Perceiving Music Quality with GANs

• URL: http://arxiv.org/abs/2006.06287v2
• Date: Sun, 4 Apr 2021 14:01:17 GMT
• Title: Perceiving Music Quality with GANs
• Abstract summary: We propose training a GAN on a large music library, and using its discriminator as a no-reference quality assessment measure of the perceived quality of music. In a listening test with 448 human subjects, where participants rated professionally produced music tracks degraded with different levels and types of signal degradations, we establish a dataset of human rated material. By using the human rated dataset we show that the discriminator score correlates significantly with the subjective ratings, suggesting that the proposed method can be used to create a no-reference musical audio quality assessment measure.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Several methods have been developed to assess the perceptual quality of audio under transforms like lossy compression. However, they require paired reference signals of the unaltered content, limiting their use in applications where references are unavailable. This has hindered progress in audio generation and style transfer, where a no-reference quality assessment method would allow more reproducible comparisons across methods. We propose training a GAN on a large music library, and using its discriminator as a no-reference quality assessment measure of the perceived quality of music. This method is unsupervised, needs no access to degraded material and can be tuned for various domains of music. In a listening test with 448 human subjects, where participants rated professionally produced music tracks degraded with different levels and types of signal degradations such as waveshaping distortion and low-pass filtering, we establish a dataset of human rated material. By using the human rated dataset we show that the discriminator score correlates significantly with the subjective ratings, suggesting that the proposed method can be used to create a no-reference musical audio quality assessment measure.

