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

TL;DR

This paper introduces a lightweight, noise-robust infant cry detection method combining blueprint separable convolutions and a time-frequency recurrent neural network, outperforming existing approaches in noisy environments.

Contribution

The paper presents a novel multi-scale convolutional recurrent neural network with attention mechanisms for infant cry detection in noisy settings, emphasizing computational efficiency and robustness.

Findings

Outperforms state-of-the-art methods in accuracy and F1-score.

Effective in various noisy environments with different SNR levels.

Uses diverse datasets and environmental corruption techniques for robustness.

Abstract

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.