{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:IY7WS2PGED5NNSGEI7KJSACDDC","short_pith_number":"pith:IY7WS2PG","schema_version":"1.0","canonical_sha256":"463f6969e620fad6c8c447d4990043188556a0e05db7608347e54a62884bff15","source":{"kind":"arxiv","id":"2104.14700","version":2},"attestation_state":"computed","paper":{"title":"The Zero Resource Speech Challenge 2021: Spoken language modelling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Emmanuel Dupoux, Eugene Kharitonov, Ewan Dunbar, Mathieu Bernard, Maureen de Seyssel, Morgane Rivi\\`ere, Nicolas Hamilakis, Patricia Roz\\'e, Tu Anh Nguyen","submitted_at":"2021-04-29T23:53:37Z","abstract_excerpt":"We present the Zero Resource Speech Challenge 2021, which asks participants to learn a language model directly from audio, without any text or labels. The challenge is based on the Libri-light dataset, which provides up to 60k hours of audio from English audio books without any associated text. We provide a pipeline baseline system consisting on an encoder based on contrastive predictive coding (CPC), a quantizer ($k$-means) and a standard language model (BERT or LSTM). The metrics evaluate the learned representations at the acoustic (ABX discrimination), lexical (spot-the-word), syntactic (ac"},"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":"2104.14700","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-29T23:53:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"27c963d728b3dd80a549020d17f9f398fdfbf7a8d18a4c44b1b117d3dff9e158","abstract_canon_sha256":"a3743a2fd559def5538e4bf70fc34e7791a4f82710381ed58c5249f9e65df8a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:04:24.324583Z","signature_b64":"/eV7jJ8hmouDF5XZuaBq42gsg6YxXY+pi1MkOZUn0vHVcK1UWxrnnM+GjZ388ApaiNjtUCiwr/R6yOCdSX2hCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"463f6969e620fad6c8c447d4990043188556a0e05db7608347e54a62884bff15","last_reissued_at":"2026-07-05T03:04:24.324097Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:04:24.324097Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Zero Resource Speech Challenge 2021: Spoken language modelling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Emmanuel Dupoux, Eugene Kharitonov, Ewan Dunbar, Mathieu Bernard, Maureen de Seyssel, Morgane Rivi\\`ere, Nicolas Hamilakis, Patricia Roz\\'e, Tu Anh Nguyen","submitted_at":"2021-04-29T23:53:37Z","abstract_excerpt":"We present the Zero Resource Speech Challenge 2021, which asks participants to learn a language model directly from audio, without any text or labels. The challenge is based on the Libri-light dataset, which provides up to 60k hours of audio from English audio books without any associated text. We provide a pipeline baseline system consisting on an encoder based on contrastive predictive coding (CPC), a quantizer ($k$-means) and a standard language model (BERT or LSTM). The metrics evaluate the learned representations at the acoustic (ABX discrimination), lexical (spot-the-word), syntactic (ac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.14700","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/2104.14700/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":"2104.14700","created_at":"2026-07-05T03:04:24.324156+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.14700v2","created_at":"2026-07-05T03:04:24.324156+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.14700","created_at":"2026-07-05T03:04:24.324156+00:00"},{"alias_kind":"pith_short_12","alias_value":"IY7WS2PGED5N","created_at":"2026-07-05T03:04:24.324156+00:00"},{"alias_kind":"pith_short_16","alias_value":"IY7WS2PGED5NNSGE","created_at":"2026-07-05T03:04:24.324156+00:00"},{"alias_kind":"pith_short_8","alias_value":"IY7WS2PG","created_at":"2026-07-05T03:04:24.324156+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.15456","citing_title":"Factorized RVQ-GAN For Disentangled Speech Tokenization","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IY7WS2PGED5NNSGEI7KJSACDDC","json":"https://pith.science/pith/IY7WS2PGED5NNSGEI7KJSACDDC.json","graph_json":"https://pith.science/api/pith-number/IY7WS2PGED5NNSGEI7KJSACDDC/graph.json","events_json":"https://pith.science/api/pith-number/IY7WS2PGED5NNSGEI7KJSACDDC/events.json","paper":"https://pith.science/paper/IY7WS2PG"},"agent_actions":{"view_html":"https://pith.science/pith/IY7WS2PGED5NNSGEI7KJSACDDC","download_json":"https://pith.science/pith/IY7WS2PGED5NNSGEI7KJSACDDC.json","view_paper":"https://pith.science/paper/IY7WS2PG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.14700&json=true","fetch_graph":"https://pith.science/api/pith-number/IY7WS2PGED5NNSGEI7KJSACDDC/graph.json","fetch_events":"https://pith.science/api/pith-number/IY7WS2PGED5NNSGEI7KJSACDDC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IY7WS2PGED5NNSGEI7KJSACDDC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IY7WS2PGED5NNSGEI7KJSACDDC/action/storage_attestation","attest_author":"https://pith.science/pith/IY7WS2PGED5NNSGEI7KJSACDDC/action/author_attestation","sign_citation":"https://pith.science/pith/IY7WS2PGED5NNSGEI7KJSACDDC/action/citation_signature","submit_replication":"https://pith.science/pith/IY7WS2PGED5NNSGEI7KJSACDDC/action/replication_record"}},"created_at":"2026-07-05T03:04:24.324156+00:00","updated_at":"2026-07-05T03:04:24.324156+00:00"}