{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DIO3CPKCUFIDBDUQCSHVQVQDVH","short_pith_number":"pith:DIO3CPKC","schema_version":"1.0","canonical_sha256":"1a1db13d42a150308e90148f585603a9e1b084b8be4fb3145e52d771f10f5a05","source":{"kind":"arxiv","id":"2506.06343","version":1},"attestation_state":"computed","paper":{"title":"TESU-LLM: Training Speech-LLMs Without Speech via Unified Encoder Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Jong Hwan Ko, Taesoo Kim","submitted_at":"2025-06-01T09:27:55Z","abstract_excerpt":"Recent advances in speech-enabled language models have shown promising results in building intelligent voice assistants. However, most existing approaches rely on large-scale paired speech-text data and extensive computational resources, which pose challenges in terms of scalability and accessibility. In this paper, we present \\textbf{TESU-LLM}, a novel framework that enables training speech-capable language models using only text data. Our key insight is to leverage a unified encoder that maps semantically equivalent text and speech inputs to a shared latent space. By aligning the encoder out"},"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":"2506.06343","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-01T09:27:55Z","cross_cats_sorted":["cs.AI","cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"8dedff2d0cea4b435a9d5e3646f51f6711b2317172cb48a773cc19c8c584e01e","abstract_canon_sha256":"5b5459d2fad10ff02041c0b5faafc2f2355d282beab3c8fbe465cbda9e59eb43"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:48.489940Z","signature_b64":"cMM4LIE37p2D07nufZ++lT7ZcKn51Mz1HPtNOnioWO2aQSAzNvueJoWvSs7R6qO05MmVla77Tpx9BbMSw1w2Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a1db13d42a150308e90148f585603a9e1b084b8be4fb3145e52d771f10f5a05","last_reissued_at":"2026-07-05T11:17:48.489495Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:48.489495Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TESU-LLM: Training Speech-LLMs Without Speech via Unified Encoder Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Jong Hwan Ko, Taesoo Kim","submitted_at":"2025-06-01T09:27:55Z","abstract_excerpt":"Recent advances in speech-enabled language models have shown promising results in building intelligent voice assistants. However, most existing approaches rely on large-scale paired speech-text data and extensive computational resources, which pose challenges in terms of scalability and accessibility. In this paper, we present \\textbf{TESU-LLM}, a novel framework that enables training speech-capable language models using only text data. Our key insight is to leverage a unified encoder that maps semantically equivalent text and speech inputs to a shared latent space. By aligning the encoder out"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06343","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/2506.06343/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":"2506.06343","created_at":"2026-07-05T11:17:48.489550+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.06343v1","created_at":"2026-07-05T11:17:48.489550+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06343","created_at":"2026-07-05T11:17:48.489550+00:00"},{"alias_kind":"pith_short_12","alias_value":"DIO3CPKCUFID","created_at":"2026-07-05T11:17:48.489550+00:00"},{"alias_kind":"pith_short_16","alias_value":"DIO3CPKCUFIDBDUQ","created_at":"2026-07-05T11:17:48.489550+00:00"},{"alias_kind":"pith_short_8","alias_value":"DIO3CPKC","created_at":"2026-07-05T11:17:48.489550+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/DIO3CPKCUFIDBDUQCSHVQVQDVH","json":"https://pith.science/pith/DIO3CPKCUFIDBDUQCSHVQVQDVH.json","graph_json":"https://pith.science/api/pith-number/DIO3CPKCUFIDBDUQCSHVQVQDVH/graph.json","events_json":"https://pith.science/api/pith-number/DIO3CPKCUFIDBDUQCSHVQVQDVH/events.json","paper":"https://pith.science/paper/DIO3CPKC"},"agent_actions":{"view_html":"https://pith.science/pith/DIO3CPKCUFIDBDUQCSHVQVQDVH","download_json":"https://pith.science/pith/DIO3CPKCUFIDBDUQCSHVQVQDVH.json","view_paper":"https://pith.science/paper/DIO3CPKC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.06343&json=true","fetch_graph":"https://pith.science/api/pith-number/DIO3CPKCUFIDBDUQCSHVQVQDVH/graph.json","fetch_events":"https://pith.science/api/pith-number/DIO3CPKCUFIDBDUQCSHVQVQDVH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DIO3CPKCUFIDBDUQCSHVQVQDVH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DIO3CPKCUFIDBDUQCSHVQVQDVH/action/storage_attestation","attest_author":"https://pith.science/pith/DIO3CPKCUFIDBDUQCSHVQVQDVH/action/author_attestation","sign_citation":"https://pith.science/pith/DIO3CPKCUFIDBDUQCSHVQVQDVH/action/citation_signature","submit_replication":"https://pith.science/pith/DIO3CPKCUFIDBDUQCSHVQVQDVH/action/replication_record"}},"created_at":"2026-07-05T11:17:48.489550+00:00","updated_at":"2026-07-05T11:17:48.489550+00:00"}