Title | Neural Audio Fingerprint for High-Specific Audio Retrieval Based on Contrastive Learning |
Publication Type | Conference Paper |
Year of Publication | 2021 |
Authors | Chang, Sungkyun, Lee, Donmoon, Park, Jeongsoo, Lim, Hyungui, Lee, Kyogu, Ko, Karam, Han, Yoonchang |
Conference Name | ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) |
Keywords | Acoustic distortion, Acoustic Fingerprint, Acoustic Fingerprints, Acoustics, composability, Conferences, data augmentation, Fingerprint recognition, Human Behavior, information retrieval, music information retrieval, pubcrawl, Resiliency, search problems, self-supervised learning, Training |
Abstract | Most of existing audio fingerprinting systems have limitations to be used for high-specific audio retrieval at scale. In this work, we generate a low-dimensional representation from a short unit segment of audio, and couple this fingerprint with a fast maximum inner-product search. To this end, we present a contrastive learning framework that derives from the segment-level search objective. Each update in training uses a batch consisting of a set of pseudo labels, randomly selected original samples, and their augmented replicas. These replicas can simulate the degrading effects on original audio signals by applying small time offsets and various types of distortions, such as background noise and room/microphone impulse responses. In the segment-level search task, where the conventional audio fingerprinting systems used to fail, our system using 10x smaller storage has shown promising results. Our code and dataset are available at https://mimbres.github.io/neural-audio-fp/. |
DOI | 10.1109/ICASSP39728.2021.9414337 |
Citation Key | chang_neural_2021 |