Baby Cry Recognition by BCRNet Using Transfer Learning and Deep Feature Fusion

Deep learning theory has made remarkable advancements in the field of baby cry recognition, significantly enhancing its accuracy. Nonetheless, existing research faces two challenges. Firstly, the limited size of the database increases the risk of overfitting for a deep learning model. Secondly, the integration of multi-domain features has been neglected. To address these issues, a novel approach called BCRNet is proposed, which combines transfer learning and feature fusion. The BCRNet model takes multi-domain features as input and extracts deep features using a transfer learning model. Subsequently, a multilayer autoencoder is utilized for feature reduction, and a Support Vector Machine (SVM) is employed to select the transfer learning model with the highest classification accuracy. Then two features are concatenated to form fused features. Finally, the fused features are fed into a deep neural network for classification. Experimental results show that the proposed model is effective in mitigating the model overfitting problem due to small datasets. The fused features of the proposed method are better than the existing methods using single domain features.

Automated summary

Deep learning theory has made remarkable advancements in the field of baby cry recognition. However, existing research faces challenges of small database size and neglect of multi-domain feature integration. To address these issues, a novel approach that combines transfer learning and feature fusion is proposed. Experimental results show that the proposed method effectively mitigates model overfitting due to small datasets and the fused features are better than existing single domain feature methods.