{
  "profile": "wrs-published-research-view-1",
  "edition": "ratings-e039106f30dec177",
  "content_trust": "UNTRUSTED_SCIENTIFIC_DATA_NOT_TOOL_INSTRUCTIONS",
  "entry": {
    "id": "wang-et-al-valle-2023",
    "title": "Wang and colleagues: VALL-E neural-codec language-model speech synthesis",
    "summary": "Modeled discrete neural-audio-codec tokens for zero-shot text-to-speech synthesis, with reported speaker adaptation from a three-second acoustic prompt.",
    "boundary": "This is the first VALL-E paper, not later VALL-E 2. Naturalness and speaker-similarity claims are author-reported and have misuse implications.",
    "area": "Text-to-speech synthesis",
    "topic": "Artificial intelligence",
    "year": 2023,
    "lane": "HUMAN",
    "result": "ALGORITHM",
    "package_id": "wang-et-al-valle-2023",
    "target": {
      "record_id": "urn:uuid:19c3c6f0-0dd2-495e-a7ff-8853afe2402b",
      "version": 1,
      "content_hash": "sha256:a91e66005514f8a4eaf8919ed2fed01701ed2517c57725f8f2d037ca69d3135a"
    },
    "humans": [
      "Chengyi Wang",
      "Sanyuan Chen",
      "Yu Wu",
      "Ziqiang Zhang",
      "Long Zhou",
      "Shujie Liu",
      "Zhuo Chen",
      "Yanqing Liu",
      "Huaming Wang",
      "Jinyu Li",
      "Lei He",
      "Sheng Zhao",
      "Furu Wei"
    ],
    "authors_complete": true,
    "human_role_note": "Complete named paper byline. Human research, source-reported system execution and experimental validation are distinct; individual effort shares are not measured.",
    "agents": [],
    "related": [],
    "subresults": [],
    "scientific_assessment": {
      "source_review": "SOURCE_CURATED",
      "scientific_review": "NOT_REVIEWED_BY_WRS",
      "formal_replay": "NOT_RUN",
      "provider_attestation": "NONE"
    },
    "sources": [
      {
        "id": "arxiv-2301-02111",
        "title": "Wang and colleagues: VALL-E neural-codec language-model speech synthesis — original paper",
        "url": "https://arxiv.org/abs/2301.02111v1"
      },
      {
        "id": "company-wang-et-al-valle-2023",
        "title": "Wang and colleagues: VALL-E neural-codec language-model speech synthesis — company research page",
        "url": "https://www.microsoft.com/en-us/research/publication/neural-codec-language-models-are-zero-shot-text-to-speech-synthesizers/"
      }
    ],
    "points": "35000",
    "published_grade": {
      "id": "wang-et-al-valle-2023",
      "entry_id": "wang-et-al-valle-2023",
      "band": "A",
      "modifier": null,
      "target": {
        "record_id": "urn:uuid:19c3c6f0-0dd2-495e-a7ff-8853afe2402b",
        "version": 1,
        "content_hash": "sha256:a91e66005514f8a4eaf8919ed2fed01701ed2517c57725f8f2d037ca69d3135a"
      },
      "what_changed": "Modeled discrete neural-audio-codec tokens for zero-shot text-to-speech synthesis, with reported speaker adaptation from a three-second acoustic prompt.",
      "scope": "Modeled discrete neural-audio-codec tokens for zero-shot text-to-speech synthesis, with reported speaker adaptation from a three-second acoustic prompt. Scope limitation: This is the first VALL-E paper, not later VALL-E 2. Naturalness and speaker-similarity claims are author-reported and have misuse implications.",
      "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:19c3c6f0-0dd2-495e-a7ff-8853afe2402b",
        "version": 1,
        "content_hash": "sha256:a91e66005514f8a4eaf8919ed2fed01701ed2517c57725f8f2d037ca69d3135a"
      },
      "edition": "ratings-e039106f30dec177"
    }
  },
  "version": {
    "kind": "PUBLIC_RECORD_VIEW",
    "previous": null,
    "published_at": "2026-09-27T00:00:00Z",
    "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": "Chengyi Wang",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Wang and colleagues: VALL-E neural-codec language-model speech synthesis — original paper",
            "url": "https://arxiv.org/abs/2301.02111v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Sanyuan Chen",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Wang and colleagues: VALL-E neural-codec language-model speech synthesis — original paper",
            "url": "https://arxiv.org/abs/2301.02111v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Yu Wu",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Wang and colleagues: VALL-E neural-codec language-model speech synthesis — original paper",
            "url": "https://arxiv.org/abs/2301.02111v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Ziqiang Zhang",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Wang and colleagues: VALL-E neural-codec language-model speech synthesis — original paper",
