Pith Number

pith:S4Y3ZWUW

pith:2020:S4Y3ZWUWEX5I3563BY74JTVKPQ

not attested not anchored not stored refs resolved

DiffWave: A Versatile Diffusion Model for Audio Synthesis

Bryan Catanzaro, Jiaji Huang, Kexin Zhao, Wei Ping, Zhifeng Kong

A diffusion model converts white noise into high-quality audio waveforms through a fixed-step Markov chain, matching WaveNet vocoder quality while running orders of magnitude faster.

arxiv:2009.09761 v3 · 2020-09-21 · eess.AS · cs.CL · cs.LG · cs.SD · stat.ML

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{S4Y3ZWUWEX5I3563BY74JTVKPQ}

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

DiffWave matches a strong WaveNet vocoder in terms of speech quality (MOS: 4.44 versus 4.43), while synthesizing orders of magnitude faster. In particular, it significantly outperforms autoregressive and GAN-based waveform models in the challenging unconditional generation task in terms of audio quality and sample diversity from various automatic and human evaluations.

C2weakest assumption

That a neural network can accurately predict the noise to remove at each step of the reverse diffusion Markov chain so that the resulting waveform matches the statistical structure of real audio data across conditional and unconditional tasks.

C3one line summary

DiffWave is a non-autoregressive diffusion model that generates high-fidelity audio waveforms from noise in constant steps, matching WaveNet vocoder quality while being orders of magnitude faster and outperforming prior models in unconditional generation.

References

25 extracted · 25 resolved · 9 Pith anchors

[1] Large Scale GAN Training for High Fidelity Natural Image Synthesis · arXiv:1809.11096

[2] Weiss, Mohammad Norouzi, and William Chan 2009

[3] Persistent rnns: Stashing recurrent weights on-chip 2024

[4] End-to-end adversarial text-to-speech 2006

[5] Ddsp: Differentiable digital signal processing 2001

Formal links

2 machine-checked theorem links

Cited by

33 papers in Pith

Score-Based Generative Modeling through Stochastic Differential Equations

Mechanisms of Multimodal Synchronization: Insights from Decoder-Based Video-Text-to-Speech Synthesis

GCDance: Genre-Controlled Music-Driven 3D Full Body Dance Generation

MSDformer: Multi-scale Discrete Transformer For Time Series Generation

Flow Map Language Models: One-step Language Modeling via Continuous Denoising

Receipt and verification

First computed	2026-05-17T23:38:52.485912Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

9731bcda9625fa8df7db0e3fc4ceaa7c1567322b3a582da7a2505b30f4e028e9

Aliases

arxiv: 2009.09761 · arxiv_version: 2009.09761v3 · doi: 10.48550/arxiv.2009.09761 · pith_short_12: S4Y3ZWUWEX5I · pith_short_16: S4Y3ZWUWEX5I3563 · pith_short_8: S4Y3ZWUW

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/S4Y3ZWUWEX5I3563BY74JTVKPQ \
  | 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: 9731bcda9625fa8df7db0e3fc4ceaa7c1567322b3a582da7a2505b30f4e028e9

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "19873d12221f4a74bda25d7330b4259d32db0ca87acfa2ff2b93e55a6392a6f0",
    "cross_cats_sorted": [
      "cs.CL",
      "cs.LG",
      "cs.SD",
      "stat.ML"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "eess.AS",
    "submitted_at": "2020-09-21T11:20:38Z",
    "title_canon_sha256": "848a2e8d4a5ddbf0e6eaeb3880f031f2c0cfa2f0510837aca0ac098a54697ee9"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2009.09761",
    "kind": "arxiv",
    "version": 3
  }
}