Echoes: A semantically-aligned music deepfake detection dataset

• URL: http://arxiv.org/abs/2603.23667v1
• Date: Tue, 24 Mar 2026 19:10:42 GMT
• Title: Echoes: A semantically-aligned music deepfake detection dataset
• Abstract summary: Echoes is a new dataset for music deepfake detection designed for training and benchmarking detectors.<n>It comprises 3,577 tracks (110 hours of audio) spanning multiple genres (pop, rock, electronic), and includes content generated by ten popular AI music generation systems.<n>We evaluate Echoes in a cross-dataset setting against three existing AI-generated music datasets using state-of-the-art Wav2Vec2 XLS-R 2B representations.
• Score: 10.959260825335354
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We introduce Echoes, a new dataset for music deepfake detection designed for training and benchmarking detectors under realistic and provider-diverse conditions. Echoes comprises 3,577 tracks (110 hours of audio) spanning multiple genres (pop, rock, electronic), and includes content generated by ten popular AI music generation systems. To prevent shortcut learning and promote robust generalization, the dataset is deliberately constructed to be challenging, enforcing semantic-level alignment between spoofed audio and bona fide references. This alignment is achieved by conditioning generated audio samples directly on bona-fide waveforms or song descriptors. We evaluate Echoes in a cross-dataset setting against three existing AI-generated music datasets using state-of-the-art Wav2Vec2 XLS-R 2B representations. Results show that (i) Echoes is the hardest in-domain dataset; (ii) detectors trained on existing datasets transfer poorly to Echoes; (iii) training on Echoes yields the strongest generalization performance. These findings suggest that provider diversity and semantic alignment help learn more transferable detection cues.

Related papers

• FIGMA: Towards FIne-Grained Music retrievAl [65.98380295254817]
  Retrieving music using natural language descriptions has improved with contrastive audio-text models such as CLAP, but current systems remain limited to coarse semantic queries.<n>We show that this limitation stems from the contrastive learning objective itself: despite being trained on long captions, CLAP-based models effectively utilize only the first few tokens.<n>We propose FIGMA, a multi-view contrastive architecture that addresses this limitation by jointly optimizing global audio-text alignment and frame-level, token-wise alignment.
  arXiv  Detail & Related papers  (2026-06-04T18:05:39Z)
• Detecting Musical Deepfakes [0.0]
  This study investigates the detection of AI-generated songs using the FakeMusicCaps dataset.<n>To simulate real-world adversarial conditions, tempo stretching and pitch shifting were applied to the dataset.<n>Mel spectrograms were generated from the modified audio, then used to train and evaluate a convolutional neural network.
  arXiv  Detail & Related papers  (2025-05-03T21:45:13Z)
• Hidden Echoes Survive Training in Audio To Audio Generative Instrument Models [0.5999777817331315]
  We show that if imperceptible echoes are hidden in the training data, a wide variety of audio to audio architectures reproduce these echoes in their outputs.<n>We conclude by showing that echoes make their way into fine tuned models, that they survive mixing/demixing, and that they survive pitch shift augmentation during training.
  arXiv  Detail & Related papers  (2024-12-14T02:36:45Z)
• Real Acoustic Fields: An Audio-Visual Room Acoustics Dataset and Benchmark [65.79402756995084]
  Real Acoustic Fields (RAF) is a new dataset that captures real acoustic room data from multiple modalities. RAF is the first dataset to provide densely captured room acoustic data.
  arXiv  Detail & Related papers  (2024-03-27T17:59:56Z)
• EchoTrack: Auditory Referring Multi-Object Tracking for Autonomous Driving [64.58258341591929]
  Auditory Referring Multi-Object Tracking (AR-MOT) is a challenging problem in autonomous driving. We put forward EchoTrack, an end-to-end AR-MOT framework with dual-stream vision transformers. We establish the first set of large-scale AR-MOT benchmarks.
  arXiv  Detail & Related papers  (2024-02-28T12:50:16Z)
• Perceptual Musical Features for Interpretable Audio Tagging [2.1730712607705485]
  This study explores the relevance of interpretability in the context of automatic music tagging. We constructed a workflow that incorporates three different information extraction techniques. We conducted experiments on two datasets, namely the MTG-Jamendo dataset and the GTZAN dataset.
  arXiv  Detail & Related papers  (2023-12-18T14:31:58Z)
• Self-Supervised Contrastive Learning for Robust Audio-Sheet Music Retrieval Systems [3.997809845676912]
  We show that self-supervised contrastive learning can mitigate the scarcity of annotated data from real music content. We employ the snippet embeddings in the higher-level task of cross-modal piece identification. In this work, we observe that the retrieval quality improves from 30% up to 100% when real music data is present.
  arXiv  Detail & Related papers  (2023-09-21T14:54:48Z)
• Self-Supervised Visual Acoustic Matching [63.492168778869726]
  Acoustic matching aims to re-synthesize an audio clip to sound as if it were recorded in a target acoustic environment. We propose a self-supervised approach to visual acoustic matching where training samples include only the target scene image and audio. Our approach jointly learns to disentangle room acoustics and re-synthesize audio into the target environment, via a conditional GAN framework and a novel metric.
  arXiv  Detail & Related papers  (2023-07-27T17:59:59Z)
• 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)
• BYOL-S: Learning Self-supervised Speech Representations by Bootstrapping [19.071463356974387]
  This work extends existing methods based on self-supervised learning by bootstrapping, proposes various encoder architectures, and explores the effects of using different pre-training datasets. We present a novel training framework to come up with a hybrid audio representation, which combines handcrafted and data-driven learned audio features. All the proposed representations were evaluated within the HEAR NeurIPS 2021 challenge for auditory scene classification and timestamp detection tasks.
  arXiv  Detail & Related papers  (2022-06-24T02:26:40Z)
• Semantic Object Prediction and Spatial Sound Super-Resolution with Binaural Sounds [106.87299276189458]
  Humans can robustly recognize and localize objects by integrating visual and auditory cues. This work develops an approach for dense semantic labelling of sound-making objects, purely based on sounds.
  arXiv  Detail & Related papers  (2020-03-09T15:49:01Z)

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.