Yu Tsao, PhD | Research Center for Information Technology Innovation, Academia Sinica; Cheng-Hung Hsin, PhD
Competition Sponsor: Academia Sinica
Awardee Year: 2023
This research project aims to advance the field of audiology by developing a novel approach for evaluating speech quality and assessing listening fatigue in users of speech enhancement (SE) technology. Utilizing brainwave-based audiometry techniques and leveraging advancements in machine learning, this project seeks to provide personalized and objective assessments of SE system effectiveness.
The initial phase of the project entails recruiting a sizable cohort of healthy young adults to participate in electroencephalogram (EEG) experiments. These experiments will capture brainwave patterns during speech perception tasks, encompassing various listening conditions such as clear speech, noisy speech, and speech processed by SE systems. By establishing a normative model of brainwave activity in a healthy population, the project aims to quantify the impact of SE technology on speech comprehension.
The subsequent phase focuses on developing neural network models that extract pertinent features from the EEG data. These models will enable the objective evaluation of speech quality and the detection of listening fatigue in SE users. The primary objective is to optimize SE systems to enhance individual user experiences and communication outcomes.
By merging state-of-the-art technology with insights from neuroscience, this project strives to revolutionize audiological evaluation paradigms. Our ultimate goal is to make substantial contributions to audiology, advancing personalized solutions that empower individuals with hearing loss to actively participate in the auditory world and enhance their life quality.