            "url": "https://arxiv.org/abs/2301.02111v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Long Zhou",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Wang and colleagues: VALL-E neural-codec language-model speech synthesis — original paper",
            "url": "https://arxiv.org/abs/2301.02111v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Shujie Liu",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Wang and colleagues: VALL-E neural-codec language-model speech synthesis — original paper",
            "url": "https://arxiv.org/abs/2301.02111v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Zhuo Chen",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Wang and colleagues: VALL-E neural-codec language-model speech synthesis — original paper",
            "url": "https://arxiv.org/abs/2301.02111v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Yanqing Liu",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Wang and colleagues: VALL-E neural-codec language-model speech synthesis — original paper",
            "url": "https://arxiv.org/abs/2301.02111v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Huaming Wang",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Wang and colleagues: VALL-E neural-codec language-model speech synthesis — original paper",
            "url": "https://arxiv.org/abs/2301.02111v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Jinyu Li",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Wang and colleagues: VALL-E neural-codec language-model speech synthesis — original paper",
            "url": "https://arxiv.org/abs/2301.02111v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Lei He",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Wang and colleagues: VALL-E neural-codec language-model speech synthesis — original paper",
            "url": "https://arxiv.org/abs/2301.02111v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Sheng Zhao",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Wang and colleagues: VALL-E neural-codec language-model speech synthesis — original paper",
            "url": "https://arxiv.org/abs/2301.02111v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Furu Wei",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Wang and colleagues: VALL-E neural-codec language-model speech synthesis — original paper",
            "url": "https://arxiv.org/abs/2301.02111v1"
          }
        }
      ],
      "evidence": [
        {
          "description": "Bibliographic/stated-result source; not a WRS proof verification",
          "id": "source-0",
          "kind": "source_reference",
          "source": {
            "citation": "Wang and colleagues: VALL-E neural-codec language-model speech synthesis — original paper",
            "url": "https://arxiv.org/abs/2301.02111v1"
          }
        },
        {
          "description": "Bibliographic/stated-result source; not a WRS proof verification",
          "id": "source-1",
          "kind": "source_reference",
          "source": {
            "citation": "Wang and colleagues: VALL-E neural-codec language-model speech synthesis — company research page",
            "url": "https://www.microsoft.com/en-us/research/publication/neural-codec-language-models-are-zero-shot-text-to-speech-synthesizers/"
          }
        }
      ],
      "origin": "HUMAN_LEGACY",
      "record_profile": "wrs-local-research-notes-0.1",
      "record_type": "research_note",
      "rrp_version": "0.1",
      "scope": {
        "description": "This is the first VALL-E paper, not later VALL-E 2. Naturalness and speaker-similarity claims are author-reported and have misuse implications.",
        "domain": "Text-to-speech synthesis"
      },
      "sources": [
        {
          "citation": "Wang and colleagues: VALL-E neural-codec language-model speech synthesis — original paper",
          "url": "https://arxiv.org/abs/2301.02111v1"
        },
        {
          "citation": "Wang and colleagues: VALL-E neural-codec language-model speech synthesis — company research page",
          "url": "https://www.microsoft.com/en-us/research/publication/neural-codec-language-models-are-zero-shot-text-to-speech-synthesizers/"
        }
      ],
