Pith Number

pith:ZZJCXPKS

pith:2025:ZZJCXPKS6SRF5QOFNHOAVAYUL4

not attested not anchored not stored refs resolved

Aliasing-Free Neural Audio Synthesis

Chaoren Wang, Jerry Li, Junan Zhang, Lauri Juvela, Yicheng Gu, Zhizheng Wu

Differentiable anti-aliasing modules in neural vocoders and codecs remove artifacts to boost music and singing synthesis.

arxiv:2512.20211 v2 · 2025-12-23 · cs.SD · eess.AS · eess.SP

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{ZZJCXPKS6SRF5QOFNHOAVAYUL4}

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

Pupu-Vocoder and Pupu-Codec outperform existing systems on singing voice, music, and audio, while achieving comparable performance on speech.

C2weakest assumption

That the differentiable anti-aliasing modules can be inserted into standard neural vocoder and codec architectures without introducing new training instabilities or quality trade-offs that would negate the reported gains.

C3one line summary

Pupu-Vocoder and Pupu-Codec integrate differentiable anti-aliasing into neural audio models to eliminate aliasing artifacts from non-linear activations and upsampling, yielding better results on music and singing voice.

References

102 extracted · 102 resolved · 2 Pith anchors

[1] MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformer, 2025

[2] Vevo: Controllable Zero-Shot V oice Imitation with Self-Supervised Disentanglement, 2025

[3] Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers 2023 · arXiv:2301.02111

[4] Efficient Neural Audio Synthe- sis, 2018

[5] LPCNet: Improving Neural Speech Synthesis through Linear Prediction, 2019

Receipt and verification

First computed	2026-05-18T02:44:32.064541Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

ce522bbd52f4a25ec1c569dc0a83145f02e85bc2a0252fe4fd5ea87b3f0b6364

Aliases

arxiv: 2512.20211 · arxiv_version: 2512.20211v2 · doi: 10.48550/arxiv.2512.20211 · pith_short_12: ZZJCXPKS6SRF · pith_short_16: ZZJCXPKS6SRF5QOF · pith_short_8: ZZJCXPKS

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/ZZJCXPKS6SRF5QOFNHOAVAYUL4 \
  | 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: ce522bbd52f4a25ec1c569dc0a83145f02e85bc2a0252fe4fd5ea87b3f0b6364

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "20c6bd67582d7d70363a5c554ca22afada52ad9e3adfe665876b4b939c453cba",
    "cross_cats_sorted": [
      "eess.AS",
      "eess.SP"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.SD",
    "submitted_at": "2025-12-23T10:04:48Z",
    "title_canon_sha256": "0f999c6eb495e20a94d0602f00d4c7d49a6e85ed152af098e9b1ca0a01956006"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2512.20211",
    "kind": "arxiv",
    "version": 2
  }
}