Single-channel speech enhancement by PSO-GSA with harmonic regeneration noise reduction

Speech quality significantly affects the performance of speech dependent systems. Noise in background lowers clarity and intelligibility speech. The augmentation can increase its quality. We propose a single-channel improvement framework that combines particle swarm optimization (PSO), gravitational search algorithm (GSA), harmonic regeneration noise reduction (HRNR) to minimize signal intelligibility. proposed hybrid optimizes amount overlap between noisy frames. This helps reducing overlapped noise. Then HRNR is applied retain harmonics. gives for babble, car exhibition segmental ratio (SNR) also improved these types. There with minimal distortion.