{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:KZT3ZSOYR3YD46DFHXH6TQR3TQ","short_pith_number":"pith:KZT3ZSOY","schema_version":"1.0","canonical_sha256":"5667bcc9d88ef03e78653dcfe9c23b9c389b5c50576d414c158eb252d094819d","source":{"kind":"arxiv","id":"1910.05453","version":3},"attestation_state":"computed","paper":{"title":"vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Alexei Baevski, Michael Auli, Steffen Schneider","submitted_at":"2019-10-12T00:55:06Z","abstract_excerpt":"We propose vq-wav2vec to learn discrete representations of audio segments through a wav2vec-style self-supervised context prediction task. The algorithm uses either a gumbel softmax or online k-means clustering to quantize the dense representations. Discretization enables the direct application of algorithms from the NLP community which require discrete inputs. Experiments show that BERT pre-training achieves a new state of the art on TIMIT phoneme classification and WSJ speech recognition."},"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":"1910.05453","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-12T00:55:06Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d864eca84425c5d1e04116a896c09ed7c91395a0814e5edce20539a1fb908672","abstract_canon_sha256":"6d4e736c6d398e284835c1628b0a2222c637b82d12947dfede6a6070443ad3a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:40:59.303051Z","signature_b64":"mAEpYZ6XA+OH8TYZDQgyIq/6W7Mwlf/r241U6uq99Oa+2YCQkvlhnGROOcLPJsJ0DXwA3xsIL9uMPOHRreNMAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5667bcc9d88ef03e78653dcfe9c23b9c389b5c50576d414c158eb252d094819d","last_reissued_at":"2026-07-05T00:40:59.302675Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:40:59.302675Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Alexei Baevski, Michael Auli, Steffen Schneider","submitted_at":"2019-10-12T00:55:06Z","abstract_excerpt":"We propose vq-wav2vec to learn discrete representations of audio segments through a wav2vec-style self-supervised context prediction task. The algorithm uses either a gumbel softmax or online k-means clustering to quantize the dense representations. Discretization enables the direct application of algorithms from the NLP community which require discrete inputs. Experiments show that BERT pre-training achieves a new state of the art on TIMIT phoneme classification and WSJ speech recognition."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.05453","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/1910.05453/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":"1910.05453","created_at":"2026-07-05T00:40:59.302736+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.05453v3","created_at":"2026-07-05T00:40:59.302736+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.05453","created_at":"2026-07-05T00:40:59.302736+00:00"},{"alias_kind":"pith_short_12","alias_value":"KZT3ZSOYR3YD","created_at":"2026-07-05T00:40:59.302736+00:00"},{"alias_kind":"pith_short_16","alias_value":"KZT3ZSOYR3YD46DF","created_at":"2026-07-05T00:40:59.302736+00:00"},{"alias_kind":"pith_short_8","alias_value":"KZT3ZSOY","created_at":"2026-07-05T00:40:59.302736+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09234","citing_title":"End-to-End Training for Discrete Token LLM based TTS System","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02385","citing_title":"How Optimality Structures Sparse Dictionaries: A Theory for Understanding SAE Representations","ref_index":272,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06582","citing_title":"PairAlign: A Framework for Sequence Tokenization via Self-Alignment with Applications to Audio Tokenization","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17152","citing_title":"Multilingual and Multimodal LLMs in the Wild: Building for Low-Resource Languages","ref_index":235,"is_internal_anchor":false},{"citing_arxiv_id":"2509.22220","citing_title":"StableToken: A Noise-Robust Semantic Speech Tokenizer for Resilient SpeechLLMs","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04170","citing_title":"Incomplete Multi-View Multi-Label Classification via Shared Codebook and Fused-Teacher Self-Distillation","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06582","citing_title":"PairAlign: A Framework for Sequence Tokenization via Self-Alignment with Applications to Audio Tokenization","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KZT3ZSOYR3YD46DFHXH6TQR3TQ","json":"https://pith.science/pith/KZT3ZSOYR3YD46DFHXH6TQR3TQ.json","graph_json":"https://pith.science/api/pith-number/KZT3ZSOYR3YD46DFHXH6TQR3TQ/graph.json","events_json":"https://pith.science/api/pith-number/KZT3ZSOYR3YD46DFHXH6TQR3TQ/events.json","paper":"https://pith.science/paper/KZT3ZSOY"},"agent_actions":{"view_html":"https://pith.science/pith/KZT3ZSOYR3YD46DFHXH6TQR3TQ","download_json":"https://pith.science/pith/KZT3ZSOYR3YD46DFHXH6TQR3TQ.json","view_paper":"https://pith.science/paper/KZT3ZSOY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.05453&json=true","fetch_graph":"https://pith.science/api/pith-number/KZT3ZSOYR3YD46DFHXH6TQR3TQ/graph.json","fetch_events":"https://pith.science/api/pith-number/KZT3ZSOYR3YD46DFHXH6TQR3TQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KZT3ZSOYR3YD46DFHXH6TQR3TQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KZT3ZSOYR3YD46DFHXH6TQR3TQ/action/storage_attestation","attest_author":"https://pith.science/pith/KZT3ZSOYR3YD46DFHXH6TQR3TQ/action/author_attestation","sign_citation":"https://pith.science/pith/KZT3ZSOYR3YD46DFHXH6TQR3TQ/action/citation_signature","submit_replication":"https://pith.science/pith/KZT3ZSOYR3YD46DFHXH6TQR3TQ/action/replication_record"}},"created_at":"2026-07-05T00:40:59.302736+00:00","updated_at":"2026-07-05T00:40:59.302736+00:00"}