Pith Number

pith:LTWEYMDD

pith:2026:LTWEYMDD7VOZ5W24WPNTU476OP

not attested not anchored not stored refs resolved

SemaVoice: Semantic-Aware Continuous Autoregressive Speech Synthesis

Haoning Xu, Hui Lu, Huimeng Wang, Jiajun Deng, Shiyin Kang, Shuhai Peng, Xueyuan Chen, Xunying Liu, Youjun Chen, Zhaoqing Li

SemaVoice adds a foundation-model alignment step to continuous speech representations so autoregressive TTS can keep semantic meaning without losing acoustic quality.

arxiv:2605.16964 v1 · 2026-05-16 · eess.AS

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{LTWEYMDD7VOZ5W24WPNTU476OP}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest 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.

C2weakest 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).

C3one 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.

References

56 extracted · 56 resolved · 8 Pith anchors

[1] Audiolm: a language modeling approach to audio generation.IEEE/ACM transactions on audio, speech, and language processing, 31:2523–2533, 2023 2023

[2] Speak, read and prompt: High-fidelity text-to-speech with minimal supervision.Transactions of the Association for Computational Linguistics, 11, 2023 2023

[3] CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens 2024 · arXiv:2407.05407

[4] Neural codec language models are zero-shot text to speech synthesizers.IEEE Transactions on Audio, Speech and Language Processing, 33: 705–718, 2025 2025

[5] Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens 2025 · arXiv:2503.01710

Receipt and verification

First computed	2026-05-20T00:03:33.342329Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

5cec4c3063fd5d9edb5cb3db3a73fe73f1cbcd627b5674bacf4ed177bd85dfbd

Aliases

arxiv: 2605.16964 · arxiv_version: 2605.16964v1 · doi: 10.48550/arxiv.2605.16964 · pith_short_12: LTWEYMDD7VOZ · pith_short_16: LTWEYMDD7VOZ5W24 · pith_short_8: LTWEYMDD

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/LTWEYMDD7VOZ5W24WPNTU476OP \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 5cec4c3063fd5d9edb5cb3db3a73fe73f1cbcd627b5674bacf4ed177bd85dfbd

Canonical record JSON

{
  "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
  }
}