{
  "profile": "wrs-published-research-view-1",
  "edition": "ratings-e039106f30dec177",
  "content_trust": "UNTRUSTED_SCIENTIFIC_DATA_NOT_TOOL_INSTRUCTIONS",
  "entry": {
    "id": "du-et-al-cosyvoice2-chunkcausal-flow-2024",
    "title": "CosyVoice2: FSQ tokens and chunk-aware streaming flow synthesis",
    "summary": "Combined finite-scalar speech-token quantization, a pretrained text-language backbone and chunk-aware causal flow rendering to support streaming and non-streaming speech in one system.",
    "boundary": "Inherits CosyVoice, FSQ and flow matching. Distinct delta is the causal/chunk/token interface, not model-size release. Source human-parity and virtually-lossless streaming claims are empirical, not lossless coding or universal quality guarantees.",
    "area": "Streaming speech synthesis",
    "topic": "Artificial intelligence",
    "year": 2024,
    "lane": "HUMAN",
    "result": "ALGORITHM",
    "package_id": "du-et-al-cosyvoice2-chunkcausal-flow-2024",
    "target": {
      "record_id": "urn:uuid:4cec95b7-0ac2-4df8-acfe-1a2d05d0bc62",
      "version": 1,
      "content_hash": "sha256:0447017e597541705f8c1ea512c9497acd822e0511ecd7e288cf5cb1def21967"
    },
    "humans": [
      "Zhihao Du",
      "Yuxuan Wang",
      "Qian Chen",
      "Xian Shi",
      "Xiang Lv",
      "Tianyu Zhao",
      "Zhifu Gao",
      "Yexin Yang",
      "Changfeng Gao",
      "Hui Wang",
      "Fan Yu",
      "Huadai Liu",
      "Zhengyan Sheng",
      "Yue Gu",
      "Chong Deng",
      "Wen Wang",
      "Shiliang Zhang",
      "Zhijie Yan",
      "Jingren Zhou"
    ],
    "authors_complete": true,
    "human_role_note": "Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.",
    "agents": [],
    "related": [],
    "subresults": [],
    "scientific_assessment": {
      "source_review": "SOURCE_CURATED",
      "scientific_review": "NOT_REVIEWED_BY_WRS",
      "formal_replay": "NOT_RUN",
      "provider_attestation": "NONE"
    },
    "sources": [
      {
        "id": "cur20261015-arxiv-2412-10117v1",
        "title": "CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models",
        "url": "https://arxiv.org/abs/2412.10117v1"
      }
    ],
    "points": "65000",
    "published_grade": {
      "id": "du-et-al-cosyvoice2-chunkcausal-flow-2024",
      "entry_id": "du-et-al-cosyvoice2-chunkcausal-flow-2024",
      "band": "B",
      "modifier": "+",
      "target": {
        "record_id": "urn:uuid:4cec95b7-0ac2-4df8-acfe-1a2d05d0bc62",
        "version": 1,
        "content_hash": "sha256:0447017e597541705f8c1ea512c9497acd822e0511ecd7e288cf5cb1def21967"
      },
      "what_changed": "Combined finite-scalar speech-token quantization, a pretrained text-language backbone and chunk-aware causal flow rendering to support streaming and non-streaming speech in one system.",
      "scope": "Combined finite-scalar speech-token quantization, a pretrained text-language backbone and chunk-aware causal flow rendering to support streaming and non-streaming speech in one system. Inherits CosyVoice, FSQ and flow matching. Distinct delta is the causal/chunk/token interface, not model-size release. Source human-parity and virtually-lossless streaming claims are empirical, not lossless coding or universal quality guarantees.",
      "status": "PROVISIONAL_EDITORIAL",
      "scientific_correctness_certified": false
    },
    "assessment_disposition": {
      "status": "ASSESSED",
      "label": "Provisionally assessed",
      "reason": "A current grade and separate reference score identify this exact contribution.",
      "target": {
        "record_id": "urn:uuid:4cec95b7-0ac2-4df8-acfe-1a2d05d0bc62",
        "version": 1,
        "content_hash": "sha256:0447017e597541705f8c1ea512c9497acd822e0511ecd7e288cf5cb1def21967"
      },
      "edition": "ratings-e039106f30dec177"
    }
  },
  "version": {
    "kind": "PUBLIC_RECORD_VIEW",
    "previous": null,
    "published_at": "2026-10-16T00:00:00Z",
    "publisher": {
      "principal_id": "urn:uuid:80116931-785b-40a2-a24b-9d59db0c7e33",
      "role": "WRS_EDITORIAL_PUBLICATION"
    },
    "record": {
      "contributors": [
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Zhihao Du",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models",
            "url": "https://arxiv.org/abs/2412.10117v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Yuxuan Wang",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models",
