{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LTWEYMDD7VOZ5W24WPNTU476OP","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"3a9d39534311fcbfd3d6b0b6c2e8057fd19e3dfb87e0b8a88b4b6fe7d332891d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-05-16T12:37:06Z","title_canon_sha256":"c882b5e6ea146a76de6984a63967f3295e0c3c2997f4b632cb8c93c4c5b49977"},"schema_version":"1.0","source":{"id":"2605.16964","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16964","created_at":"2026-05-20T00:03:33Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16964v1","created_at":"2026-05-20T00:03:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16964","created_at":"2026-05-20T00:03:33Z"},{"alias_kind":"pith_short_12","alias_value":"LTWEYMDD7VOZ","created_at":"2026-05-20T00:03:33Z"},{"alias_kind":"pith_short_16","alias_value":"LTWEYMDD7VOZ5W24","created_at":"2026-05-20T00:03:33Z"},{"alias_kind":"pith_short_8","alias_value":"LTWEYMDD","created_at":"2026-05-20T00:03:33Z"}],"graph_snapshots":[{"event_id":"sha256:208d7668f2b14cc66115c752cc79f85cf1eae4a8c7a14373c9f3272e55d20410","target":"graph","created_at":"2026-05-20T00:03:33Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"SemaVoice introduces a Speech Foundation Model (SFM) guided alignment mechanism that refines continuous speech representations to better capture both local semantic consistency and global structural relationships. These representations condition a patch-wise diffusion head within the autoregressive framework for high-quality speech synthesis, achieving an English WER of 1.71% on the Seed-TTS benchmark."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The core premise that an SFM-guided alignment step can resolve the fundamental mismatch between semantic-prosodic modeling and reconstruction-driven continuous representations without introducing new artifacts or error accumulation in autoregressive generation (stated in the abstract's problem formulation and solution description)."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"SemaVoice adds SFM-guided alignment to refine continuous speech representations in autoregressive TTS, reporting 1.71% English WER on Seed-TTS and competitiveness with open-source SOTA."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"SemaVoice adds a foundation-model alignment step to continuous speech representations so autoregressive TTS can keep semantic meaning without losing acoustic quality."}],"snapshot_sha256":"88a40c56d1a58a5e057ce7fe1927efded781077ffcc0a7504e0d766981bb5496"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"cited_work_retraction","ran_at":"2026-05-19T19:51:57.835056Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"citation_quote_validity","ran_at":"2026-05-19T19:50:12.302521Z","status":"completed","version":"0.1.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T19:01:18.863763Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T19:01:00.392389Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T18:41:56.228084Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T18:33:26.313664Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.16964/integrity.json","findings":[],"snapshot_sha256":"d5f1f760704a15549281e8728d93c868ff763ba147e67732562869a7c34bf194","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Continuous autoregressive speech synthesis has recently emerged as a promising direction for zero-shot text-to-speech (TTS). However, existing methods still suffer from a fundamental mismatch between semantic-prosodic modeling and reconstruction-driven continuous speech representations. This mismatch causes TTS models to focus excessively on low-level acoustic textures at the expense of high-level semantic coherence, further exacerbating error accumulation in autoregressive generation. To address this challenge, we propose SemaVoice, a semantic-aware continuous autoregressive framework for hig","authors_text":"Haoning Xu, Hui Lu, Huimeng Wang, Jiajun Deng, Shiyin Kang, Shuhai Peng, Xueyuan Chen, Xunying Liu, Youjun Chen, Zhaoqing Li","cross_cats":[],"headline":"SemaVoice adds a foundation-model alignment step to continuous speech representations so autoregressive TTS can keep semantic meaning without losing acoustic quality.