Infant Cry Detection In Noisy Environment Using Blueprint Separable Convolutions and Time-Frequency Recurrent Neural Network

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yu, Haolin, Li, Yanxiong
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912555992088576
author Yu, Haolin
Li, Yanxiong
author_facet Yu, Haolin
Li, Yanxiong
contents Infant cry detection is a crucial component of baby care system. In this paper, we propose a lightweight and robust method for infant cry detection. The method leverages blueprint separable convolutions to reduce computational complexity, and a time-frequency recurrent neural network for adaptive denoising. The overall framework of the method is structured as a multi-scale convolutional recurrent neural network, which is enhanced by efficient spatial attention mechanism and contrast-aware channel attention module, and acquire local and global information from the input feature of log Mel-spectrogram. Multiple public datasets are adopted to create a diverse and representative dataset, and environmental corruption techniques are used to generate the noisy samples encountered in real-world scenarios. Results show that our method exceeds many state-of-the-art methods in accuracy, F1-score, and complexity under various signal-to-noise ratio conditions. The code is at https://github.com/fhfjsd1/ICD_MMSP.
format Preprint
id arxiv_https___arxiv_org_abs_2508_19308
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Infant Cry Detection In Noisy Environment Using Blueprint Separable Convolutions and Time-Frequency Recurrent Neural Network
Yu, Haolin
Li, Yanxiong
Sound
Infant cry detection is a crucial component of baby care system. In this paper, we propose a lightweight and robust method for infant cry detection. The method leverages blueprint separable convolutions to reduce computational complexity, and a time-frequency recurrent neural network for adaptive denoising. The overall framework of the method is structured as a multi-scale convolutional recurrent neural network, which is enhanced by efficient spatial attention mechanism and contrast-aware channel attention module, and acquire local and global information from the input feature of log Mel-spectrogram. Multiple public datasets are adopted to create a diverse and representative dataset, and environmental corruption techniques are used to generate the noisy samples encountered in real-world scenarios. Results show that our method exceeds many state-of-the-art methods in accuracy, F1-score, and complexity under various signal-to-noise ratio conditions. The code is at https://github.com/fhfjsd1/ICD_MMSP.
title Infant Cry Detection In Noisy Environment Using Blueprint Separable Convolutions and Time-Frequency Recurrent Neural Network
topic Sound
url https://arxiv.org/abs/2508.19308