Improving Speech Intelligibility in Noise Using a Binary Mask That Is Based on Magnitude Spectrum Constraints
A computationally-efficient single-channel speech enhancement algorithm to improve intelligibility in monaural hearing aids is presented in this paper. The algorithm combines a novel set of features with a simple supervised machine learning technique to estimate the frequency-domain Wiener filter for noise reduction, using extremely low computational resources. Results show a noticeable intelligibility improvement in terms of PESQ score and SNR<sub>ESI</sub>, even for low input SNR, using only a 7% of the computational resources available in a state-of-the-art commercial hearing aid. The performance of the algorithm is comparable to the performance of current algorithms that use more computationally complex features and learning schemas.