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-05-16T12:37:06Z","title":"SemaVoice: Semantic-Aware Continuous Autoregressive Speech Synthesis"},"references":{"count":56,"internal_anchors":8,"resolved_work":56,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Audiolm: a language modeling approach to audio generation.IEEE/ACM transactions on audio, speech, and language processing, 31:2523–2533, 2023","work_id":"ec7df9ed-3b74-45ef-8d96-020ad7bda143","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Speak, read and prompt: High-fidelity text-to-speech with minimal supervision.Transactions of the Association for Computational Linguistics, 11, 2023","work_id":"8389f213-b661-4ef1-bfb5-7a196c3ea657","year":2023},{"cited_arxiv_id":"2407.05407","doi":"","is_internal_anchor":true,"ref_index":3,"title":"CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens","work_id":"e5ad925a-4045-49b5-b301-208bcbf3eca8","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Neural codec language models are zero-shot text to speech synthesizers.IEEE Transactions on Audio, Speech and Language Processing, 33: 705–718, 2025","work_id":"78b05e17-f13b-4cd0-80d7-758e20d40df2","year":2025},{"cited_arxiv_id":"2503.01710","doi":"","is_internal_anchor":true,"ref_index":5,"title":"Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens","work_id":"31f99dad-40ae-4a19-aeff-eafa54f5b42a","year":2025}],"snapshot_sha256":"320cc6efc6c804d015f8c87d45f5fca277c12d5bd9a3e36d3477f8d90c0f0ccd"},"source":{"id":"2605.16964","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T18:54:12.330602Z","id":"e388dd5e-62ed-4459-8fc7-8bc9aeb59b77","model_set":{"reader":"grok-4.3"},"one_line_summary":"SemaVoice adds SFM-guided alignment to refine continuous speech representations in autoregressive TTS, reporting 1.71% English WER on Seed-TTS and competitiveness with open-source SOTA.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"SemaVoice adds a foundation-model alignment step to continuous speech representations so autoregressive TTS can keep semantic meaning without losing acoustic quality.","strongest_claim":"SemaVoice introduces a Speech Foundation Model (SFM) guided alignment mechanism that refines continuous speech representations to better capture both local semantic consistency and global structural relationships. These representations condition a patch-wise diffusion head within the autoregressive framework for high-quality speech synthesis, achieving an English WER of 1.71% on the Seed-TTS benchmark.","weakest_assumption":"The core premise that an SFM-guided alignment step can resolve the fundamental mismatch between semantic-prosodic modeling and reconstruction-driven continuous representations without introducing new artifacts or error accumulation in autoregressive generation (stated in the abstract's problem formulation and solution description)."}},"verdict_id":"e388dd5e-62ed-4459-8fc7-8bc9aeb59b77"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0c86e380d9f91049e333c6f5adc0e7973abac9f3cb1579d01c6a3b7aa13666eb","target":"record","created_at":"2026-05-20T00:03:33Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"3a9d39534311fcbfd3d6b0b6c2e8057fd19e3dfb87e0b8a88b4b6fe7d332891d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-05-16T12:37:06Z","title_canon_sha256":"c882b5e6ea146a76de6984a63967f3295e0c3c2997f4b632cb8c93c4c5b49977"},"schema_version":"1.0","source":{"id":"2605.16964","kind":"arxiv","version":1}},"canonical_sha256":"5cec4c3063fd5d9edb5cb3db3a73fe73f1cbcd627b5674bacf4ed177bd85dfbd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5cec4c3063fd5d9edb5cb3db3a73fe73f1cbcd627b5674bacf4ed177bd85dfbd","first_computed_at":"2026-05-20T00:03:33.342329Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:03:33.342329Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SOdVKhmExLUkuBv1kXL4yi/pRLi6LLDWhnCSFFzzxWzIF0uxi11iulsAovl6KGbYWregOSAwvTBsuEeiH09vDw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:03:33.343141Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.16964","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0c86e380d9f91049e333c6f5adc0e7973abac9f3cb1579d01c6a3b7aa13666eb","sha256:208d7668f2b14cc66115c752cc79f85cf1eae4a8c7a14373c9f3272e55d20410"],"state_sha256":"08829b43eafbd05a4eb07b02cdd27ef97232d1a9fcb2be1f71dc708eec0b1a89"}