{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OTWV6PFHVXHXV6O7EQT7LVNP5P","short_pith_number":"pith:OTWV6PFH","schema_version":"1.0","canonical_sha256":"74ed5f3ca7adcf7af9df2427f5d5afebd0968cb81a79a2d41024b82e17e03346","source":{"kind":"arxiv","id":"2502.14145","version":3},"attestation_state":"computed","paper":{"title":"LLM-Enhanced Dialogue Management for Full-Duplex Spoken Dialogue Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Dong Yu, Hao Zhang, Meng Yu, Rilin Chen, Vinay Kothapally, Weiwei Li","submitted_at":"2025-02-19T23:15:13Z","abstract_excerpt":"Achieving full-duplex communication in spoken dialogue systems (SDS) requires real-time coordination between listening, speaking, and thinking. This paper proposes a semantic voice activity detection (VAD) module as a dialogue manager (DM) to efficiently manage turn-taking in full-duplex SDS. Implemented as a lightweight (0.5B) LLM fine-tuned on full-duplex conversation data, the semantic VAD predicts four control tokens to regulate turn-switching and turn-keeping, distinguishing between intentional and unintentional barge-ins while detecting query completion for handling user pauses and hesit"},"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":"2502.14145","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-19T23:15:13Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"eab23ebff45682f7b7c61de5136722b41131f4649b71cabe06fa68111c0d95a8","abstract_canon_sha256":"d49a1dd7bc20abb1b15ac32179eb30031d78f2f25e5277be8abdb5006edc6f03"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:14:25.258177Z","signature_b64":"dOkbn2IsbStpB4swm41aaXIeQ2OZouKqcPV5f+LquqKdr8A1LFrSoqBtLuw6G2c/zTui4c6sU7e3fKffz3/zCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74ed5f3ca7adcf7af9df2427f5d5afebd0968cb81a79a2d41024b82e17e03346","last_reissued_at":"2026-06-05T01:14:25.257442Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:14:25.257442Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM-Enhanced Dialogue Management for Full-Duplex Spoken Dialogue Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Dong Yu, Hao Zhang, Meng Yu, Rilin Chen, Vinay Kothapally, Weiwei Li","submitted_at":"2025-02-19T23:15:13Z","abstract_excerpt":"Achieving full-duplex communication in spoken dialogue systems (SDS) requires real-time coordination between listening, speaking, and thinking. This paper proposes a semantic voice activity detection (VAD) module as a dialogue manager (DM) to efficiently manage turn-taking in full-duplex SDS. Implemented as a lightweight (0.5B) LLM fine-tuned on full-duplex conversation data, the semantic VAD predicts four control tokens to regulate turn-switching and turn-keeping, distinguishing between intentional and unintentional barge-ins while detecting query completion for handling user pauses and hesit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14145","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/2502.14145/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":"2502.14145","created_at":"2026-06-05T01:14:25.257537+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.14145v3","created_at":"2026-06-05T01:14:25.257537+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14145","created_at":"2026-06-05T01:14:25.257537+00:00"},{"alias_kind":"pith_short_12","alias_value":"OTWV6PFHVXHX","created_at":"2026-06-05T01:14:25.257537+00:00"},{"alias_kind":"pith_short_16","alias_value":"OTWV6PFHVXHXV6O7","created_at":"2026-06-05T01:14:25.257537+00:00"},{"alias_kind":"pith_short_8","alias_value":"OTWV6PFH","created_at":"2026-06-05T01:14:25.257537+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":6,"sample":[{"citing_arxiv_id":"2606.18094","citing_title":"Next-Turn: Duration-Aware Streaming Endpoint Detection via Time-to-Next-Speech-Onset Prediction","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2607.02062","citing_title":"LMPAN: A Lightweight Multi-Path Alignment Network for Joint Full-Duplex Acoustic Echo Cancellation and Noise Suppression","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2606.06559","citing_title":"IRAF: Interference-Resilient Adaptive Fusion for Noise-Robust End-to-End Full-Duplex Spoken Dialogue Systems","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2605.25343","citing_title":"Toward Native Multimodal Modeling: A Roadmap","ref_index":241,"is_internal_anchor":true},{"citing_arxiv_id":"2603.17837","citing_title":"The Silent Thought: Modeling Internal Cognition in Full-Duplex Spoken Dialogue Models via Latent Reasoning","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2603.17837","citing_title":"The Silent Thought: Modeling Internal Cognition in Full-Duplex Spoken Dialogue Models via Latent Reasoning","ref_index":43,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OTWV6PFHVXHXV6O7EQT7LVNP5P","json":"https://pith.science/pith/OTWV6PFHVXHXV6O7EQT7LVNP5P.json","graph_json":"https://pith.science/api/pith-number/OTWV6PFHVXHXV6O7EQT7LVNP5P/graph.json","events_json":"https://pith.science/api/pith-number/OTWV6PFHVXHXV6O7EQT7LVNP5P/events.json","paper":"https://pith.science/paper/OTWV6PFH"},"agent_actions":{"view_html":"https://pith.science/pith/OTWV6PFHVXHXV6O7EQT7LVNP5P","download_json":"https://pith.science/pith/OTWV6PFHVXHXV6O7EQT7LVNP5P.json","view_paper":"https://pith.science/paper/OTWV6PFH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.14145&json=true","fetch_graph":"https://pith.science/api/pith-number/OTWV6PFHVXHXV6O7EQT7LVNP5P/graph.json","fetch_events":"https://pith.science/api/pith-number/OTWV6PFHVXHXV6O7EQT7LVNP5P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OTWV6PFHVXHXV6O7EQT7LVNP5P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OTWV6PFHVXHXV6O7EQT7LVNP5P/action/storage_attestation","attest_author":"https://pith.science/pith/OTWV6PFHVXHXV6O7EQT7LVNP5P/action/author_attestation","sign_citation":"https://pith.science/pith/OTWV6PFHVXHXV6O7EQT7LVNP5P/action/citation_signature","submit_replication":"https://pith.science/pith/OTWV6PFHVXHXV6O7EQT7LVNP5P/action/replication_record"}},"created_at":"2026-06-05T01:14:25.257537+00:00","updated_at":"2026-06-05T01:14:25.257537+00:00"}