Evaluates the ability of audio generative models to reconstruct raw musical note waveforms and interpolate timbre and pitch in a learned latent space. Probes phase preservation, harmonic structure modeling, and the decoupling of pitch and timbre information. Use when the user wants to benchmark on NSynth, or asks about evaluating this task. Reports Classification accuracy.
Installs into .claude/skills of the current project.
Are you the author of Nsynth Reconstruction Eval?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/qhjqhj00-nsynth-reconstruction-eval)
---
name: nsynth-reconstruction-eval
description: Evaluates the ability of audio generative models to reconstruct raw musical note waveforms and interpolate timbre and pitch in a learned latent space. Probes phase preservation, harmonic structure modeling, and the decoupling of pitch and timbre information. Use when the user wants to benchmark on NSynth, or asks about evaluating this task. Reports Classification accuracy.
metadata:
skill_kind: dataset_eval
source_arxiv: 1704.01279
bibtex_key: engel2017neural
confidence: high
---
# nsynth-reconstruction-eval
> Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders — Engel et al. (2017) (arXiv:1704.01279, 2017)
## What this evaluates
Evaluates the ability of audio generative models to reconstruct raw musical note waveforms and interpolate timbre and pitch in a learned latent space. Probes phase preservation, harmonic structure modeling, and the decoupling of pitch and timbre information.
## Datasets
- **NSynth** — total 300000; splits: test (-1)
## Metrics
- `Classification accuracy` **(primary)** — range: percent
- Percentage of correctly predicted pitch or quality labels by a trained classifier on model outputs or latent embeddings.
## Input / output format
**Input**: Raw audio waveforms of musical notes (mu-law encoded), latent embeddings (Z), and pitch conditioning variables.
**Output**: Reconstructed audio waveforms, interpolated audio samples, and latent embeddings.
## Scoring recipe
```python
clf = train_classifier(labels=["pitch", "quality"], data=reconstructions)
preds = clf.predict(held_out_reconstructions[:4096])
accuracy = (preds == gold_labels).mean() * 100
```
## Common pitfalls
- Audio quality heavily depends on phase information, which standard magnitude spectrograms fail to capture, leading to misleading visual evaluations.
- The quantitative classifier is evaluated on a fixed subset of 4096 examples, which may not represent the full distribution of the ~300k dataset.
- Mu-law encoding introduces built-in distortion that affects lower frequencies more severely, confounding pure reconstruction quality metrics.
## Evidence (verbatim from paper)
> Table 1: Classification accuracy of a deep nonlinear pitch and quality classifier on reconstructions of a test set.
## Citation
```bibtex
@misc{engel2017neural,
title={Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders},
author={Engel et al. (2017)},
year={2017},
note={arXiv:1704.01279}
}
```
- arXiv: 1704.01279
