TEANet: A Transpose-Enhanced Autoencoder Network for Wearable Stress Monitoring

Mental stress poses a significant public health concern due to its detrimental effects on physical and mental well-being, necessitating the development of continuous stress monitoring tools for wearable devices. Blood volume pulse (BVP) sensors, readily available in many smartwatches, offer a convenient and cost-effective solution for stress monitoring. This study proposes a deep learning approach, a Transpose-Enhanced Autoencoder Network (TEANet), for stress detection using BVP signals. The proposed TEANet model was trained and validated utilizing a self-collected RUET SPML dataset, comprising 19 healthy subjects, and the publicly available wearable stress and affect detection (WESAD) dataset, comprising 15 healthy subjects. It achieves the highest accuracy of 92.51% and 96.94%, F1 scores of 95.03% and 95.95%, and kappa of 0.7915 and 0.9350 for RUET SPML, and WESAD datasets respectively. The proposed TEANet effectively detects mental stress through BVP signals with high accuracy, making it a promising tool for continuous stress monitoring. Furthermore, the proposed model effectively addresses class imbalances and demonstrates high accuracy, underscoring its potential for reliable real-time stress monitoring using wearable devices.

oboVox Far Field Speaker Recognition: A Novel Data Augmentation Approach with Pretrained Models

In this study, we address the challenge of speaker recognition using a novel data augmentation technique of adding noise to enrollment files. This technique efficiently aligns the sources of test and enrollment files, enhancing comparability. Various pre-trained models were employed, with the resnet model achieving the highest DCF of 0.84 and an EER of 13.44. The augmentation technique notably improved these results to 0.75 DCF and 12.79 EER for the resnet model. Comparative analysis revealed the superiority of resnet over models such as ECPA, Mel-spectrogram, Payonnet, and Titanet large. Results, along with different augmentation schemes, contribute to the success of RoboVox far-field speaker recognition in this paper