{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RNV6NAX7NXIAUQRG5ITYU7XGME","short_pith_number":"pith:RNV6NAX7","schema_version":"1.0","canonical_sha256":"8b6be682ff6dd00a4226ea278a7ee661101c05c4fc14529c905873ec871a2550","source":{"kind":"arxiv","id":"2310.08715","version":1},"attestation_state":"computed","paper":{"title":"Toward Joint Language Modeling for Speech Units and Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Alexei Baevski, Alexis Conneau, Arun Babu, Chung-Ming Chien, Ju-chieh Chou, Karen Livescu, Michael Auli, Wei-Ning Hsu","submitted_at":"2023-10-12T20:53:39Z","abstract_excerpt":"Speech and text are two major forms of human language. The research community has been focusing on mapping speech to text or vice versa for many years. However, in the field of language modeling, very little effort has been made to model them jointly. In light of this, we explore joint language modeling for speech units and text. Specifically, we compare different speech tokenizers to transform continuous speech signals into discrete units and use different methods to construct mixed speech-text data. We introduce automatic metrics to evaluate how well the joint LM mixes speech and text. We al"},"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":"2310.08715","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-12T20:53:39Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"101be719986e2cf5f5edcba43e751b0f6b863fad256994a9773bc610baac5a9b","abstract_canon_sha256":"e48667070b91ba90c05a05ba843264046db80471bc3d3e09f13459965add2ffa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:00:33.807976Z","signature_b64":"RG1mxT0zo2q+Cbpc4N+vRGMWxOs27y2msX7vd6Is/AZ+ZJAr04GNWEST/rZA+UsjBt2lZgXnn2Y7jjaFyKqADg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b6be682ff6dd00a4226ea278a7ee661101c05c4fc14529c905873ec871a2550","last_reissued_at":"2026-07-05T07:00:33.807522Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:00:33.807522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Toward Joint Language Modeling for Speech Units and Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Alexei Baevski, Alexis Conneau, Arun Babu, Chung-Ming Chien, Ju-chieh Chou, Karen Livescu, Michael Auli, Wei-Ning Hsu","submitted_at":"2023-10-12T20:53:39Z","abstract_excerpt":"Speech and text are two major forms of human language. The research community has been focusing on mapping speech to text or vice versa for many years. However, in the field of language modeling, very little effort has been made to model them jointly. In light of this, we explore joint language modeling for speech units and text. Specifically, we compare different speech tokenizers to transform continuous speech signals into discrete units and use different methods to construct mixed speech-text data. We introduce automatic metrics to evaluate how well the joint LM mixes speech and text. We al"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.08715","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/2310.08715/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":"2310.08715","created_at":"2026-07-05T07:00:33.807575+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.08715v1","created_at":"2026-07-05T07:00:33.807575+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.08715","created_at":"2026-07-05T07:00:33.807575+00:00"},{"alias_kind":"pith_short_12","alias_value":"RNV6NAX7NXIA","created_at":"2026-07-05T07:00:33.807575+00:00"},{"alias_kind":"pith_short_16","alias_value":"RNV6NAX7NXIAUQRG","created_at":"2026-07-05T07:00:33.807575+00:00"},{"alias_kind":"pith_short_8","alias_value":"RNV6NAX7","created_at":"2026-07-05T07:00:33.807575+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/RNV6NAX7NXIAUQRG5ITYU7XGME","json":"https://pith.science/pith/RNV6NAX7NXIAUQRG5ITYU7XGME.json","graph_json":"https://pith.science/api/pith-number/RNV6NAX7NXIAUQRG5ITYU7XGME/graph.json","events_json":"https://pith.science/api/pith-number/RNV6NAX7NXIAUQRG5ITYU7XGME/events.json","paper":"https://pith.science/paper/RNV6NAX7"},"agent_actions":{"view_html":"https://pith.science/pith/RNV6NAX7NXIAUQRG5ITYU7XGME","download_json":"https://pith.science/pith/RNV6NAX7NXIAUQRG5ITYU7XGME.json","view_paper":"https://pith.science/paper/RNV6NAX7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.08715&json=true","fetch_graph":"https://pith.science/api/pith-number/RNV6NAX7NXIAUQRG5ITYU7XGME/graph.json","fetch_events":"https://pith.science/api/pith-number/RNV6NAX7NXIAUQRG5ITYU7XGME/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RNV6NAX7NXIAUQRG5ITYU7XGME/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RNV6NAX7NXIAUQRG5ITYU7XGME/action/storage_attestation","attest_author":"https://pith.science/pith/RNV6NAX7NXIAUQRG5ITYU7XGME/action/author_attestation","sign_citation":"https://pith.science/pith/RNV6NAX7NXIAUQRG5ITYU7XGME/action/citation_signature","submit_replication":"https://pith.science/pith/RNV6NAX7NXIAUQRG5ITYU7XGME/action/replication_record"}},"created_at":"2026-07-05T07:00:33.807575+00:00","updated_at":"2026-07-05T07:00:33.807575+00:00"}