REVIEW 5 cited by
KAD: No More FAD! An Effective and Efficient Evaluation Metric for Audio Generation
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
KAD: No More FAD! An Effective and Efficient Evaluation Metric for Audio Generation
read the original abstract
Although being widely adopted for evaluating generated audio signals, the Fr\'echet Audio Distance (FAD) suffers from significant limitations, including reliance on Gaussian assumptions, sensitivity to sample size, and high computational complexity. As an alternative, we introduce the Kernel Audio Distance (KAD), a novel, distribution-free, unbiased, and computationally efficient metric based on Maximum Mean Discrepancy (MMD). Through analysis and empirical validation, we demonstrate KAD's advantages: (1) faster convergence with smaller sample sizes, enabling reliable evaluation with limited data; (2) lower computational cost, with scalable GPU acceleration; and (3) stronger alignment with human perceptual judgments. By leveraging advanced embeddings and characteristic kernels, KAD captures nuanced differences between real and generated audio. Open-sourced in the kadtk toolkit, KAD provides an efficient, reliable, and perceptually aligned benchmark for evaluating generative audio models.
Forward citations
Cited by 5 Pith papers
-
Polyphonia: Zero-Shot Timbre Transfer in Polyphonic Music with Acoustic-Informed Attention Calibration
Polyphonia improves zero-shot stem-specific timbre transfer in polyphonic music by 15.5% target alignment via acoustic-informed attention calibration that uses probabilistic priors to set coarse boundaries.
-
Fr\'echet Distance Loss on Speech Representations for Text-to-Speech Synthesis
A Fréchet-distance training loss on frozen Whisper and CTC features reduces 4-step TTS word error rate below the 10-step baseline on Seed-TTS English, with no inference-time cost.
-
PianoKontext: Expressive Performance Rendering from Deadpan Context
PianoKontext renders expressive piano performances from deadpan scores using flow matching in Music2Latent latent space with DTW alignment for paired training data.
-
Optimal Transport Audio Distance with Learned Riemannian Ground Metrics
OTAD replaces FAD's frozen embedding cost and Gaussian coupling with a learned Riemannian adapter and Sinkhorn OT, reporting higher MOS Spearman correlation on DCASE 2023 and per-sample diagnostics with AUROC at least 0.86.
-
Sensitivity Analysis of Generative Spatial Audio Metrics: A Study on Responsiveness, Smoothness, and Symmetry
The paper defines three desiderata (responsiveness, smoothness, symmetry) and empirically compares FAD, intensity vectors, and acoustic maps on controlled FOA scenes of increasing complexity.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.