Variable-Length Audio Fingerprinting

2026-03-25

AI Summary

Existing deep audio fingerprinting methods rely on fixed-length inputs, which struggle to capture temporal dynamics and thus limit robustness in real-world scenarios. This work proposes the first end-to-end trainable variable-length audio fingerprinting model that unifies training and inference for audio segments of arbitrary duration through deep variable-length encoding, temporal feature aggregation, and similarity matching. By eliminating the conventional constraint of fixed segmentation, the proposed approach substantially enhances adaptability to temporal variations. It consistently outperforms state-of-the-art methods across three real-world datasets on both live audio identification and audio retrieval tasks.

Technology Category

• Machine Learning: Life-Long and Continual Learning
• Computer Vision: Segmentation
• Search and Optimization: Learning to Search

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

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.

Problem

• Audio fingerprinting
• Variable-length audio
• Temporal dynamics
• Fixed-length segmentation
• Deep learning

Innovation

• variable-length audio fingerprinting
• deep audio fingerprinting
• temporal dynamics
• audio retrieval
• live audio identification