pith. sign in

arxiv: 1812.08466 · v4 · pith:XMDYSOB4new · submitted 2018-12-20 · 📡 eess.AS · cs.SD

Fr\'echet Audio Distance: A Metric for Evaluating Music Enhancement Algorithms

classification 📡 eess.AS cs.SD
keywords distanceaudioechetenhancementmetricalgorithmscorrelationcosine
0
0 comments X
read the original abstract

We propose the Fr\'echet Audio Distance (FAD), a novel, reference-free evaluation metric for music enhancement algorithms. We demonstrate how typical evaluation metrics for speech enhancement and blind source separation can fail to accurately measure the perceived effect of a wide variety of distortions. As an alternative, we propose adapting the Fr\'echet Inception Distance (FID) metric used to evaluate generative image models to the audio domain. FAD is validated using a wide variety of artificial distortions and is compared to the signal based metrics signal to distortion ratio (SDR), cosine distance and magnitude L2 distance. We show that, with a correlation coefficient of 0.52, FAD correlates more closely with human perception than either SDR, cosine distance or magnitude L2 distance, with correlation coefficients of 0.39, -0.15 and -0.01 respectively.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 21 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. AudioCALM: Continuous Autoregressive Language Modeling for Universal Audio Generation

    eess.AS 2026-06 unverdicted novelty 7.0

    AudioCALM presents a continuous autoregressive framework with flow-matching prediction and A-MoME architecture that unifies speech, sound, and music generation while matching modality-specific state-of-the-art performance.

  2. Towards Unified Song Generation and Singing Voice Conversion with Accompaniment Co-Generation

    cs.SD 2026-06 unverdicted novelty 7.0

    UniSinger unifies speaker-cloned song generation and accompaniment co-generation SVC in one multimodal diffusion transformer model trained with curriculum learning via task-specific modality masking.

  3. Academic Text-to-Music Grand Challenge: Datasets, Baselines, and Evaluation Methods

    cs.SD 2026-05 unverdicted novelty 7.0

    Presents the ATTM grand challenge with efficiency and performance tracks for text-to-music generation using a public instrumental music dataset, evaluated via FAD, CLAP, a new CCS metric, and subjective tests.

  4. InstructAV2AV: Instruction-Guided Audio-Video Joint Editing

    cs.CV 2026-05 unverdicted novelty 7.0

    InstructAV2AV is an end-to-end instruction-guided audio-video joint editing model that adapts a pre-trained backbone with gated attention and two-stage training, outperforming prior methods on 11 metrics after buildin...

  5. Remix the Timbre: Diffusion-Based Style Transfer Across Polyphonic Stems

    cs.SD 2026-05 unverdicted novelty 7.0

    MixtureTT performs direct per-stem timbre transfer on polyphonic mixtures via a shared diffusion transformer, outperforming single-stem baselines on SATB choral data while eliminating cascaded separation errors.

  6. Latent Fourier Transform

    cs.SD 2026-04 unverdicted novelty 7.0

    LatentFT uses latent-space Fourier transforms and frequency masking in diffusion autoencoders to enable timescale-specific manipulation of musical structure in generative models.

  7. FoleyDesigner: Immersive Stereo Foley Generation with Precise Spatio-Temporal Alignment for Film Clips

    cs.CV 2026-04 unverdicted novelty 7.0

    FoleyDesigner generates spatio-temporally aligned stereo Foley audio for film clips via multi-agent analysis, diffusion models on video cues, and LLM mixing, supported by the new FilmStereo dataset.

  8. OmniSonic: Towards Universal and Holistic Audio Generation from Video and Text

    cs.SD 2026-04 unverdicted novelty 7.0

    OmniSonic introduces a TriAttn-DiT architecture with MoE gating to jointly generate on-screen, off-screen, and speech audio from video and text, outperforming prior models on a new UniHAGen-Bench.

  9. Amplifying Membership Signal Through Chained Regeneration

    cs.LG 2026-06 unverdicted novelty 6.0

    MADreMIA amplifies membership inference signals by showing that memorized samples maintain higher coherence and slower degradation in chained regeneration trajectories than non-members.

