# KAD: No More FAD! An Effective and Efficient Evaluation Metric for Audio Generation

arXiv: https://arxiv.org/abs/2502.15602 · HTML: https://mlsanity.com/paper/2502.15602/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 57 of its 82 references that are in the map.
- First posted on arXiv 21 Feb 2025.

## Builds on (most cited first, 30 of 57)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [Demystifying MMD GANs](https://mlsanity.com/paper/1801.01401/) (2018)
- [Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation](https://mlsanity.com/paper/2211.06687/) (2022)
- [CNN Architectures for Large-Scale Audio Classification](https://mlsanity.com/paper/1609.09430/) (2016)
- [High Fidelity Neural Audio Compression](https://mlsanity.com/paper/2210.13438/) (2022)
- [AudioLDM: Text-to-Audio Generation with Latent Diffusion Models](https://mlsanity.com/paper/2301.12503/) (2023)
- [PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition](https://mlsanity.com/paper/1912.10211/) (2019)
- [High-Fidelity Audio Compression with Improved RVQGAN](https://mlsanity.com/paper/2306.06546/) (2023)
- [Clotho: An Audio Captioning Dataset](https://mlsanity.com/paper/1910.09387/) (2019)
- [AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining](https://mlsanity.com/paper/2308.05734/) (2023)
- [Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Models](https://mlsanity.com/paper/2301.12661/) (2023)
- [Rethinking FID: Towards a Better Evaluation Metric for Image Generation](https://mlsanity.com/paper/2401.09603/) (2023)
- [AudioGen: Textually Guided Audio Generation](https://mlsanity.com/paper/2209.15352/) (2022)
- [Efficient Training of Audio Transformers with Patchout](https://mlsanity.com/paper/2110.05069/) (2021)
- [Adversarial Audio Synthesis](https://mlsanity.com/paper/1802.04208/) (2018)
- [Fr'echet Audio Distance: A Metric for Evaluating Music Enhancement Algorithms](https://mlsanity.com/paper/1812.08466/) (2018)
- [The Role of ImageNet Classes in Fr'echet Inception Distance](https://mlsanity.com/paper/2203.06026/) (2022)
- [Stable Audio Open](https://mlsanity.com/paper/2407.14358/) (2024)
- [MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training](https://mlsanity.com/paper/2306.00107/) (2023)
- [Effectively Unbiased FID and Inception Score and where to find them](https://mlsanity.com/paper/1911.07023/) (2019)
- [MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis](https://mlsanity.com/paper/2412.15322/) (2024)
- [Tango 2: Aligning Diffusion-based Text-to-Audio Generations through Direct Preference Optimization](https://mlsanity.com/paper/2404.09956/) (2024)
- [I Hear Your True Colors: Image Guided Audio Generation](https://mlsanity.com/paper/2211.03089/) (2022)
- [Adapting Frechet Audio Distance for Generative Music Evaluation](https://mlsanity.com/paper/2311.01616/) (2023)
- [V2A-Mapper: A Lightweight Solution for Vision-to-Audio Generation by Connecting Foundation Models](https://mlsanity.com/paper/2308.09300/) (2023)

## Built on by (most cited first, 24 of 24)

- [Aligning Text-to-Music Evaluation with Human Preferences](https://mlsanity.com/paper/2503.16669/) (2025)
- [Survey on the Evaluation of Generative Models in Music](https://mlsanity.com/paper/2506.05104/) (2025)
- [Massive Sound Embedding Benchmark (MSEB)](https://mlsanity.com/paper/2602.07143/) (2026)
- [MuQ-Eval: An Open-Source Per-Sample Quality Metric for AI Music Generation Evaluation](https://mlsanity.com/paper/2603.22677/) (2026)
- [SoundReactor: Frame-level Online Video-to-Audio Generation](https://mlsanity.com/paper/2510.02110/) (2025)
- [CMI-RewardBench: Evaluating Music Reward Models with Compositional Multimodal Instruction](https://mlsanity.com/paper/2603.00610/) (2026)
- [TuneJury: An Open Metric for Improving Music Generation Preference Alignment](https://mlsanity.com/paper/2606.17006/) (2026)
- [Hear What Matters! Text-conditioned Selective Video-to-Audio Generation](https://mlsanity.com/paper/2512.02650/) (2025)
- [Mitigating data replication in text-to-audio generative diffusion models through anti-memorization guidance](https://mlsanity.com/paper/2509.14934/) (2025)
- [Bias beyond Borders: Global Inequalities in AI-Generated Music](https://mlsanity.com/paper/2510.01963/) (2025)
- [GuitarFlow: Realistic Electric Guitar Synthesis From Tablatures via Flow Matching and Style Transfer](https://mlsanity.com/paper/2510.21872/) (2025)
- [Learning Linearity in Audio Consistency Autoencoders via Implicit Regularization](https://mlsanity.com/paper/2510.23530/) (2025)
- [Diff-TONE: Timestep Optimization for iNstrument Editing in Text-to-Music Diffusion Models](https://mlsanity.com/paper/2506.15530/) (2025)
- [S-PRESSO: Ultra Low Bitrate Sound Effect Compression With Diffusion Autoencoders And Offline Quantization](https://mlsanity.com/paper/2602.15082/) (2026)
- [SyncTrack: Rhythmic Stability and Synchronization in Multi-Track Music Generation](https://mlsanity.com/paper/2603.01101/) (2026)
- [PianoKontext: Expressive Performance Rendering from Deadpan Context](https://mlsanity.com/paper/2606.12282/) (2026)
- [Fr'echet Distance Loss on Speech Representations for Text-to-Speech Synthesis](https://mlsanity.com/paper/2607.06027/) (2026)
- [Integrating Contextual Embeddings into Evaluation of Expressive MIDI Piano Performances](https://mlsanity.com/paper/2607.27909/) (2026)
- [Music Restoration via Latent Operator Optimization and Diffusion Model Priors](https://mlsanity.com/paper/2608.01972/) (2026)
- [InvFlowFD: Reference-Free and Background-Set-Free Perceptual Music Quality Metric with Flow Matching Inversion](https://mlsanity.com/paper/2608.04142/) (2026)
- [Diff2Mix: Controllable Music Mixing via Diffusion Models and Differentiable Audio Effects](https://mlsanity.com/paper/2608.05442/) (2026)
- [SCAPES: Semantically Conditioned Autoregressive Prior for Environmental Sounds](https://mlsanity.com/paper/2609.04634/) (2026)
- [SsgCaps: A controlled dataset for the evaluation of sound scene generation algorithms](https://mlsanity.com/paper/2609.26854/) (2026)
- [Don't CLAP: Are Music-Text Models Bag-of-Words?](https://mlsanity.com/paper/2609.30540/) (2026)

## Abstract (arXiv)

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.