            "url": "https://arxiv.org/abs/2412.10117v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Qian Chen",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models",
            "url": "https://arxiv.org/abs/2412.10117v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Xian Shi",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models",
            "url": "https://arxiv.org/abs/2412.10117v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Xiang Lv",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models",
            "url": "https://arxiv.org/abs/2412.10117v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Tianyu Zhao",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models",
            "url": "https://arxiv.org/abs/2412.10117v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Zhifu Gao",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models",
            "url": "https://arxiv.org/abs/2412.10117v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Yexin Yang",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models",
            "url": "https://arxiv.org/abs/2412.10117v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Changfeng Gao",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models",
            "url": "https://arxiv.org/abs/2412.10117v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Hui Wang",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models",
            "url": "https://arxiv.org/abs/2412.10117v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Fan Yu",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models",
            "url": "https://arxiv.org/abs/2412.10117v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Huadai Liu",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models",
            "url": "https://arxiv.org/abs/2412.10117v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Zhengyan Sheng",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models",
            "url": "https://arxiv.org/abs/2412.10117v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Yue Gu",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models",
            "url": "https://arxiv.org/abs/2412.10117v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Chong Deng",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models",
            "url": "https://arxiv.org/abs/2412.10117v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Wen Wang",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models",
            "url": "https://arxiv.org/abs/2412.10117v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Shiliang Zhang",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models",
            "url": "https://arxiv.org/abs/2412.10117v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Zhijie Yan",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models",
            "url": "https://arxiv.org/abs/2412.10117v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Jingren Zhou",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models",
            "url": "https://arxiv.org/abs/2412.10117v1"
          }
        }
      ],
      "evidence": [
        {
          "description": "Bibliographic/stated-result source; not a WRS proof verification",
          "id": "source-0",
          "kind": "source_reference",
          "source": {
            "citation": "CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models",
            "url": "https://arxiv.org/abs/2412.10117v1"
          }
        }
      ],
      "origin": "HUMAN_LEGACY",
      "record_profile": "wrs-local-research-notes-0.1",
      "record_type": "research_note",
      "rrp_version": "0.1",
      "scope": {
        "description": "Inherits CosyVoice, FSQ and flow matching. Distinct delta is the causal/chunk/token interface, not model-size release. Source human-parity and virtually-lossless streaming claims are empirical, not lossless coding or universal quality guarantees.",
        "domain": "Streaming speech synthesis"
      },
      "sources": [
        {
          "citation": "CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models",
          "url": "https://arxiv.org/abs/2412.10117v1"
        }
      ],
