{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DD35RNZ6KCJ7Z3A7COIFJCRC2P","short_pith_number":"pith:DD35RNZ6","schema_version":"1.0","canonical_sha256":"18f7d8b73e5093fcec1f1390548a22d3c9bf9a3259f447b0676681c88f1576d6","source":{"kind":"arxiv","id":"2409.08680","version":1},"attestation_state":"computed","paper":{"title":"NEST-RQ: Next Token Prediction for Speech Self-Supervised Pre-Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"eess.AS","authors_text":"Chen Shen, Linhao Dong, Lu Lu, Mingkun Huang, Minglun Han, Ye Bai, Youjia Huang, Yuxuan Wang, Zehua Lin","submitted_at":"2024-09-13T09:48:11Z","abstract_excerpt":"Speech self-supervised pre-training can effectively improve the performance of downstream tasks. However, previous self-supervised learning (SSL) methods for speech, such as HuBERT and BEST-RQ, focus on utilizing non-causal encoders with bidirectional context, and lack sufficient support for downstream streaming models. To address this issue, we introduce the next token prediction based speech pre-training method with random-projection quantizer (NEST-RQ). NEST-RQ employs causal encoders with only left context and uses next token prediction (NTP) as the training task. On the large-scale datase"},"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":"2409.08680","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-13T09:48:11Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"bf6725e4b3916122778264c51c694a6881b8ff882002b9decdae3d90f6d69192","abstract_canon_sha256":"17e72ac7f53b32ab7e3b15a243191565d3d259cfc812fe541d4d95dc58e05d54"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:06:45.720135Z","signature_b64":"Ero5c9l+cT9MnqjLVq2mnwrGJPyKxzgRzI6qYFUblL2PK+T3iGTuW9+w5fPFhdOsYINAr3HKzx8H9ERSLXaOAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18f7d8b73e5093fcec1f1390548a22d3c9bf9a3259f447b0676681c88f1576d6","last_reissued_at":"2026-07-05T09:06:45.719649Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:06:45.719649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NEST-RQ: Next Token Prediction for Speech Self-Supervised Pre-Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"eess.AS","authors_text":"Chen Shen, Linhao Dong, Lu Lu, Mingkun Huang, Minglun Han, Ye Bai, Youjia Huang, Yuxuan Wang, Zehua Lin","submitted_at":"2024-09-13T09:48:11Z","abstract_excerpt":"Speech self-supervised pre-training can effectively improve the performance of downstream tasks. However, previous self-supervised learning (SSL) methods for speech, such as HuBERT and BEST-RQ, focus on utilizing non-causal encoders with bidirectional context, and lack sufficient support for downstream streaming models. To address this issue, we introduce the next token prediction based speech pre-training method with random-projection quantizer (NEST-RQ). NEST-RQ employs causal encoders with only left context and uses next token prediction (NTP) as the training task. On the large-scale datase"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.08680","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/2409.08680/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":"2409.08680","created_at":"2026-07-05T09:06:45.719714+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.08680v1","created_at":"2026-07-05T09:06:45.719714+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.08680","created_at":"2026-07-05T09:06:45.719714+00:00"},{"alias_kind":"pith_short_12","alias_value":"DD35RNZ6KCJ7","created_at":"2026-07-05T09:06:45.719714+00:00"},{"alias_kind":"pith_short_16","alias_value":"DD35RNZ6KCJ7Z3A7","created_at":"2026-07-05T09:06:45.719714+00:00"},{"alias_kind":"pith_short_8","alias_value":"DD35RNZ6","created_at":"2026-07-05T09:06:45.719714+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21268","citing_title":"Online Predictive Coding for Dual-Mode Self-Supervised Speech Model","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06357","citing_title":"F3-Tokenizer: Taming Audio Autoencoder Latents for Understanding and Generation","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DD35RNZ6KCJ7Z3A7COIFJCRC2P","json":"https://pith.science/pith/DD35RNZ6KCJ7Z3A7COIFJCRC2P.json","graph_json":"https://pith.science/api/pith-number/DD35RNZ6KCJ7Z3A7COIFJCRC2P/graph.json","events_json":"https://pith.science/api/pith-number/DD35RNZ6KCJ7Z3A7COIFJCRC2P/events.json","paper":"https://pith.science/paper/DD35RNZ6"},"agent_actions":{"view_html":"https://pith.science/pith/DD35RNZ6KCJ7Z3A7COIFJCRC2P","download_json":"https://pith.science/pith/DD35RNZ6KCJ7Z3A7COIFJCRC2P.json","view_paper":"https://pith.science/paper/DD35RNZ6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.08680&json=true","fetch_graph":"https://pith.science/api/pith-number/DD35RNZ6KCJ7Z3A7COIFJCRC2P/graph.json","fetch_events":"https://pith.science/api/pith-number/DD35RNZ6KCJ7Z3A7COIFJCRC2P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DD35RNZ6KCJ7Z3A7COIFJCRC2P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DD35RNZ6KCJ7Z3A7COIFJCRC2P/action/storage_attestation","attest_author":"https://pith.science/pith/DD35RNZ6KCJ7Z3A7COIFJCRC2P/action/author_attestation","sign_citation":"https://pith.science/pith/DD35RNZ6KCJ7Z3A7COIFJCRC2P/action/citation_signature","submit_replication":"https://pith.science/pith/DD35RNZ6KCJ7Z3A7COIFJCRC2P/action/replication_record"}},"created_at":"2026-07-05T09:06:45.719714+00:00","updated_at":"2026-07-05T09:06:45.719714+00:00"}