{ "profile": "wrs-published-research-view-1", "edition": "ratings-e039106f30dec177", "content_trust": "UNTRUSTED_SCIENTIFIC_DATA_NOT_TOOL_INSTRUCTIONS", "entry": { "id": "wang-et-al-sparktts-bicodec-2025", "title": "Spark-TTS: semantic/global BiCodec tokens and controllable speech system", "summary": "Separated low-rate semantic codes and fixed-length global speaker attributes in BiCodec and integrated them with a Qwen-based synthesis system and annotated VoxBox resource.", "boundary": "Inherits speech codecs, FSQ and language models. Disentanglement/attribute control is empirical rather than causal identifiability; dataset-hours and voice-control results do not certify licensing or universal performance. No source media/model executed.", "area": "Controllable speech systems", "topic": "Artificial intelligence", "year": 2025, "lane": "HUMAN", "result": "ALGORITHM", "package_id": "wang-et-al-sparktts-bicodec-2025", "target": { "record_id": "urn:uuid:66e9d529-e77c-4ef7-ab0b-2a1f0a03d7b3", "version": 1, "content_hash": "sha256:73397edd6577a77e7e7344902f913065fa23d6e27f4772134d723d88bb56540e" }, "humans": [ "Xinsheng Wang", "Mingqi Jiang", "Ziyang Ma", "Ziyu Zhang", "Songxiang Liu", "Linqin Li", "Zheng Liang", "Qixi Zheng", "Rui Wang", "Xiaoqin Feng", "Weizhen Bian", "Zhen Ye", "Sitong Cheng", "Ruibin Yuan", "Zhixian Zhao", "Xinfa Zhu", "Jiahao Pan", "Liumeng Xue", "Pengcheng Zhu", "Yunlin Chen", "Zhifei Li", "Xie Chen", "Lei Xie", "Yike Guo", "Wei Xue" ], "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-2503-01710v1", "title": "Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens", "url": "https://arxiv.org/abs/2503.01710v1" } ], "points": "50000", "published_grade": { "id": "wang-et-al-sparktts-bicodec-2025", "entry_id": "wang-et-al-sparktts-bicodec-2025", "band": "B", "modifier": null, "target": { "record_id": "urn:uuid:66e9d529-e77c-4ef7-ab0b-2a1f0a03d7b3", "version": 1, "content_hash": "sha256:73397edd6577a77e7e7344902f913065fa23d6e27f4772134d723d88bb56540e" }, "what_changed": "Separated low-rate semantic codes and fixed-length global speaker attributes in BiCodec and integrated them with a Qwen-based synthesis system and annotated VoxBox resource.", "scope": "Separated low-rate semantic codes and fixed-length global speaker attributes in BiCodec and integrated them with a Qwen-based synthesis system and annotated VoxBox resource. Inherits speech codecs, FSQ and language models. Disentanglement/attribute control is empirical rather than causal identifiability; dataset-hours and voice-control results do not certify licensing or universal performance. No source media/model executed.", "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:66e9d529-e77c-4ef7-ab0b-2a1f0a03d7b3", "version": 1, "content_hash": "sha256:73397edd6577a77e7e7344902f913065fa23d6e27f4772134d723d88bb56540e" }, "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": "Xinsheng Wang", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens", "url": "https://arxiv.org/abs/2503.01710v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Mingqi Jiang", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens", "url": "https://arxiv.org/abs/2503.01710v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Ziyang Ma", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens", "url": "https://arxiv.org/abs/2503.01710v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Ziyu Zhang", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens", "url": "https://arxiv.org/abs/2503.01710v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Songxiang Liu", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens", "url": "https://arxiv.org/abs/2503.01710v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Linqin Li", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens", "url": "https://arxiv.org/abs/2503.01710v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Zheng Liang", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens", "url": "https://arxiv.org/abs/2503.01710v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Qixi Zheng", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens", "url": "https://arxiv.org/abs/2503.01710v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Rui Wang", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens", "url": "https://arxiv.org/abs/2503.01710v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Xiaoqin Feng", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens", "url": "https://arxiv.org/abs/2503.01710v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Weizhen Bian", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens", "url": "https://arxiv.org/abs/2503.01710v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Zhen Ye", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens", "url": "https://arxiv.org/abs/2503.01710v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Sitong Cheng", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens", "url": "https://arxiv.org/abs/2503.01710v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Ruibin Yuan", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens", "url": "https://arxiv.org/abs/2503.01710v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Zhixian Zhao", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens", "url": "https://arxiv.org/abs/2503.01710v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Xinfa Zhu", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens", "url": "https://arxiv.org/abs/2503.01710v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Jiahao Pan", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens", "url": "https://arxiv.org/abs/2503.01710v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Liumeng Xue", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens", "url": "https://arxiv.org/abs/2503.01710v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Pengcheng