{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:KOJD2NJAV6I2DAGI7HYCDOL6TH","short_pith_number":"pith:KOJD2NJA","schema_version":"1.0","canonical_sha256":"53923d3520af91a180c8f9f021b97e99c25cd7d759ce65863cefb2b28090c063","source":{"kind":"arxiv","id":"1904.03240","version":2},"attestation_state":"computed","paper":{"title":"An Unsupervised Autoregressive Model for Speech Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Hao Tang, James Glass, Wei-Ning Hsu, Yu-An Chung","submitted_at":"2019-04-05T19:04:19Z","abstract_excerpt":"This paper proposes a novel unsupervised autoregressive neural model for learning generic speech representations. In contrast to other speech representation learning methods that aim to remove noise or speaker variabilities, ours is designed to preserve information for a wide range of downstream tasks. In addition, the proposed model does not require any phonetic or word boundary labels, allowing the model to benefit from large quantities of unlabeled data. Speech representations learned by our model significantly improve performance on both phone classification and speaker verification over t"},"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":"1904.03240","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-05T19:04:19Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"10bcf171ea6f1af58858a7eeec4342db1c6f30921f5f47a8b925d26a2069c1eb","abstract_canon_sha256":"684ebaa8f53acd54191acc9f005cab840ec1eadec86293569dc1f7fa2a66b1a6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:58.297474Z","signature_b64":"fdN0E7dow4DsiaWhUoDkn4l8LSqnkn2nqeCcuAGUq8TY5MDMyLwv9tlDLLheZzRB9UytyDOxt1fFlnKRhrRvBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53923d3520af91a180c8f9f021b97e99c25cd7d759ce65863cefb2b28090c063","last_reissued_at":"2026-05-17T23:42:58.296897Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:58.296897Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Unsupervised Autoregressive Model for Speech Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Hao Tang, James Glass, Wei-Ning Hsu, Yu-An Chung","submitted_at":"2019-04-05T19:04:19Z","abstract_excerpt":"This paper proposes a novel unsupervised autoregressive neural model for learning generic speech representations. In contrast to other speech representation learning methods that aim to remove noise or speaker variabilities, ours is designed to preserve information for a wide range of downstream tasks. In addition, the proposed model does not require any phonetic or word boundary labels, allowing the model to benefit from large quantities of unlabeled data. Speech representations learned by our model significantly improve performance on both phone classification and speaker verification over t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.03240","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":""},"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":"1904.03240","created_at":"2026-05-17T23:42:58.296990+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.03240v2","created_at":"2026-05-17T23:42:58.296990+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.03240","created_at":"2026-05-17T23:42:58.296990+00:00"},{"alias_kind":"pith_short_12","alias_value":"KOJD2NJAV6I2","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_16","alias_value":"KOJD2NJAV6I2DAGI","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_8","alias_value":"KOJD2NJA","created_at":"2026-05-18T12:33:21.387695+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2603.01482","citing_title":"A SUPERB-Style Benchmark of Self-Supervised Speech Models for Audio Deepfake Detection","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06582","citing_title":"PairAlign: A Framework for Sequence Tokenization via Self-Alignment with Applications to Audio Tokenization","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KOJD2NJAV6I2DAGI7HYCDOL6TH","json":"https://pith.science/pith/KOJD2NJAV6I2DAGI7HYCDOL6TH.json","graph_json":"https://pith.science/api/pith-number/KOJD2NJAV6I2DAGI7HYCDOL6TH/graph.json","events_json":"https://pith.science/api/pith-number/KOJD2NJAV6I2DAGI7HYCDOL6TH/events.json","paper":"https://pith.science/paper/KOJD2NJA"},"agent_actions":{"view_html":"https://pith.science/pith/KOJD2NJAV6I2DAGI7HYCDOL6TH","download_json":"https://pith.science/pith/KOJD2NJAV6I2DAGI7HYCDOL6TH.json","view_paper":"https://pith.science/paper/KOJD2NJA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.03240&json=true","fetch_graph":"https://pith.science/api/pith-number/KOJD2NJAV6I2DAGI7HYCDOL6TH/graph.json","fetch_events":"https://pith.science/api/pith-number/KOJD2NJAV6I2DAGI7HYCDOL6TH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KOJD2NJAV6I2DAGI7HYCDOL6TH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KOJD2NJAV6I2DAGI7HYCDOL6TH/action/storage_attestation","attest_author":"https://pith.science/pith/KOJD2NJAV6I2DAGI7HYCDOL6TH/action/author_attestation","sign_citation":"https://pith.science/pith/KOJD2NJAV6I2DAGI7HYCDOL6TH/action/citation_signature","submit_replication":"https://pith.science/pith/KOJD2NJAV6I2DAGI7HYCDOL6TH/action/replication_record"}},"created_at":"2026-05-17T23:42:58.296990+00:00","updated_at":"2026-05-17T23:42:58.296990+00:00"}