{"ID":2877978,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.19308","arxiv_id":"2508.19308","title":"Infant Cry Detection In Noisy Environment Using Blueprint Separable Convolutions and Time-Frequency Recurrent Neural Network","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.","short_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...","url_abs":"https://arxiv.org/abs/2508.19308","url_pdf":"https://arxiv.org/pdf/2508.19308v1","authors":"[\"Haolin Yu\",\"Yanxiong Li\"]","published":"2025-08-26T08:07:36Z","proceeding":"cs.SD","tasks":"[\"cs.SD\"]","methods":"[]","has_code":false,"code_links":[{"ID":610435,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2877978,"paper_url":"https://arxiv.org/abs/2508.19308","paper_title":"Infant Cry Detection In Noisy Environment Using Blueprint Separable Convolutions and Time-Frequency Recurrent Neural Network","repo_url":"https://github.com/fhfjsd1/ICD_MMSP","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}