{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5NZERKDHLLG76PJQ2YZDTMYS4X","short_pith_number":"pith:5NZERKDH","schema_version":"1.0","canonical_sha256":"eb7248a8675acdff3d30d63239b312e5c78602a578753879d914a6d4ae58b764","source":{"kind":"arxiv","id":"2509.06502","version":1},"attestation_state":"computed","paper":{"title":"FireRedChat: A Pluggable, Full-Duplex Voice Interaction System with Cascaded and Semi-Cascaded Implementations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.SD","authors_text":"Feiyu Shen, Fenglong Xie, Junjie Chen, Junjie Li, Kaituo Xu, Kangyue Li, Kun Liu, Kun Xie, Manzhen Wei, Wenpeng Li, Xu Li, Xu Tang, Yao Hu, Yichen Wu, Ziyuan Li","submitted_at":"2025-09-08T10:07:30Z","abstract_excerpt":"Full-duplex voice interaction allows users and agents to speak simultaneously with controllable barge-in, enabling lifelike assistants and customer service. Existing solutions are either end-to-end, difficult to design and hard to control, or modular pipelines governed by turn-taking controllers that ease upgrades and per-module optimization; however, prior modular frameworks depend on non-open components and external providers, limiting holistic optimization. In this work, we present a complete, practical full-duplex voice interaction system comprising a turn-taking controller, an interaction"},"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":"2509.06502","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-09-08T10:07:30Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"73a18357edd7e453898596e48327a8c927be7bfdb5f6781868c55242ff2636f2","abstract_canon_sha256":"a1b966dc84e8035ac7c8c64a1e0bd5d6e2ba813271eb4110c88f2b5ea9faebc3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:37.159148Z","signature_b64":"NQFHajmjoBHDVZ2/gFS/yqy1QfnVSD7wDXLQDzF5jSxW8i3O71dbgX5QB1399QCEqdZqHw85lXxWRo5Ueeu5Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb7248a8675acdff3d30d63239b312e5c78602a578753879d914a6d4ae58b764","last_reissued_at":"2026-07-05T12:06:37.158608Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:37.158608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FireRedChat: A Pluggable, Full-Duplex Voice Interaction System with Cascaded and Semi-Cascaded Implementations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.SD","authors_text":"Feiyu Shen, Fenglong Xie, Junjie Chen, Junjie Li, Kaituo Xu, Kangyue Li, Kun Liu, Kun Xie, Manzhen Wei, Wenpeng Li, Xu Li, Xu Tang, Yao Hu, Yichen Wu, Ziyuan Li","submitted_at":"2025-09-08T10:07:30Z","abstract_excerpt":"Full-duplex voice interaction allows users and agents to speak simultaneously with controllable barge-in, enabling lifelike assistants and customer service. Existing solutions are either end-to-end, difficult to design and hard to control, or modular pipelines governed by turn-taking controllers that ease upgrades and per-module optimization; however, prior modular frameworks depend on non-open components and external providers, limiting holistic optimization. In this work, we present a complete, practical full-duplex voice interaction system comprising a turn-taking controller, an interaction"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.06502","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/2509.06502/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":"2509.06502","created_at":"2026-07-05T12:06:37.158672+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.06502v1","created_at":"2026-07-05T12:06:37.158672+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.06502","created_at":"2026-07-05T12:06:37.158672+00:00"},{"alias_kind":"pith_short_12","alias_value":"5NZERKDHLLG7","created_at":"2026-07-05T12:06:37.158672+00:00"},{"alias_kind":"pith_short_16","alias_value":"5NZERKDHLLG76PJQ","created_at":"2026-07-05T12:06:37.158672+00:00"},{"alias_kind":"pith_short_8","alias_value":"5NZERKDH","created_at":"2026-07-05T12:06:37.158672+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06540","citing_title":"Hierarchical Acoustic-Semantic Modeling: Modality Separation and Semantic Coherence for Full-Duplex SLMs","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2606.19453","citing_title":"A Survey of Full-Duplex Spoken Dialogue Systems: Architectural Hierarchy, Interaction Ontology, and Decision State Machine","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18094","citing_title":"Next-Turn: Duration-Aware Streaming Endpoint Detection via Time-to-Next-Speech-Onset Prediction","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09186","citing_title":"DuplexOmni: Real-Time Listening, Seeing, Thinking, and Speaking for Full-Duplex Interaction","ref_index":1,"is_internal_anchor":false},{"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":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25343","citing_title":"Toward Native Multimodal Modeling: A Roadmap","ref_index":242,"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":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20266","citing_title":"A Survey of Large Audio Language Models: Generalization, Trustworthiness, and Outlook","ref_index":134,"is_internal_anchor":false},{"citing_arxiv_id":"2604.01897","citing_title":"FastTurn: Unifying Acoustic and Streaming Semantic Cues for Low-Latency and Robust Turn Detection","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21406","citing_title":"Full-Duplex Interaction in Spoken Dialogue Systems: A Comprehensive Study from the ICASSP 2026 HumDial Challenge","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19221","citing_title":"UAF: A Unified Audio Front-end LLM for Full-Duplex Speech Interaction","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13804","citing_title":"Character Beyond Speech: Leveraging Role-Playing Evaluation in Audio Large Language Models via Reinforcement Learning","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5NZERKDHLLG76PJQ2YZDTMYS4X","json":"https://pith.science/pith/5NZERKDHLLG76PJQ2YZDTMYS4X.json","graph_json":"https://pith.science/api/pith-number/5NZERKDHLLG76PJQ2YZDTMYS4X/graph.json","events_json":"https://pith.science/api/pith-number/5NZERKDHLLG76PJQ2YZDTMYS4X/events.json","paper":"https://pith.science/paper/5NZERKDH"},"agent_actions":{"view_html":"https://pith.science/pith/5NZERKDHLLG76PJQ2YZDTMYS4X","download_json":"https://pith.science/pith/5NZERKDHLLG76PJQ2YZDTMYS4X.json","view_paper":"https://pith.science/paper/5NZERKDH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.06502&json=true","fetch_graph":"https://pith.science/api/pith-number/5NZERKDHLLG76PJQ2YZDTMYS4X/graph.json","fetch_events":"https://pith.science/api/pith-number/5NZERKDHLLG76PJQ2YZDTMYS4X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5NZERKDHLLG76PJQ2YZDTMYS4X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5NZERKDHLLG76PJQ2YZDTMYS4X/action/storage_attestation","attest_author":"https://pith.science/pith/5NZERKDHLLG76PJQ2YZDTMYS4X/action/author_attestation","sign_citation":"https://pith.science/pith/5NZERKDHLLG76PJQ2YZDTMYS4X/action/citation_signature","submit_replication":"https://pith.science/pith/5NZERKDHLLG76PJQ2YZDTMYS4X/action/replication_record"}},"created_at":"2026-07-05T12:06:37.158672+00:00","updated_at":"2026-07-05T12:06:37.158672+00:00"}