27f66a395eb0805e7241fea0d39e42","last_reissued_at":"2026-07-05T07:03:17.350349Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:03:17.350349Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Speech Sequence Embeddings using Nearest Neighbors Contrastive Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Adel Nabli, Benoit Sagot, Emmanuel Dupoux, Robin Algayres","submitted_at":"2022-04-11T14:28:01Z","abstract_excerpt":"We introduce a simple neural encoder architecture that can be trained using an unsupervised contrastive learning objective which gets its positive samples from data-augmented k-Nearest Neighbors search. We show that when built on top of recent self-supervised audio representations, this method can be applied iteratively and yield competitive SSE as evaluated on two tasks: query-by-example of random sequences of speech, and spoken term discovery. On both tasks our method pushes the state-of-the-art by a significant margin across 5 different languages. Finally, we establish a benchmark on a quer"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.05148","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/2204.05148/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":"2204.05148","created_at":"2026-07-05T07:03:17.350404+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.05148v2","created_at":"2026-07-05T07:03:17.350404+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.05148","created_at":"2026-07-05T07:03:17.350404+00:00"},{"alias_kind":"pith_short_12","alias_value":"XKGMJADAWSV4","created_at":"2026-07-05T07:03:17.350404+00:00"},{"alias_kind":"pith_short_16","alias_value":"XKGMJADAWSV4CNBL","created_at":"2026-07-05T07:03:17.350404+00:00"},{"alias_kind":"pith_short_8","alias_value":"XKGMJADA","created_at":"2026-07-05T07:03:17.350404+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/XKGMJADAWSV4CNBLMYHDGC5PIE","json":"https://pith.science/pith/XKGMJADAWSV4CNBLMYHDGC5PIE.json","graph_json":"https://pith.science/api/pith-number/XKGMJADAWSV4CNBLMYHDGC5PIE/graph.json","events_json":"https://pith.science/api/pith-number/XKGMJADAWSV4CNBLMYHDGC5PIE/events.json","paper":"https://pith.science/paper/XKGMJADA"},"agent_actions":{"view_html":"https://pith.science/pith/XKGMJADAWSV4CNBLMYHDGC5PIE","download_json":"https://pith.science/pith/XKGMJADAWSV4CNBLMYHDGC5PIE.json","view_paper":"https://pith.science/paper/XKGMJADA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.05148&json=true","fetch_graph":"https://pith.science/api/pith-number/XKGMJADAWSV4CNBLMYHDGC5PIE/graph.json","fetch_events":"https://pith.science/api/pith-number/XKGMJADAWSV4CNBLMYHDGC5PIE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XKGMJADAWSV4CNBLMYHDGC5PIE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XKGMJADAWSV4CNBLMYHDGC5PIE/action/storage_attestation","attest_author":"https://pith.science/pith/XKGMJADAWSV4CNBLMYHDGC5PIE/action/author_attestation","sign_citation":"https://pith.science/pith/XKGMJADAWSV4CNBLMYHDGC5PIE/action/citation_signature","submit_replication":"https://pith.science/pith/XKGMJADAWSV4CNBLMYHDGC5PIE/action/replication_record"}},"created_at":"2026-07-05T07:03:17.350404+00:00","updated_at":"2026-07-05T07:03:17.350404+00:00"}