A New Spectral-Geometric Optimized Architecture for Distortion-Free Binaural Speech Intelligibility
Overview
Commercial hearing aids struggle with poor speech clarity in noise, notably “cocktail party” settings. Many devices also distort the spatial cues critical for sound localization. As a result, over a fifth of hearing aid users have discontinued usage due to discomfort. To address the fundamental speech intelligibility and spatial fidelity tradeoff, this project presents a new binaural signal-processing architecture inspired by biological auditory processing. Implemented in MATLAB and Python, the system processes signals from binaural microphones. A lightweight Conv-TasNet model classifies input sound and computes energy masks for extracted speeches. The identified speech signals feed a spatially revised GCC-PHAT function, performing direction-of-arrival (DOA) estimation to track speech in multi-speaker environments. The architecture then uses DOA information to optimize an adaptive multi-constraint LCMV beamformer, improving upon the single-constraint beamformers used in traditional hearing aids. In the LCMV, target steering is derived from user orientation, spatial constraints from localized speech sources, and a covariance matrix from exponentially weighted recursion, enabling distortion-free speech enhancement. This real-time architecture was evaluated on over 12,000 open-source recordings via the Short-Time Objective Intelligibility metric, which assesses speech intelligibility on a 0-1 scale. Results demonstrate the algorithm improved speech clarity by an average of 20% compared to leading ML filtering and 54% compared to classical noise suppression methods such as spectral subtraction or Wiener filtering. Furthermore, realistic interaural time difference cues are preserved for a spatially natural listening experience.
Competition history
- ISEF 2026
Resources
Related projects
ISEF · 2024
Clear: Utilizing Glasses-Based Beamformers to Improve Speech Clarity and Spatial Context for the Hearing Impaired
ISEF · 2021
A Non-Invasive Ear-EEG Hearing Aid to Address the Cocktail Party Problem via Cloud-Based Deep Learning
ISEF · 2015
The Exchange iMproving Unit: An Auditory Device for Directional Filtering
ISEF · 2020
Auditory Attention Decoding Approach to Cocktail Party Problem Using Deep Learning
ISEF · 2024
A Physiological Self-Supervised Attention-Based Approach for Sound Source Separation in Auditory Scenes
ISEF · 2021
SoundScape: Real-Time 3D Sound Localization and Classification with Sensory Substitution for the Deaf and Hard of Hearing
ISEF · 2025
Direct Pulse-Density-Modulated Bitstream Operators for Efficient Beamforming With Large Sensor Arrays
ISEF · 2025
Glasses for the Hearing Impaired
Closest projects by meaning, across every fair and year in the corpus.
Browse more like this
Source: Regeneron International Science and Engineering Fair