2022/04/06 by Ivan Shchekotov, Pavel A. Andreev, Shchekotov, Ivan +7
Computer Science · Mathematics · Neuroscience · #Algorithm #Artificial Intelligence (cs.AI) #Artificial intelligence #Artificial neural network #Audio and Speech Processing (eess.AS) #Computer science #Convolution (computer science) #Convolutional neural network #FOS: Computer and information sciences #FOS: Electrical engineering #Fast Fourier transform #Field (mathematics) #Fourier transform #Hearing Loss and Rehabilitation #Image (mathematics) #Inpainting #Mathematics #Operator (biology) #Receptive field #Sound (cs.SD) #Speech Recognition and Synthesis #Speech and Audio Processing #Speech enhancement #Speech recognition #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2204.03042
openalex publication_date 2022/04/06 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Fast Fourier convolution (FFC) is the recently proposed neural operator showing promising performance in several computer vision problems. The FFC operator allows employing large receptive field operations within early layers of the neural network. It was shown to be especially helpful for inpainting of periodic structures which are common in audio processing. In this work, we design neural network architectures which adapt FFC for speech enhancement. We hypothesize that a large receptive field allows these networks to produce more coherent phases than vanilla convolutional models, and validate this hypothesis experimentally. We found that neural networks based on Fast Fourier convolution outperform analogous convolutional models and show better or comparable results with other speech enhancement baselines.