Working With Environmental Noise and Noise-Cancelation: A Workload Assessment With EEG and Subjective Measures

As working and learning environments become open and flexible, people are also potentially surrounded by ambient noise, which causes an increase in mental workload. The present study uses electroencephalogram (EEG) and subjective measures to investigate if noise-canceling technologies can fade out external distractions and free up mental resources. Therefore, participants had to solve spoken arithmetic tasks that were read out via headphones in three sound environments: a quiet environment (no noise), a noisy environment (noise), and a noisy environment but with active noise-canceling headphones (noise-canceling). Our results of brain activity partially confirm an assumed lower mental load in no noise and noise-canceling compared to noise test condition. The mean P300 activation at Cz resulted in a significant differentiation between the no noise and the other two test conditions. Subjective data indicate an improved situation for the participants when using the noise-canceling technology compared to “normal” headphones but shows no significant discrimination. The present results provide a foundation for further investigations into the relationship between noise-canceling technology and mental workload. Additionally, we give recommendations for an adaptation of the test design for future studies.

Background Noise Removal Technique using Deep Learning Segmentation Network without Segmentation Map

Audio data acquired at industrial manufacturing sites often include unexpected background noise. Since the performance of data-driven models can be worse by background noise. Therefore, it is important to get rid of unwanted background noise. There are two main techniques for noise canceling in a traditional manner. One is Active Noise Canceling (ANC), which generates an inverted phase of the sound that we want to remove. The other is Passive Noise Canceling (PNC), which physically blocks the noise. However, these methods require large device size and expensive cost. Thus, we propose a deep learning-based noise canceling method. This technique was developed using audio imaging technique and deep learning segmentation network. However, the proposed model only needs the information on whether the audio contains noise or not. In other words, unlike the general segmentation technique, a pixel-wise ground truth segmentation map is not required for this method. We demonstrate to evaluate the separation using pump sound of MIMII dataset, which is open-source dataset.