Variable-Length Audio Fingerprinting (VLAFP) is a new deep learning model that converts audio into low-dimensional fingerprints while allowing variable-length input, unlike existing methods that require fixed-length segments. By supporting variable-length audio during both training and testing, VLAFP captures temporal dynamics that were previously neglected. Experiments demonstrate that VLAFP outperforms current state‑of‑the‑art systems in live audio identification and audio retrieval across three real‑world datasets.
arXiv:2603. 23667v2 Announce Type: replace-cross Abstract: We introduce Echoes, a new dataset for music deepfake detection designed for training and benchmarking detectors under realistic and provider-diverse conditions.
arXiv:2606. 27320v1 Announce Type: cross Abstract: Neural audio autoencoders have become a core component of compression, feature extraction, and generation.
arXiv:2609.14820v1 Announce Type: cross Abstract: This work presents POLARIS, a training-free audio fingerprinting system that selects landmarks from a locally normalized saliency field and groups th...
arXiv:2607. 25543v1 Announce Type: cross Abstract: Generative AI has rapidly expanded audio-visual forgery beyond human-centric deepfakes into general scenes.
arXiv:2610.07338v1 Announce Type: cross Abstract: Audio benchmarks are built around short, pre-segmented clips, limiting model design to brief inputs or fixed vocabularies. To close this gap, we intr...
arXiv:2606. 17301v1 Announce Type: cross Abstract: Search, a foundational operation in computer science, maps a query to a matching item in a collection.
arXiv:2510. 02916v2 Announce Type: replace-cross Abstract: We propose SALSA-V, a multimodal video-to-audio generation model capable of synthesizing highly synchronized, high-fidelity long-form audio from silent video content.
arXiv:2512. 15313v2 Announce Type: replace-cross Abstract: Deep learning has become a standard approach for the modeling of audio effects, yet strictly black-box modeling remains problematic for time-varying systems.
AudioFuse is a hybrid architecture that jointly learns from spectrograms and raw waveforms to classify phonocardiograms. It combines a wide-and-shallow Vision Transformer for spectral features with a shallow 1D CNN for temporal waveforms, reducing overfitting while capturing complementary information. On the PhysioNet 2016 dataset, AudioFuse achieves a state‑of‑the‑art ROC‑AUC of 0.8608 and shows superior robustness to domain shift on the PASCAL dataset, outperforming both spectrogram‑only and waveform‑only baselines.
arXiv:2608. 14916v1 Announce Type: cross Abstract: AI-generated music detectors are commonly evaluated against original songs, but real-world uploads are often remixed, re-encoded, pitch-shifted, or otherwise edited.
arXiv:2607. 04848v1 Announce Type: cross Abstract: While audio deepfake detection has advanced significantly, representative detectors show limited generalization to synthetic sound effects.
arXiv:2503. 17577v2 Announce Type: replace-cross Abstract: Deepfakes have emerged as a widespread and rapidly escalating concern in generative AI, spanning images, audio, and videos.