Towards Evaluating Generative Audio: Insights From Neural Audio Codec Embedding Distances

Abstract

Neural audio codecs (NACs) achieve low-bitrate compression by learning compact audio representations, which can also serve as features for perceptual quality evaluation. We introduce DACe, an enhanced, higher-fidelity version of the Descript Audio Codec (DAC), trained on diverse real and synthetic tonal data with balanced sampling. We systematically compare Fr\'echet Audio Distance (FAD) and Maximum Mean Discrepancy (MMD) on MUSHRA tests across speech, music, and mixed content. FAD consistently outperforms MMD, and embeddings from higher-fidelity NACs (such as DACe) show stronger correlations with human judgments. While CLAP LAION Music (CLAP-M) and OpenL3 Mel128 (OpenL3-128M) embeddings achieve higher correlations, NAC embeddings provide a practical zero-shot approach to audio quality assessment, requiring only unencoded audio for training. These results demonstrate the dual utility of NACs for compression and perceptually informed audio evaluation.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keybiswas2025towards

Related papers

• KAD: No More FAD! An Effective And Efficient Evaluation Metric For Audio Generation (2025)0.00
• Modeling Strategies For Speech Enhancement In The Latent Space Of A Neural Audio Codec (2025)0.00
• Code Drift: Towards Idempotent Neural Audio Codecs (2024)2.26
• Complexdec: A Domain-robust High-fidelity Neural Audio Codec With Complex Spectrum Modeling (2025)3.58
• Mdctcodec: A Lightweight Mdct-based Neural Audio Codec Towards High Sampling Rate And Low Bitrate Scenarios (2024)8.09
• NOMAD: Unsupervised Learning Of Perceptual Embeddings For Speech Enhancement And Non-matching Reference Audio Quality Assessment (2023)7.50
• Neural Speech And Audio Coding: Modern AI Technology Meets Traditional Codecs (2024)7.16
• Analyzing And Mitigating Inconsistency In Discrete Audio Tokens For Neural Codec Language Models (2024)5.84