Speech Enhancement for Hearing Impaired Based on Bandpass Filters and a Compound Deep Denoising Autoencoder

• Published in: Symmetry (Basel) Vol. 13; no. 8; p. 1310
• Main Authors: AL-Taai, Raghad Yaseen Lazim, Wu, Xiaojun
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.08.2021
• Subjects: Algorithms; Artificial neural networks; Bandpass filters; Frequency analysis; Hearing aids; Hearing loss; Intelligibility; Machine learning; Mean square errors; Noise; Noise reduction; Performance evaluation; Signal processing; Signal to noise ratio; Sound; Sound filters; Speech; Speech processing

Deep neural networks have been applied for speech enhancements efficiently. However, for large variations of speech patterns and noisy environments, an individual neural network with a fixed number of hidden layers causes strong interference, which can lead to a slow learning process, poor generalis...