{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LTWEYMDD7VOZ5W24WPNTU476OP","short_pith_number":"pith:LTWEYMDD","schema_version":"1.0","canonical_sha256":"5cec4c3063fd5d9edb5cb3db3a73fe73f1cbcd627b5674bacf4ed177bd85dfbd","source":{"kind":"arxiv","id":"2605.16964","version":1},"attestation_state":"computed","paper":{"title":"SemaVoice: Semantic-Aware Continuous Autoregressive Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"SemaVoice adds a foundation-model alignment step to continuous speech representations so autoregressive TTS can keep semantic meaning without losing acoustic quality.","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Haoning Xu, Hui Lu, Huimeng Wang, Jiajun Deng, Shiyin Kang, Shuhai Peng, Xueyuan Chen, Xunying Liu, Youjun Chen, Zhaoqing Li","submitted_at":"2026-05-16T12:37:06Z","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"},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.16964","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-05-16T12:37:06Z","cross_cats_sorted":[],"title_canon_sha256":"c882b5e6ea146a76de6984a63967f3295e0c3c2997f4b632cb8c93c4c5b49977","abstract_canon_sha256":"3a9d39534311fcbfd3d6b0b6c2e8057fd19e3dfb87e0b8a88b4b6fe7d332891d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:33.343141Z","signature_b64":"SOdVKhmExLUkuBv1kXL4yi/pRLi6LLDWhnCSFFzzxWzIF0uxi11iulsAovl6KGbYWregOSAwvTBsuEeiH09vDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5cec4c3063fd5d9edb5cb3db3a73fe73f1cbcd627b5674bacf4ed177bd85dfbd","last_reissued_at":"2026-05-20T00:03:33.342329Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:33.342329Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SemaVoice: Semantic-Aware Continuous Autoregressive Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"SemaVoice adds a foundation-model alignment step to continuous speech representations so autoregressive TTS can keep semantic meaning without losing acoustic quality.","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Haoning Xu, Hui Lu, Huimeng Wang, Jiajun Deng, Shiyin Kang, Shuhai Peng, Xueyuan Chen, Xunying Liu, Youjun Chen, Zhaoqing Li","submitted_at":"2026-05-16T12:37:06Z","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"},"claims":{"count":4,"items":[{"kind":"strongest_claim","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.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","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).","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","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.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"SemaVoice adds a foundation-model alignment step to continuous speech representations so autoregressive TTS can keep semantic meaning without losing acoustic quality.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"88a40c56d1a58a5e057ce7fe1927efded781077ffcc0a7504e0d766981bb5496"},"source":{"id":"2605.16964","kind":"arxiv","version":1},"verdict":{"id":"e388dd5e-62ed-4459-8fc7-8bc9aeb59b77","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T18:54:12.330602Z","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.","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","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).","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."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.16964/integrity.json","findings":[],"available":true,"detectors_run":[{"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","findings_count":0}],"snapshot_sha256":"d5f1f760704a15549281e8728d93c868ff763ba147e67732562869a7c34bf194"},"references":{"count":56,"sample":[{"doi":"","year":2023,"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","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"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","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens","work_id":"e5ad925a-4045-49b5-b301-208bcbf3eca8","ref_index":3,"cited_arxiv_id":"2407.05407","is_internal_anchor":true},{"doi":"","year":2025,"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","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens","work_id":"31f99dad-40ae-4a19-aeff-eafa54f5b42a","ref_index":5,"cited_arxiv_id":"2503.01710","is_internal_anchor":true}],"resolved_work":56,"snapshot_sha256":"320cc6efc6c804d015f8c87d45f5fca277c12d5bd9a3e36d3477f8d90c0f0ccd","internal_anchors":8},"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":"2605.16964","created_at":"2026-05-20T00:03:33.342457+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.16964v1","created_at":"2026-05-20T00:03:33.342457+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16964","created_at":"2026-05-20T00:03:33.342457+00:00"},{"alias_kind":"pith_short_12","alias_value":"LTWEYMDD7VOZ","created_at":"2026-05-20T00:03:33.342457+00:00"},{"alias_kind":"pith_short_16","alias_value":"LTWEYMDD7VOZ5W24","created_at":"2026-05-20T00:03:33.342457+00:00"},{"alias_kind":"pith_short_8","alias_value":"LTWEYMDD","created_at":"2026-05-20T00:03:33.342457+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LTWEYMDD7VOZ5W24WPNTU476OP","json":"https://pith.science/pith/LTWEYMDD7VOZ5W24WPNTU476OP.json","graph_json":"https://pith.science/api/pith-number/LTWEYMDD7VOZ5W24WPNTU476OP/graph.json","events_json":"https://pith.science/api/pith-number/LTWEYMDD7VOZ5W24WPNTU476OP/events.json","paper":"https://pith.science/paper/LTWEYMDD"},"agent_actions":{"view_html":"https://pith.science/pith/LTWEYMDD7VOZ5W24WPNTU476OP","download_json":"https://pith.science/pith/LTWEYMDD7VOZ5W24WPNTU476OP.json","view_paper":"https://pith.science/paper/LTWEYMDD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.16964&json=true","fetch_graph":"https://pith.science/api/pith-number/LTWEYMDD7VOZ5W24WPNTU476OP/graph.json","fetch_events":"https://pith.science/api/pith-number/LTWEYMDD7VOZ5W24WPNTU476OP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LTWEYMDD7VOZ5W24WPNTU476OP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LTWEYMDD7VOZ5W24WPNTU476OP/action/storage_attestation","attest_author":"https://pith.science/pith/LTWEYMDD7VOZ5W24WPNTU476OP/action/author_attestation","sign_citation":"https://pith.science/pith/LTWEYMDD7VOZ5W24WPNTU476OP/action/citation_signature","submit_replication":"https://pith.science/pith/LTWEYMDD7VOZ5W24WPNTU476OP/action/replication_record"}},"created_at":"2026-05-20T00:03:33.342457+00:00","updated_at":"2026-05-20T00:03:33.342457+00:00"}