{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QYNU5A55ASOUGDMS3GR72B5S2Q","short_pith_number":"pith:QYNU5A55","schema_version":"1.0","canonical_sha256":"861b4e83bd049d430d92d9a3fd07b2d436134e1ec8af8f4803b313b4413e056e","source":{"kind":"arxiv","id":"2502.17239","version":1},"attestation_state":"computed","paper":{"title":"Baichuan-Audio: A Unified Framework for End-to-End Speech Interaction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Da Pan, Guosheng Dong, Haoze Sun, Jianhua Xu, Jun Liu, MingAn Lin, Mingrui Wang, Tao Zhang, Tianpeng Li, Weipeng Chen, Yuanbo Fang, Zehuan Li, Zenan Zhou, Zheng Liang","submitted_at":"2025-02-24T15:16:34Z","abstract_excerpt":"We introduce Baichuan-Audio, an end-to-end audio large language model that seamlessly integrates audio understanding and generation. It features a text-guided aligned speech generation mechanism, enabling real-time speech interaction with both comprehension and generation capabilities. Baichuan-Audio leverages a pre-trained ASR model, followed by multi-codebook discretization of speech at a frame rate of 12.5 Hz. This multi-codebook setup ensures that speech tokens retain both semantic and acoustic information. To further enhance modeling, an independent audio head is employed to process audio"},"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":"2502.17239","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-24T15:16:34Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"d00fd72ce6dde6016dcb85c773f2d80c7a816d6fc4e4067ba43801ff59fe4ad0","abstract_canon_sha256":"33da85bed94409c819d85f490b4f91f287ff928418f4d91dd5debbdacd0ec438"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:19:07.572655Z","signature_b64":"o1n6ouwuVB+v2Dusdh1vmGEcGMYSWrmNJWyvWPilKs7NKrTiL8jatEVR9LZaY4DSUXlsYe0ZHf3CmMyWvg7fAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"861b4e83bd049d430d92d9a3fd07b2d436134e1ec8af8f4803b313b4413e056e","last_reissued_at":"2026-07-05T10:19:07.572146Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:19:07.572146Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Baichuan-Audio: A Unified Framework for End-to-End Speech Interaction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Da Pan, Guosheng Dong, Haoze Sun, Jianhua Xu, Jun Liu, MingAn Lin, Mingrui Wang, Tao Zhang, Tianpeng Li, Weipeng Chen, Yuanbo Fang, Zehuan Li, Zenan Zhou, Zheng Liang","submitted_at":"2025-02-24T15:16:34Z","abstract_excerpt":"We introduce Baichuan-Audio, an end-to-end audio large language model that seamlessly integrates audio understanding and generation. It features a text-guided aligned speech generation mechanism, enabling real-time speech interaction with both comprehension and generation capabilities. Baichuan-Audio leverages a pre-trained ASR model, followed by multi-codebook discretization of speech at a frame rate of 12.5 Hz. This multi-codebook setup ensures that speech tokens retain both semantic and acoustic information. To further enhance modeling, an independent audio head is employed to process audio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.17239","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/2502.17239/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":"2502.17239","created_at":"2026-07-05T10:19:07.572205+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.17239v1","created_at":"2026-07-05T10:19:07.572205+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.17239","created_at":"2026-07-05T10:19:07.572205+00:00"},{"alias_kind":"pith_short_12","alias_value":"QYNU5A55ASOU","created_at":"2026-07-05T10:19:07.572205+00:00"},{"alias_kind":"pith_short_16","alias_value":"QYNU5A55ASOUGDMS","created_at":"2026-07-05T10:19:07.572205+00:00"},{"alias_kind":"pith_short_8","alias_value":"QYNU5A55","created_at":"2026-07-05T10:19:07.572205+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":14,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01802","citing_title":"MOSS-Audio Technical Report","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31247","citing_title":"FlexiSLM: A Dynamic and Controllable Frame Rate Spoken Language Model","ref_index":218,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01016","citing_title":"PolySpeech-100: A Large-Scale Benchmark for Speech Understanding Across 100+ Languages and Dialects","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2503.14324","citing_title":"DualToken: Towards Unifying Visual Understanding and Generation with Dual Visual Vocabularies","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2603.17837","citing_title":"The Silent Thought: Modeling Internal Cognition in Full-Duplex Spoken Dialogue Models via Latent Reasoning","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20266","citing_title":"A Survey of Large Audio Language Models: Generalization, Trustworthiness, and Outlook","ref_index":128,"is_internal_anchor":false},{"citing_arxiv_id":"2509.14804","citing_title":"Towards Building Speech Large Language Models for Multitask Understanding in Low-Resource Languages","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2603.17837","citing_title":"The Silent Thought: Modeling Internal Cognition in Full-Duplex Spoken Dialogue Models via Latent Reasoning","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2507.08128","citing_title":"Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2603.22267","citing_title":"TiCo: Time-Controllable Spoken Dialogue Model","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10199","citing_title":"How Should LLMs Listen While Speaking? A Study of User-Stream Routing in Full-Duplex Spoken Dialogue","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2504.18425","citing_title":"Kimi-Audio Technical Report","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03937","citing_title":"MiniMind-O Technical Report: An Open Small-Scale Speech-Native Omni Model","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06765","citing_title":"VITA-QinYu: Expressive Spoken Language Model for Role-Playing and Singing","ref_index":104,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QYNU5A55ASOUGDMS3GR72B5S2Q","json":"https://pith.science/pith/QYNU5A55ASOUGDMS3GR72B5S2Q.json","graph_json":"https://pith.science/api/pith-number/QYNU5A55ASOUGDMS3GR72B5S2Q/graph.json","events_json":"https://pith.science/api/pith-number/QYNU5A55ASOUGDMS3GR72B5S2Q/events.json","paper":"https://pith.science/paper/QYNU5A55"},"agent_actions":{"view_html":"https://pith.science/pith/QYNU5A55ASOUGDMS3GR72B5S2Q","download_json":"https://pith.science/pith/QYNU5A55ASOUGDMS3GR72B5S2Q.json","view_paper":"https://pith.science/paper/QYNU5A55","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.17239&json=true","fetch_graph":"https://pith.science/api/pith-number/QYNU5A55ASOUGDMS3GR72B5S2Q/graph.json","fetch_events":"https://pith.science/api/pith-number/QYNU5A55ASOUGDMS3GR72B5S2Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QYNU5A55ASOUGDMS3GR72B5S2Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QYNU5A55ASOUGDMS3GR72B5S2Q/action/storage_attestation","attest_author":"https://pith.science/pith/QYNU5A55ASOUGDMS3GR72B5S2Q/action/author_attestation","sign_citation":"https://pith.science/pith/QYNU5A55ASOUGDMS3GR72B5S2Q/action/citation_signature","submit_replication":"https://pith.science/pith/QYNU5A55ASOUGDMS3GR72B5S2Q/action/replication_record"}},"created_at":"2026-07-05T10:19:07.572205+00:00","updated_at":"2026-07-05T10:19:07.572205+00:00"}