{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:L65QHNAPTGL3XKOIBHQO5FEF6Q","short_pith_number":"pith:L65QHNAP","schema_version":"1.0","canonical_sha256":"5fbb03b40f9997bba9c809e0ee9485f40f389441f76c0fe091ae7ae617bd88bd","source":{"kind":"arxiv","id":"2210.16755","version":1},"attestation_state":"computed","paper":{"title":"token2vec: A Joint Self-Supervised Pre-training Framework Using Unpaired Speech and Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Haizhou Li, Junyi Ao, Xianghu Yue, Xiaoxue Gao","submitted_at":"2022-10-30T06:38:19Z","abstract_excerpt":"Self-supervised pre-training has been successful in both text and speech processing. Speech and text offer different but complementary information. The question is whether we are able to perform a speech-text joint pre-training on unpaired speech and text. In this paper, we take the idea of self-supervised pre-training one step further and propose token2vec, a novel joint pre-training framework for unpaired speech and text based on discrete representations of speech. Firstly, due to the distinct characteristics between speech and text modalities, where speech is continuous while text is discre"},"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":"2210.16755","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-30T06:38:19Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"79dde63f732c63f6c70973adf038c9125a43b637449c2932fe20a542f0f6f5f2","abstract_canon_sha256":"7177ce1ab12379e10cb44c0d56caf5a4f9413e2f68ffe0b221ef48ed073844db"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:11:50.342676Z","signature_b64":"301iNoWu2ZbadBofNm3Y45r/JcYRn+oGdqZTxEyzz2cX1R0UkNqsw5bEJCDuatc5FRJ4pLdRtIVwoXMMdkWOAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5fbb03b40f9997bba9c809e0ee9485f40f389441f76c0fe091ae7ae617bd88bd","last_reissued_at":"2026-07-05T05:11:50.342267Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:11:50.342267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"token2vec: A Joint Self-Supervised Pre-training Framework Using Unpaired Speech and Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Haizhou Li, Junyi Ao, Xianghu Yue, Xiaoxue Gao","submitted_at":"2022-10-30T06:38:19Z","abstract_excerpt":"Self-supervised pre-training has been successful in both text and speech processing. Speech and text offer different but complementary information. The question is whether we are able to perform a speech-text joint pre-training on unpaired speech and text. In this paper, we take the idea of self-supervised pre-training one step further and propose token2vec, a novel joint pre-training framework for unpaired speech and text based on discrete representations of speech. Firstly, due to the distinct characteristics between speech and text modalities, where speech is continuous while text is discre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.16755","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/2210.16755/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":"2210.16755","created_at":"2026-07-05T05:11:50.342334+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.16755v1","created_at":"2026-07-05T05:11:50.342334+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.16755","created_at":"2026-07-05T05:11:50.342334+00:00"},{"alias_kind":"pith_short_12","alias_value":"L65QHNAPTGL3","created_at":"2026-07-05T05:11:50.342334+00:00"},{"alias_kind":"pith_short_16","alias_value":"L65QHNAPTGL3XKOI","created_at":"2026-07-05T05:11:50.342334+00:00"},{"alias_kind":"pith_short_8","alias_value":"L65QHNAP","created_at":"2026-07-05T05:11:50.342334+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/L65QHNAPTGL3XKOIBHQO5FEF6Q","json":"https://pith.science/pith/L65QHNAPTGL3XKOIBHQO5FEF6Q.json","graph_json":"https://pith.science/api/pith-number/L65QHNAPTGL3XKOIBHQO5FEF6Q/graph.json","events_json":"https://pith.science/api/pith-number/L65QHNAPTGL3XKOIBHQO5FEF6Q/events.json","paper":"https://pith.science/paper/L65QHNAP"},"agent_actions":{"view_html":"https://pith.science/pith/L65QHNAPTGL3XKOIBHQO5FEF6Q","download_json":"https://pith.science/pith/L65QHNAPTGL3XKOIBHQO5FEF6Q.json","view_paper":"https://pith.science/paper/L65QHNAP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.16755&json=true","fetch_graph":"https://pith.science/api/pith-number/L65QHNAPTGL3XKOIBHQO5FEF6Q/graph.json","fetch_events":"https://pith.science/api/pith-number/L65QHNAPTGL3XKOIBHQO5FEF6Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L65QHNAPTGL3XKOIBHQO5FEF6Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L65QHNAPTGL3XKOIBHQO5FEF6Q/action/storage_attestation","attest_author":"https://pith.science/pith/L65QHNAPTGL3XKOIBHQO5FEF6Q/action/author_attestation","sign_citation":"https://pith.science/pith/L65QHNAPTGL3XKOIBHQO5FEF6Q/action/citation_signature","submit_replication":"https://pith.science/pith/L65QHNAPTGL3XKOIBHQO5FEF6Q/action/replication_record"}},"created_at":"2026-07-05T05:11:50.342334+00:00","updated_at":"2026-07-05T05:11:50.342334+00:00"}