  10. What Do Deepfake Benchmarks Measure? An Audit Using Frozen Self-Supervised Representations

    cs.CV 2026-06 unverdicted novelty 6.0

    Linear probes on frozen self-supervised representations closely approach bespoke deepfake detector performance on benchmarks, indicating benchmarks largely measure general modality understanding.

  11. UniVocal: Unified Speech-Singing Code-Switching Synthesis

    cs.SD 2026-06 unverdicted novelty 6.0

    UniVocal presents a text-context-only framework for speech-singing code-switching synthesis via two-stage curriculum learning and a synthetic data pipeline, claiming SOTA on a new benchmark.

  12. Stage-adaptive audio diffusion modeling

    cs.SD 2026-05 unverdicted novelty 6.0

    A semantic progress signal from SSL discrepancy slope enables three stage-aware mechanisms that improve training efficiency and performance in audio diffusion models over static baselines.

  13. Meta Audiobox Aesthetics: Unified Automatic Quality Assessment for Speech, Music, and Sound

    cs.SD 2025-02 unverdicted novelty 6.0

    Unified no-reference models assess audio aesthetics across speech, music, and sound via four perceptual axes and achieve performance comparable or superior to human mean opinion scores.

  14. The Moving Drone: Negotiating Agency Between the Voice and the Virtual

    cs.SD 2026-06 unverdicted novelty 5.0

    Presents an artistic system that turns the static Hindustani tanpura drone into an evolving, co-creative virtual agent via real-time looping, pitch shifting, and low-fidelity generative AI.

  15. SketchSong: Hierarchical Song Generation with Sketch Planning and Fine-Grained Multi-Track Modeling

    cs.SD 2026-06 unverdicted novelty 5.0

    SketchSong uses temporal sketch planning with high-level tokens and explicit modeling of four tracks (vocals, bass, drums, other) to generate more coherent songs than baselines.

  16. Academic Text-to-Music Grand Challenge: Datasets, Baselines, and Evaluation Methods

    cs.SD 2026-05 accept novelty 5.0

    The paper introduces the ATTM Grand Challenge with a CC-licensed instrumental subset of MTG-Jamendo, two tracks, and evaluation via FAD, CLAP, and a new Concept Coverage Score to support academic text-to-music research.

  17. Fast Text-to-Audio Generation with One-Step Sampling via Energy-Scoring and Auxiliary Contextual Representation Distillation

    cs.SD 2026-05 unverdicted novelty 5.0

    A one-step text-to-audio model using energy-distance training and contextual distillation outperforms prior fast baselines on AudioCaps and achieves up to 8.5x faster inference than the multi-step IMPACT system with c...

  18. Movie Gen: A Cast of Media Foundation Models

    cs.CV 2024-10 unverdicted novelty 5.0

    A 30B-parameter transformer and related models generate high-quality videos and audio, claiming state-of-the-art results on text-to-video, video editing, personalization, and audio generation tasks.

  19. MAVIN: Multi-Shot Audio-Visual Generation with Narrative Control

    cs.CV 2026-06 unverdicted novelty 4.0

    MAVIN proposes boundary-aware attention, ID-aware propagation, a multi-agent scripting pipeline, and the MAVINSet dataset as the first framework for multi-shot audio-visual generation with narrative control, claiming ...

  20. STAR-VAE: Structured Topology-Aware Regularization for Audio Reconstruction and Generation

    eess.AS 2026-06 unverdicted novelty 4.0

    STAR-VAE introduces topology-aware regularization to reshape VAE latent geometry for audio, claiming to resolve the Rate-Distortion-Regularity Trilemma and achieve SOTA reconstruction.

  21. MMAudioSep: Taming Video-to-Audio Generative Model Towards Video/Text-Queried Sound Separation

    cs.SD 2025-10 unverdicted novelty 4.0

    MMAudioSep adapts a pretrained video-to-audio model via fine-tuning for video/text-queried sound separation, outperforming baselines while preserving generation ability.