aiqbench analysis
This research introduces VLAFP, the first deep learning model capable of processing audio signals of variable length while preserving temporal dynamics during segmentation. By overcoming the rigid fixed-length constraints of existing methods, it significantly improves performance in live audio identification and retrieval across distorted recordings. The advancement represents a notable step forward in robust acoustic signal processing within the broader field of machine learning.
Variable-Length Audio Fingerprinting
arXiv:2603.23947v2 Announce Type: replace-cross 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.
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.
Sound (cs.SD); Artificial Intelligence (cs.AI); Multimedia (cs.MM)
arXiv:2603.23947 [cs.SD]
(or arXiv:2603.23947v2 [cs.SD] for this version)
https://doi.org/10.48550/arXiv.2603.23947 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 197 words
Related coverage
PairAlign: A Framework for Sequence Tokenization via Self-Alignment with Applications to Audio Tokenization
arXiv · Jun 9, 2026
Can Voice Agents Handle Bilingual Customers? Benchmarking Frontier ASR on Code-Switched Speech
Hugging Face · Jun 9, 2026
PairAlign: A Framework for Autoregressive Tokenization via Self-Alignment with Applications to Audio Tokenization
arXiv · Sep 1, 2026
Seedance 2.5 Review: What It's Best At and When to Use It
OpenRouter · Sep 9, 2026