{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FAJCITHPOG6W2BRVEHN2OCL25C","short_pith_number":"pith:FAJCITHP","schema_version":"1.0","canonical_sha256":"2812244cef71bd6d063521dba7097ae8ac4d189999dde0b3018aacf8812e7618","source":{"kind":"arxiv","id":"2501.01384","version":1},"attestation_state":"computed","paper":{"title":"OmniChat: Enhancing Spoken Dialogue Systems with Scalable Synthetic Data for Diverse Scenarios","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.HC","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Bai Jionghao, Dongjie Fu, Jingyu Lu, Linjun Li, Minghui Fang, Rongjie Huang, Ruofan Hu, Shengpeng Ji, Tao Jin, Xiaoda Yang, Xize Cheng, Yu Chen, Zehan Wang, Zhou Zhao","submitted_at":"2025-01-02T17:58:23Z","abstract_excerpt":"With the rapid development of large language models, researchers have created increasingly advanced spoken dialogue systems that can naturally converse with humans. However, these systems still struggle to handle the full complexity of real-world conversations, including audio events, musical contexts, and emotional expressions, mainly because current dialogue datasets are constrained in both scale and scenario diversity. In this paper, we propose leveraging synthetic data to enhance the dialogue models across diverse scenarios. We introduce ShareChatX, the first comprehensive, large-scale dat"},"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":"2501.01384","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-02T17:58:23Z","cross_cats_sorted":["cs.HC","cs.SD","eess.AS"],"title_canon_sha256":"b5ac74050abe62130890651ae3b93badaf70094254b7159b59efbc21221bc50f","abstract_canon_sha256":"330a90cc926b96899d1767ed8140c5b9b687a7f35c5ca8eb7a84bbc2e306654c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:56:19.129095Z","signature_b64":"cBALUzlxpbcSylOtjuyshK0T0Nsn4dShR6A4oJK+owqaov0uz7hpyxFVosjhmlPsuZkyjq/v3JL+8gm3OJO/DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2812244cef71bd6d063521dba7097ae8ac4d189999dde0b3018aacf8812e7618","last_reissued_at":"2026-07-05T09:56:19.128676Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:56:19.128676Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OmniChat: Enhancing Spoken Dialogue Systems with Scalable Synthetic Data for Diverse Scenarios","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.HC","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Bai Jionghao, Dongjie Fu, Jingyu Lu, Linjun Li, Minghui Fang, Rongjie Huang, Ruofan Hu, Shengpeng Ji, Tao Jin, Xiaoda Yang, Xize Cheng, Yu Chen, Zehan Wang, Zhou Zhao","submitted_at":"2025-01-02T17:58:23Z","abstract_excerpt":"With the rapid development of large language models, researchers have created increasingly advanced spoken dialogue systems that can naturally converse with humans. However, these systems still struggle to handle the full complexity of real-world conversations, including audio events, musical contexts, and emotional expressions, mainly because current dialogue datasets are constrained in both scale and scenario diversity. In this paper, we propose leveraging synthetic data to enhance the dialogue models across diverse scenarios. We introduce ShareChatX, the first comprehensive, large-scale dat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.01384","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/2501.01384/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":"2501.01384","created_at":"2026-07-05T09:56:19.128732+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.01384v1","created_at":"2026-07-05T09:56:19.128732+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.01384","created_at":"2026-07-05T09:56:19.128732+00:00"},{"alias_kind":"pith_short_12","alias_value":"FAJCITHPOG6W","created_at":"2026-07-05T09:56:19.128732+00:00"},{"alias_kind":"pith_short_16","alias_value":"FAJCITHPOG6W2BRV","created_at":"2026-07-05T09:56:19.128732+00:00"},{"alias_kind":"pith_short_8","alias_value":"FAJCITHP","created_at":"2026-07-05T09:56:19.128732+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01825","citing_title":"ROGLE: Robust Global-Local Alignment with Automated Region Supervision for Text-Based Person Search","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04306","citing_title":"Organizational Control Layer: Governance Infrastructure at the Execution Boundary of LLM Agent Systems","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01825","citing_title":"ROGLE: Robust Global-Local Alignment with Automated Region Supervision for Text-Based Person Search","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23954","citing_title":"EchoDistill:Alignment Noisy-to-Clean Self-Distillation for Robust Audio LLMs","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2508.18167","citing_title":"DiscussLLM: Teaching Large Language Models When to Speak","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FAJCITHPOG6W2BRVEHN2OCL25C","json":"https://pith.science/pith/FAJCITHPOG6W2BRVEHN2OCL25C.json","graph_json":"https://pith.science/api/pith-number/FAJCITHPOG6W2BRVEHN2OCL25C/graph.json","events_json":"https://pith.science/api/pith-number/FAJCITHPOG6W2BRVEHN2OCL25C/events.json","paper":"https://pith.science/paper/FAJCITHP"},"agent_actions":{"view_html":"https://pith.science/pith/FAJCITHPOG6W2BRVEHN2OCL25C","download_json":"https://pith.science/pith/FAJCITHPOG6W2BRVEHN2OCL25C.json","view_paper":"https://pith.science/paper/FAJCITHP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.01384&json=true","fetch_graph":"https://pith.science/api/pith-number/FAJCITHPOG6W2BRVEHN2OCL25C/graph.json","fetch_events":"https://pith.science/api/pith-number/FAJCITHPOG6W2BRVEHN2OCL25C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FAJCITHPOG6W2BRVEHN2OCL25C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FAJCITHPOG6W2BRVEHN2OCL25C/action/storage_attestation","attest_author":"https://pith.science/pith/FAJCITHPOG6W2BRVEHN2OCL25C/action/author_attestation","sign_citation":"https://pith.science/pith/FAJCITHPOG6W2BRVEHN2OCL25C/action/citation_signature","submit_replication":"https://pith.science/pith/FAJCITHPOG6W2BRVEHN2OCL25C/action/replication_record"}},"created_at":"2026-07-05T09:56:19.128732+00:00","updated_at":"2026-07-05T09:56:19.128732+00:00"}