Scalable Evaluation for Audio Identification via Synthetic Latent Fingerprint Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bhattacharjee, Aditya, Pasini, Marco, Benetos, Emmanouil
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915508443414528
author Bhattacharjee, Aditya
Pasini, Marco
Benetos, Emmanouil
author_facet Bhattacharjee, Aditya
Pasini, Marco
Benetos, Emmanouil
contents The evaluation of audio fingerprinting at a realistic scale is limited by the scarcity of large public music databases. We present an audio-free approach that synthesises latent fingerprints which approximate the distribution of real fingerprints. Our method trains a Rectified Flow model on embeddings extracted by pre-trained neural audio fingerprinting systems. The synthetic fingerprints generated using our system act as realistic distractors and enable the simulation of retrieval performance at a large scale without requiring additional audio. We assess the fidelity of synthetic fingerprints by comparing the distributions to real data. We further benchmark the retrieval performances across multiple state-of-the-art audio fingerprinting frameworks by augmenting real reference databases with synthetic distractors, and show that the scaling trends obtained with synthetic distractors closely track those obtained with real distractors. Finally, we scale the synthetic distractor database to model retrieval performance for very large databases, providing a practical metric of system scalability that does not depend on access to audio corpora.
format Preprint
id arxiv_https___arxiv_org_abs_2509_18620
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Scalable Evaluation for Audio Identification via Synthetic Latent Fingerprint Generation
Bhattacharjee, Aditya
Pasini, Marco
Benetos, Emmanouil
Sound
Information Retrieval
Audio and Speech Processing
H.5.5; I.2.6
The evaluation of audio fingerprinting at a realistic scale is limited by the scarcity of large public music databases. We present an audio-free approach that synthesises latent fingerprints which approximate the distribution of real fingerprints. Our method trains a Rectified Flow model on embeddings extracted by pre-trained neural audio fingerprinting systems. The synthetic fingerprints generated using our system act as realistic distractors and enable the simulation of retrieval performance at a large scale without requiring additional audio. We assess the fidelity of synthetic fingerprints by comparing the distributions to real data. We further benchmark the retrieval performances across multiple state-of-the-art audio fingerprinting frameworks by augmenting real reference databases with synthetic distractors, and show that the scaling trends obtained with synthetic distractors closely track those obtained with real distractors. Finally, we scale the synthetic distractor database to model retrieval performance for very large databases, providing a practical metric of system scalability that does not depend on access to audio corpora.
title Scalable Evaluation for Audio Identification via Synthetic Latent Fingerprint Generation
topic Sound
Information Retrieval
Audio and Speech Processing
H.5.5; I.2.6
url https://arxiv.org/abs/2509.18620