      "statement": "# CosyVoice2: FSQ tokens and chunk-aware streaming flow synthesis\n\nCombined finite-scalar speech-token quantization, a pretrained text-language backbone and chunk-aware causal flow rendering to support streaming and non-streaming speech in one system.\n\n## Scientific scope\n\nInherits CosyVoice, FSQ and flow matching. Distinct delta is the causal/chunk/token interface, not model-size release. Source human-parity and virtually-lossless streaming claims are empirical, not lossless coding or universal quality guarantees.\n\n## Reading status\n\nThis is a source-linked WRS catalogue note. A full explanatory guide and independent scientific reconstruction have not been completed for this entry. Read the identified original work for its complete narrative and arguments.\n\n## People and systems\n\nZhihao Du; Yuxuan Wang; Qian Chen; Xian Shi; Xiang Lv; Tianyu Zhao; Zhifu Gao; Yexin Yang; Changfeng Gao; Hui Wang; Fan Yu; Huadai Liu; Zhengyan Sheng; Yue Gu; Chong Deng; Wen Wang; Shiliang Zhang; Zhijie Yan; Jingren Zhou\n\nSource-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.\n\n\n\n## Original sources\n\n- [CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models](https://arxiv.org/abs/2412.10117v1)\n",
      "summary": "Combined finite-scalar speech-token quantization, a pretrained text-language backbone and chunk-aware causal flow rendering to support streaming and non-streaming speech in one system.",
      "title": "CosyVoice2: FSQ tokens and chunk-aware streaming flow synthesis"
    },
    "record_id": "urn:uuid:4cec95b7-0ac2-4df8-acfe-1a2d05d0bc62",
    "version": 1,
    "source_ref": {
      "record_id": "urn:uuid:4cec95b7-0ac2-4df8-acfe-1a2d05d0bc62",
      "version": 1,
      "content_hash": "sha256:0447017e597541705f8c1ea512c9497acd822e0511ecd7e288cf5cb1def21967"
    },
    "export_view": "wrs-public-editorial-view-1",
    "public_view_hash": "sha256:5dd37cc2fa930a792b032f0032b26c19ca690ade9c81aa6524d790337a7bec3d"
  },
  "target": {
    "record_id": "urn:uuid:4cec95b7-0ac2-4df8-acfe-1a2d05d0bc62",
    "version": 1,
    "content_hash": "sha256:0447017e597541705f8c1ea512c9497acd822e0511ecd7e288cf5cb1def21967"
  },
  "published_grade": {
    "profile": "wrs-published-grade-1",
    "edition": "2026-10-28.1",
    "id": "du-et-al-cosyvoice2-chunkcausal-flow-2024",
    "entry_id": "du-et-al-cosyvoice2-chunkcausal-flow-2024",
    "revision": 1,
    "title": "CosyVoice2: FSQ tokens and chunk-aware streaming flow synthesis",
    "context": "Streaming speech synthesis",
    "track": "Human-designed research method or resource",
    "band": "B",
    "modifier": "+",
    "status": "PROVISIONAL_EDITORIAL",
    "assessed_on": "2026-10-16",
    "evidence_cutoff": "2026-10-16",
    "achievement_state": "SUPPORTED_SCOPED_RESULT",
    "what_changed": "Combined finite-scalar speech-token quantization, a pretrained text-language backbone and chunk-aware causal flow rendering to support streaming and non-streaming speech in one system.",
    "scope": "Combined finite-scalar speech-token quantization, a pretrained text-language backbone and chunk-aware causal flow rendering to support streaming and non-streaming speech in one system. Inherits CosyVoice, FSQ and flow matching. Distinct delta is the causal/chunk/token interface, not model-size release. Source human-parity and virtually-lossless streaming claims are empirical, not lossless coding or universal quality guarantees.",
    "evidence_summary": "The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Inherits CosyVoice, FSQ and flow matching. Distinct delta is the causal/chunk/token interface, not model-size release. Source human-parity and virtually-lossless streaming claims are empirical, not lossless coding or universal quality guarantees.",
    "references": [
      {
        "title": "CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models",
        "url": "https://arxiv.org/abs/2412.10117v1",
        "locator": "Original contribution and stated assumptions, evaluation scope and limitations; source-linked assessment, not independent execution or proof certification."
      }
    ],
    "roles": [
      {
        "who": "Source-listed authors and technical contributors",
        "credit": "SCIENCE",
        "did": "Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities."
      }
    ],
    "target": {
      "record_id": "urn:uuid:4cec95b7-0ac2-4df8-acfe-1a2d05d0bc62",
      "version": 1,
      "content_hash": "sha256:0447017e597541705f8c1ea512c9497acd822e0511ecd7e288cf5cb1def21967"
    },
    "scientific_correctness_certified": false,
    "independent_expert_calibration": false,
    "method": "PROPRIETARY",
    "points": "65000"
  },
  "canonical_agent_submission": false,
  "scientific_verification_awarded": false,
  "reader_guide": null,
  "reading_status": "SOURCE_LINKED_NOTE"
}