Smartphone-based real-time speech enhancement for improving hearing aids speech perception

Area of Science:

• Audiology and Speech Processing
• Mobile Health Technology
• Signal Processing

Background:

• Hearing aid devices (HADs) often struggle with noise suppression and speech enhancement in real-world environments.
• Existing solutions may be limited by processing power or accessibility.
• The integration of advanced signal processing on ubiquitous mobile devices offers a potential solution.

Purpose of the Study:

• To develop and evaluate a real-time speech processing pipeline for hearing aid devices (HADs) implemented on Android smartphones.
• To improve speech quality and intelligibility through effective noise suppression and speech enhancement (SE).
• To assess the performance of the pipeline using objective perceptual metrics.

Main Methods:

• Development of a novel speech processing pipeline optimized for mobile execution.
• Real-time implementation on Android smartphone platforms.
• Objective evaluation using Perceptual Evaluation of Speech Quality (PESQ), Noise Attenuation Level (NAL), and Coherent Speech Intelligibility Index (CSII).

Main Results:

• The developed pipeline successfully suppresses background noise.
• Significant improvements in speech quality and intelligibility were observed.
• Objective measures (PESQ, NAL, CSII) confirmed the effectiveness of the noise suppression and speech enhancement.

Conclusions:

• A real-time speech processing pipeline for HADs can be effectively implemented on smartphones.
• The proposed method offers a promising approach to enhance speech perception for hearing aid users.
• Mobile-based solutions have the potential to improve accessibility and performance of hearing assistance technology.