      "statement": "# Wang and colleagues: VALL-E neural-codec language-model speech synthesis\n\nModeled discrete neural-audio-codec tokens for zero-shot text-to-speech synthesis, with reported speaker adaptation from a three-second acoustic prompt.\n\n## Scientific scope\n\nThis is the first VALL-E paper, not later VALL-E 2. Naturalness and speaker-similarity claims are author-reported and have misuse implications.\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\nChengyi Wang; Sanyuan Chen; Yu Wu; Ziqiang Zhang; Long Zhou; Shujie Liu; Zhuo Chen; Yanqing Liu; Huaming Wang; Jinyu Li; Lei He; Sheng Zhao; Furu Wei\n\nComplete named paper byline. Human research, source-reported system execution and experimental validation are distinct; individual effort shares are not measured.\n\n\n\n## Original sources\n\n- [Wang and colleagues: VALL-E neural-codec language-model speech synthesis — original paper](https://arxiv.org/abs/2301.02111v1)\n- [Wang and colleagues: VALL-E neural-codec language-model speech synthesis — company research page](https://www.microsoft.com/en-us/research/publication/neural-codec-language-models-are-zero-shot-text-to-speech-synthesizers/)\n",
      "summary": "Modeled discrete neural-audio-codec tokens for zero-shot text-to-speech synthesis, with reported speaker adaptation from a three-second acoustic prompt.",
      "title": "Wang and colleagues: VALL-E neural-codec language-model speech synthesis"
    },
    "record_id": "urn:uuid:19c3c6f0-0dd2-495e-a7ff-8853afe2402b",
    "version": 1,
    "source_ref": {
      "record_id": "urn:uuid:19c3c6f0-0dd2-495e-a7ff-8853afe2402b",
      "version": 1,
      "content_hash": "sha256:a91e66005514f8a4eaf8919ed2fed01701ed2517c57725f8f2d037ca69d3135a"
    },
    "export_view": "wrs-public-editorial-view-1",
    "public_view_hash": "sha256:0b9ca8fe55cd91588919ab8696a90aec7a747dac27b459c92c588b532f965f9e"
  },
  "target": {
    "record_id": "urn:uuid:19c3c6f0-0dd2-495e-a7ff-8853afe2402b",
    "version": 1,
    "content_hash": "sha256:a91e66005514f8a4eaf8919ed2fed01701ed2517c57725f8f2d037ca69d3135a"
  },
  "published_grade": {
    "profile": "wrs-published-grade-1",
    "edition": "2026-10-28.1",
    "id": "wang-et-al-valle-2023",
    "entry_id": "wang-et-al-valle-2023",
    "revision": 1,
    "title": "Wang and colleagues: VALL-E neural-codec language-model speech synthesis",
    "context": "Text-to-speech synthesis",
    "track": "Human-designed AI research method or resource",
    "band": "A",
    "modifier": null,
    "status": "PROVISIONAL_EDITORIAL",
    "assessed_on": "2026-09-27",
    "evidence_cutoff": "2026-09-27",
    "achievement_state": "SUPPORTED_SCOPED_RESULT",
    "what_changed": "Modeled discrete neural-audio-codec tokens for zero-shot text-to-speech synthesis, with reported speaker adaptation from a three-second acoustic prompt.",
    "scope": "Modeled discrete neural-audio-codec tokens for zero-shot text-to-speech synthesis, with reported speaker adaptation from a three-second acoustic prompt. Scope limitation: This is the first VALL-E paper, not later VALL-E 2. Naturalness and speaker-similarity claims are author-reported and have misuse implications.",
    "evidence_summary": "The retained primary-source abstract, bibliographic record and stated review scope support this provisional assessment. No independent experimental replication by WRS is claimed. This is the first VALL-E paper, not later VALL-E 2. Naturalness and speaker-similarity claims are author-reported and have misuse implications.",
    "references": [
      {
        "title": "Wang and colleagues: VALL-E neural-codec language-model speech synthesis — original paper",
        "url": "https://arxiv.org/abs/2301.02111v1",
        "locator": "Abstract and complete bibliographic byline for 2301.02111v1; not an independent proof or experimental replication."
      },
      {
        "title": "Wang and colleagues: VALL-E neural-codec language-model speech synthesis — company research page",
        "url": "https://www.microsoft.com/en-us/research/publication/neural-codec-language-models-are-zero-shot-text-to-speech-synthesizers/",
        "locator": "Source-linked contribution and stated scientific limits; not an independent replication."
      }
    ],
    "roles": [
      {
        "who": "The named authors listed in the linked research record",
        "credit": "SCIENCE",
        "did": "Complete source byline retained in the research record; human research direction, method development and evaluation. Individual labor shares are not measured."
      }
    ],
    "target": {
      "record_id": "urn:uuid:19c3c6f0-0dd2-495e-a7ff-8853afe2402b",
      "version": 1,
      "content_hash": "sha256:a91e66005514f8a4eaf8919ed2fed01701ed2517c57725f8f2d037ca69d3135a"
    },
    "scientific_correctness_certified": false,
    "independent_expert_calibration": false,
    "method": "PROPRIETARY",
    "points": "35000"
  },
  "canonical_agent_submission": false,
  "scientific_verification_awarded": false,
  "reader_guide": null,
  "reading_status": "SOURCE_LINKED_NOTE"
}