Pre-training Autoencoder for Acoustic Event Classification via Blinky

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Xiaoyang, Kinoshita, Yuma
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915502408859648
author Liu, Xiaoyang
Kinoshita, Yuma
author_facet Liu, Xiaoyang
Kinoshita, Yuma
contents In the acoustic event classification (AEC) framework that employs Blinkies, audio signals are converted into LED light emissions and subsequently captured by a single video camera. However, the 30 fps optical transmission channel conveys only about 0.2% of the normal audio bandwidth and is highly susceptible to noise. We propose a novel sound-to-light conversion method that leverages the encoder of a pre-trained autoencoder (AE) to distill compact, discriminative features from the recorded audio. To pre-train the AE, we adopt a noise-robust learning strategy in which artificial noise is injected into the encoder's latent representations during training, thereby enhancing the model's robustness against channel noise. The encoder architecture is specifically designed for the memory footprint of contemporary edge devices such as the Raspberry Pi 4. In a simulation experiment on the ESC-50 dataset under a stringent 15 Hz bandwidth constraint, the proposed method achieved higher macro-F1 scores than conventional sound-to-light conversion approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2509_15261
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Pre-training Autoencoder for Acoustic Event Classification via Blinky
Liu, Xiaoyang
Kinoshita, Yuma
Audio and Speech Processing
Sound
In the acoustic event classification (AEC) framework that employs Blinkies, audio signals are converted into LED light emissions and subsequently captured by a single video camera. However, the 30 fps optical transmission channel conveys only about 0.2% of the normal audio bandwidth and is highly susceptible to noise. We propose a novel sound-to-light conversion method that leverages the encoder of a pre-trained autoencoder (AE) to distill compact, discriminative features from the recorded audio. To pre-train the AE, we adopt a noise-robust learning strategy in which artificial noise is injected into the encoder's latent representations during training, thereby enhancing the model's robustness against channel noise. The encoder architecture is specifically designed for the memory footprint of contemporary edge devices such as the Raspberry Pi 4. In a simulation experiment on the ESC-50 dataset under a stringent 15 Hz bandwidth constraint, the proposed method achieved higher macro-F1 scores than conventional sound-to-light conversion approaches.
title Pre-training Autoencoder for Acoustic Event Classification via Blinky
topic Audio and Speech Processing
Sound
url https://arxiv.org/abs/2509.15261