Related papers

• VA-Judger: Reward Modeling from Human Preference Feedback for Joint Video-Audio Generation [79.34043102155964]
  We propose VA-Judger, a chain-of-thought omni-reward model for joint video-audio generation.<n>We show VA-Judger outperforms metric baselines in predicting human preferences on both in-domain and out-of-domain evaluations.
  arXiv  Detail & Related papers  (2026-08-19T06:53:14Z)
• InvFlowFD: Reference-Free and Background-Set-Free Perceptual Music Quality Metric with Flow Matching Inversion [28.58617981784364]
  We propose a novel approach that eliminates background-set-free and reference-free quality estimation using only a pre-trained Flow Matching backbone.<n>We demonstrate that unconditional Flow Matching inversion is sufficient to detect various artificial distortions and accurately rank music generation models against human perceptual judgments.<n>Results suggest that InvFlowFD is highly correlated with human perception of sound distortions, as well as generative models' quality, while being more flexible and less restrictive than existing metrics.
  arXiv  Detail & Related papers  (2026-08-04T18:50:14Z)
• When Noise Lowers The Loss: Rethinking Likelihood-Based Evaluation in Music Large Language Models [4.959996513415697]
  Music large language models (LLMs) need robust methods of evaluating output quality.<n>We show that models encounter systematically corrupted music, undermining its validity as a standalone quality indicator.<n>Our results highlight a new principle: the shape of the loss curve -- rather than its absolute value -- encodes critical information about the quality of the generated content.
  arXiv  Detail & Related papers  (2026-02-02T19:53:12Z)
• SAM Audio Judge: A Unified Multimodal Framework for Perceptual Evaluation of Audio Separation [52.468945848774844]
  This paper addresses the need for automated systems capable of evaluating audio separation without human intervention.<n>The proposed evaluation metric, SAM Audio Judge (SAJ), is a multimodal fine-grained reference-free objective metric.<n>SAJ supports three audio domains (speech, music and general sound events) and three prompt inputs (text, visual and span), covering four different dimensions of evaluation.
  arXiv  Detail & Related papers  (2026-01-27T15:29:02Z)
• Discriminating real and synthetic super-resolved audio samples using embedding-based classifiers [9.870143085379146]
  Generative adversarial networks (GANs) and diffusion models have recently achieved state-of-the-art performance in audio super-resolution.<n>Here we analyze the separability of real and super-resolved audio in various embedding spaces.
  arXiv  Detail & Related papers  (2026-01-06T22:10:45Z)
• BGM2Pose: Active 3D Human Pose Estimation with Non-Stationary Sounds [16.0759003139539]
  BGM2Pose is a non-invasive 3D human pose estimation method using arbitrary music (e.g., background music) as active sensing signals. Our method utilizes natural music that causes minimal discomfort to humans.
  arXiv  Detail & Related papers  (2025-03-01T07:32:19Z)
• Meta Audiobox Aesthetics: Unified Automatic Quality Assessment for Speech, Music, and Sound [46.7144966835279]
  This paper addresses the need for automated systems capable of predicting audio aesthetics without human intervention. We propose new annotation guidelines that decompose human listening perspectives into four distinct axes. We develop and train no-reference, per-item prediction models that offer a more nuanced assessment of audio quality.
  arXiv  Detail & Related papers  (2025-02-07T18:15:57Z)
• Evaluation of pretrained language models on music understanding [0.0]
  We demonstrate that Large Language Models (LLM) suffer from 1) prompt sensitivity, 2) inability to model negation, and 3) sensitivity towards the presence of specific words. We quantified these properties as a triplet-based accuracy, evaluating the ability to model the relative similarity of labels in a hierarchical ontology. Despite the relatively high accuracy reported, inconsistencies are evident in all six models, suggesting that off-the-shelf LLMs need adaptation to music before use.
  arXiv  Detail & Related papers  (2024-09-17T14:44:49Z)
• Generating High-quality Symbolic Music Using Fine-grained Discriminators [42.200747558496055]
  We propose to decouple the melody and rhythm from music, and design corresponding fine-grained discriminators to tackle the issues. Specifically, equipped with a pitch augmentation strategy, the melody discriminator discerns the melody variations presented by the generated samples. The rhythm discriminator, enhanced with bar-level relative positional encoding, focuses on the velocity of generated notes.
  arXiv  Detail & Related papers  (2024-08-03T07:32:21Z)
• A No-Reference Quality Assessment Method for Digital Human Head [56.17852258306602]
  We develop a novel no-reference (NR) method based on Transformer to deal with digital human quality assessment (DHQA) Specifically, the front 2D projections of the digital humans are rendered as inputs and the vision transformer (ViT) is employed for the feature extraction. Then we design a multi-task module to jointly classify the distortion types and predict the perceptual quality levels of digital humans.
  arXiv  Detail & Related papers  (2023-10-25T16:01:05Z)
• MARBLE: Music Audio Representation Benchmark for Universal Evaluation [79.25065218663458]
  We introduce the Music Audio Representation Benchmark for universaL Evaluation, termed MARBLE. It aims to provide a benchmark for various Music Information Retrieval (MIR) tasks by defining a comprehensive taxonomy with four hierarchy levels, including acoustic, performance, score, and high-level description. We then establish a unified protocol based on 14 tasks on 8 public-available datasets, providing a fair and standard assessment of representations of all open-sourced pre-trained models developed on music recordings as baselines.
  arXiv  Detail & Related papers  (2023-06-18T12:56:46Z)
• AudioGen: Textually Guided Audio Generation [116.57006301417306]
  We tackle the problem of generating audio samples conditioned on descriptive text captions. In this work, we propose AaudioGen, an auto-regressive model that generates audio samples conditioned on text inputs.
  arXiv  Detail & Related papers  (2022-09-30T10:17:05Z)
• A Perceptual Measure for Evaluating the Resynthesis of Automatic Music Transcriptions [10.957528713294874]
  This study focuses on the perception of music performances when contextual factors, such as room acoustics and instrument, change. We propose to distinguish the concept of "performance" from the one of "interpretation", which expresses the "artistic intention"
  arXiv  Detail & Related papers  (2022-02-24T18:09:22Z)
• Audio Defect Detection in Music with Deep Networks [8.680081568962997]
  Deliberate use of artefacts such as clicks in popular music calls for data-centric and context sensitive solutions for detection. We present a convolutional network architecture following end-to-end encoder decoder configuration to develop detectors for two exemplary audio defects.
  arXiv  Detail & Related papers  (2022-02-11T15:56:14Z)
• Evaluating Deep Music Generation Methods Using Data Augmentation [13.72212417973239]
  We focus on a homogeneous, objective framework for evaluating samples of algorithmically generated music. We do not seek to assess the musical merit of generated music, but instead explore whether generated samples contain meaningful information pertaining to emotion or mood/theme.
  arXiv  Detail & Related papers  (2021-12-31T20:35:46Z)
• Robust Audio-Visual Instance Discrimination [79.74625434659443]
  We present a self-supervised learning method to learn audio and video representations. We address the problems of audio-visual instance discrimination and improve transfer learning performance.
  arXiv  Detail & Related papers  (2021-03-29T19:52:29Z)
• Hierarchical Timbre-Painting and Articulation Generation [92.59388372914265]
  We present a fast and high-fidelity method for music generation, based on specified f0 and loudness. The synthesized audio mimics the timbre and articulation of a target instrument.
  arXiv  Detail & Related papers  (2020-08-30T05:27:39Z)
• Audio Impairment Recognition Using a Correlation-Based Feature Representation [85.08880949780894]
  We propose a new representation of hand-crafted features that is based on the correlation of feature pairs. We show superior performance in terms of compact feature dimensionality and improved computational speed in the test stage.
  arXiv  Detail & Related papers  (2020-03-22T13:34:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.