{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KXOZB7YXDGCE3ONPZSOMGGLAXX","short_pith_number":"pith:KXOZB7YX","schema_version":"1.0","canonical_sha256":"55dd90ff1719844db9afcc9cc31960bdc65c3f4e65cf81edbcf1de81d0b6e3f7","source":{"kind":"arxiv","id":"2307.03917","version":3},"attestation_state":"computed","paper":{"title":"On decoder-only architecture for speech-to-text and large language model integration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Bo Ren, Jian Wu, Jinyu Li, Linquan Liu, Long Zhou, Shujie Liu, Tianrui Wang, Yashesh Gaur, Yimeng Zhu, Yu Wu, Zhuo Chen","submitted_at":"2023-07-08T06:47:58Z","abstract_excerpt":"Large language models (LLMs) have achieved remarkable success in the field of natural language processing, enabling better human-computer interaction using natural language. However, the seamless integration of speech signals into LLMs has not been explored well. The \"decoder-only\" architecture has also not been well studied for speech processing tasks. In this research, we introduce Speech-LLaMA, a novel approach that effectively incorporates acoustic information into text-based large language models. Our method leverages Connectionist Temporal Classification and a simple audio encoder to map"},"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":"2307.03917","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-07-08T06:47:58Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"02a43e12ccb9780fb0af22347de59ca007d6b3e3b4852b62d6da5b48209f10bf","abstract_canon_sha256":"02b653030617e208daaa3d4677f44c55e1f955784fdca85c95bbaadcde29ed73"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:55:56.905849Z","signature_b64":"mtoRGeOrhU2LvQQsA9/OTLWj7FnOHqUEVsIKyA1ZZThsO8FiAC5r1yusNw0C4r9jbSH5fSiVnXYGTQEgRTNzDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55dd90ff1719844db9afcc9cc31960bdc65c3f4e65cf81edbcf1de81d0b6e3f7","last_reissued_at":"2026-07-05T06:55:56.905155Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:55:56.905155Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On decoder-only architecture for speech-to-text and large language model integration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Bo Ren, Jian Wu, Jinyu Li, Linquan Liu, Long Zhou, Shujie Liu, Tianrui Wang, Yashesh Gaur, Yimeng Zhu, Yu Wu, Zhuo Chen","submitted_at":"2023-07-08T06:47:58Z","abstract_excerpt":"Large language models (LLMs) have achieved remarkable success in the field of natural language processing, enabling better human-computer interaction using natural language. However, the seamless integration of speech signals into LLMs has not been explored well. The \"decoder-only\" architecture has also not been well studied for speech processing tasks. In this research, we introduce Speech-LLaMA, a novel approach that effectively incorporates acoustic information into text-based large language models. Our method leverages Connectionist Temporal Classification and a simple audio encoder to map"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.03917","kind":"arxiv","version":3},"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/2307.03917/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":"2307.03917","created_at":"2026-07-05T06:55:56.905251+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.03917v3","created_at":"2026-07-05T06:55:56.905251+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.03917","created_at":"2026-07-05T06:55:56.905251+00:00"},{"alias_kind":"pith_short_12","alias_value":"KXOZB7YXDGCE","created_at":"2026-07-05T06:55:56.905251+00:00"},{"alias_kind":"pith_short_16","alias_value":"KXOZB7YXDGCE3ONP","created_at":"2026-07-05T06:55:56.905251+00:00"},{"alias_kind":"pith_short_8","alias_value":"KXOZB7YX","created_at":"2026-07-05T06:55:56.905251+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2310.13289","citing_title":"SALMONN: Towards Generic Hearing Abilities for Large Language Models","ref_index":109,"is_internal_anchor":false},{"citing_arxiv_id":"2503.20215","citing_title":"Qwen2.5-Omni Technical Report","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KXOZB7YXDGCE3ONPZSOMGGLAXX","json":"https://pith.science/pith/KXOZB7YXDGCE3ONPZSOMGGLAXX.json","graph_json":"https://pith.science/api/pith-number/KXOZB7YXDGCE3ONPZSOMGGLAXX/graph.json","events_json":"https://pith.science/api/pith-number/KXOZB7YXDGCE3ONPZSOMGGLAXX/events.json","paper":"https://pith.science/paper/KXOZB7YX"},"agent_actions":{"view_html":"https://pith.science/pith/KXOZB7YXDGCE3ONPZSOMGGLAXX","download_json":"https://pith.science/pith/KXOZB7YXDGCE3ONPZSOMGGLAXX.json","view_paper":"https://pith.science/paper/KXOZB7YX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.03917&json=true","fetch_graph":"https://pith.science/api/pith-number/KXOZB7YXDGCE3ONPZSOMGGLAXX/graph.json","fetch_events":"https://pith.science/api/pith-number/KXOZB7YXDGCE3ONPZSOMGGLAXX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KXOZB7YXDGCE3ONPZSOMGGLAXX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KXOZB7YXDGCE3ONPZSOMGGLAXX/action/storage_attestation","attest_author":"https://pith.science/pith/KXOZB7YXDGCE3ONPZSOMGGLAXX/action/author_attestation","sign_citation":"https://pith.science/pith/KXOZB7YXDGCE3ONPZSOMGGLAXX/action/citation_signature","submit_replication":"https://pith.science/pith/KXOZB7YXDGCE3ONPZSOMGGLAXX/action/replication_record"}},"created_at":"2026-07-05T06:55:56.905251+00:00","updated_at":"2026-07-05T06:55:56.905251+00:00"}