Mar 2026· arXiv.org· Vol abs/2603.23947· 1 citation· 43 references
Computer Science
TL;DR
VLAFP is the first deep audio fingerprinting model capable of processing audio of variable length, for both training and testing, and outperforms existing state-of-the-arts in live audio identification and audio retrieval across three real-world datasets.
Abstract
Audio fingerprinting converts audio to much lower-dimensional representations, allowing distorted recordings to still be recognized as their originals through similar fingerprints. Existing deep learning approaches rigidly fingerprint fixed-length audio segments, thereby neglecting temporal dynamics during segmentation. To address limitations due to this rigidity, we propose Variable-Length Audio FingerPrinting (VLAFP), a novel method that supports variable-length fingerprinting. To the best of our knowledge, VLAFP is the first deep audio fingerprinting model capable of processing audio of variable length, for both training and testing. Our experiments show that VLAFP outperforms existing state-of-the-arts in live audio identification and audio retrieval across three real-world datasets.
Residual Vector Quantization (RVQ)-based neural audio codecs (NACs) enable high-fidelity audio distribution at unprecedentedly low bitrates through discrete token-based representations. However, this shift disrupts traditional forensics, as non-linear neural transcoding obscures the underlying traces of legacy compress...
A Generative Adversarial Network (GAN)-based framework is a well-known method for concealing textual information within digital audio signals via spectral-domain embedding. Conventional audio steganography techniques, such as Least Significant Bit (LSB) substitution, are low in robustness to signal processing operation...
Mohamed Mansur, Husayn Alhuwayji, Ahmed Almantsri et al.· Al-Farooq Journal of Science...· 0 citations
In this paper, we propose a few-shot authentication framework based on radio-frequency fingerprint identification (RFFI). Unlike conventional RFFI approaches, which often memorize device-specific features, our framework learns to accurately compare over-the-air (OTA) signals from different Internet of Things (IoT) devi...
Luis Lago Enamorado, Chuan Liu, Xu-Yu Wang· Proceedings of the 21st Work...· 0 citations
We present AudioNoisePrints, a training-free watermarking pipeline for flow matching and diffusion TTS models, which requires minimal extra computation during inference and does not require retraining the TTS model or reducing the generation quality. We exploited the fact that there are strong correlations between the...
Timothy Tin-Long, Jian Zhu, Aidan Pine et al.· 0 citations
A forensic-preserving neural audio codec (FP-NAC), which fine-tunes a pretrained codec using a detector-guided objective while preserving its native hard quantization path and bitrate, and highlights forensic transparency as a codec design objective alongside perceptual quality.
Jungwoo Kim, Joonyong Park, Junyoung Koh et al.· 0 citations
Modern text-to-speech (TTS) systems are rarely deployed as unchanged pre-trained models. They are often adapted through supervised fine-tuning (SFT) or preference optimization such as DPO and GRPO. This raises a practical question for audio deepfake forensics: do fingerprints learned from a foundation generator remain...
Machine-learning networks can learn without detailed instructions from a designer. Those that do may offer insight into how the brain reorganizes itself during learning.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