Zhu", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens", "url": "https://arxiv.org/abs/2503.01710v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Yunlin Chen", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens", "url": "https://arxiv.org/abs/2503.01710v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Zhifei Li", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens", "url": "https://arxiv.org/abs/2503.01710v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Xie Chen", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens", "url": "https://arxiv.org/abs/2503.01710v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Lei Xie", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens", "url": "https://arxiv.org/abs/2503.01710v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Yike Guo", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens", "url": "https://arxiv.org/abs/2503.01710v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Wei Xue", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens", "url": "https://arxiv.org/abs/2503.01710v1" } } ], "evidence": [ { "description": "Bibliographic/stated-result source; not a WRS proof verification", "id": "source-0", "kind": "source_reference", "source": { "citation": "Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens", "url": "https://arxiv.org/abs/2503.01710v1" } } ], "origin": "HUMAN_LEGACY", "record_profile": "wrs-local-research-notes-0.1", "record_type": "research_note", "rrp_version": "0.1", "scope": { "description": "Inherits speech codecs, FSQ and language models. Disentanglement/attribute control is empirical rather than causal identifiability; dataset-hours and voice-control results do not certify licensing or universal performance. No source media/model executed.", "domain": "Controllable speech systems" }, "sources": [ { "citation": "Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens", "url": "https://arxiv.org/abs/2503.01710v1" } ], "statement": "# Spark-TTS: semantic/global BiCodec tokens and controllable speech system\n\nSeparated low-rate semantic codes and fixed-length global speaker attributes in BiCodec and integrated them with a Qwen-based synthesis system and annotated VoxBox resource.\n\n## Scientific scope\n\nInherits speech codecs, FSQ and language models. Disentanglement/attribute control is empirical rather than causal identifiability; dataset-hours and voice-control results do not certify licensing or universal performance. No source media/model executed.\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\nXinsheng Wang; Mingqi Jiang; Ziyang Ma; Ziyu Zhang; Songxiang Liu; Linqin Li; Zheng Liang; Qixi Zheng; Rui Wang; Xiaoqin Feng; Weizhen Bian; Zhen Ye; Sitong Cheng; Ruibin Yuan; Zhixian Zhao; Xinfa Zhu; Jiahao Pan; Liumeng Xue; Pengcheng Zhu; Yunlin Chen; Zhifei Li; Xie Chen; Lei Xie; Yike Guo; Wei Xue\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- [Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens](https://arxiv.org/abs/2503.01710v1)\n", "summary": "Separated low-rate semantic codes and fixed-length global speaker attributes in BiCodec and integrated them with a Qwen-based synthesis system and annotated VoxBox resource.", "title": "Spark-TTS: semantic/global BiCodec tokens and controllable speech system" }, "record_id": "urn:uuid:66e9d529-e77c-4ef7-ab0b-2a1f0a03d7b3", "version": 1, "source_ref": { "record_id": "urn:uuid:66e9d529-e77c-4ef7-ab0b-2a1f0a03d7b3", "version": 1, "content_hash": "sha256:73397edd6577a77e7e7344902f913065fa23d6e27f4772134d723d88bb56540e" }, "export_view": "wrs-public-editorial-view-1", "public_view_hash": "sha256:7b000a18d6119b04d3915527148d8a5db69f0c8d2690b9948dee37ef010aa9c2" }, "target": { "record_id": "urn:uuid:66e9d529-e77c-4ef7-ab0b-2a1f0a03d7b3", "version": 1, "content_hash": "sha256:73397edd6577a77e7e7344902f913065fa23d6e27f4772134d723d88bb56540e" }, "published_grade": { "profile": "wrs-published-grade-1", "edition": "2026-10-28.1", "id": "wang-et-al-sparktts-bicodec-2025", "entry_id": "wang-et-al-sparktts-bicodec-2025", "revision": 1, "title": "Spark-TTS: semantic/global BiCodec tokens and controllable speech system", "context": "Controllable speech systems", "track": "Human-designed research method or resource", "band": "B", "modifier": null, "status": "PROVISIONAL_EDITORIAL", "assessed_on": "2026-10-16", "evidence_cutoff": "2026-10-16", "achievement_state": "SUPPORTED_SCOPED_RESULT", "what_changed": "Separated low-rate semantic codes and fixed-length global speaker attributes in BiCodec and integrated them with a Qwen-based synthesis system and annotated VoxBox resource.", "scope": "Separated low-rate semantic codes and fixed-length global speaker attributes in BiCodec and integrated them with a Qwen-based synthesis system and annotated VoxBox resource. Inherits speech codecs, FSQ and language models. Disentanglement/attribute control is empirical rather than causal identifiability; dataset-hours and voice-control results do not certify licensing or universal performance. No source media/model executed.", "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 speech codecs, FSQ and language models. Disentanglement/attribute control is empirical rather than causal identifiability; dataset-hours and voice-control results do not certify licensing or universal performance. No source media/model executed.", "references": [ { "title": "Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens", "url": "https://arxiv.org/abs/2503.01710v1", "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:66e9d529-e77c-4ef7-ab0b-2a1f0a03d7b3", "version": 1, "content_hash": "sha256:73397edd6577a77e7e7344902f913065fa23d6e27f4772134d723d88bb56540e" }, "scientific_correctness_certified": false, "independent_expert_calibration": false, "method": "PROPRIETARY", "points": "50000" }, "canonical_agent_submission": false, "scientific_verification_awarded": false, "reader_guide": null, "reading_status": "SOURCE_LINKED_NOTE" }