Paper ID | MLSP-11.1 | ||
Paper Title | NEURAL AUDIO FINGERPRINT FOR HIGH-SPECIFIC AUDIO RETRIEVAL BASED ON CONTRASTIVE LEARNING | ||
Authors | Sungkyun Chang, Cochlear.ai, South Korea; Donmoon Lee, Cochlear.ai, Seoul National University, South Korea; Jeongsoo Park, Hyungui Lim, Cochlear.ai, South Korea; Kyogu Lee, Seoul National University, South Korea; Karam Ko, SK Telecom, South Korea; Yoonchang Han, Cochlear.ai, South Korea | ||
Session | MLSP-11: Self-supervised Learning for Speech Processing | ||
Location | Gather.Town | ||
Session Time: | Tuesday, 08 June, 16:30 - 17:15 | ||
Presentation Time: | Tuesday, 08 June, 16:30 - 17:15 | ||
Presentation | Poster | ||
Topic | Machine Learning for Signal Processing: [MLR-SSUP] Self-supervised and semi-supervised learning | ||
IEEE Xplore Open Preview | Click here to view in IEEE Xplore | ||
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/. |