Open AccessSpeech Dereverberation Using Deep Learning Algorithm
Author(s) -
S. Saraswathi,
S Ramya
Publication year - 2021
Publication title -
international journal of advanced research in science, communication and technology
Language(s) - English
Resource type - Journals
ISSN - 2581-9429
DOI - 10.48175/ijarsct-2318
Subject(s) - computer science , generator (circuit theory) , short time fourier transform , speech recognition , microphone , deep learning , algorithm , artificial intelligence , speech enhancement , fourier transform , encoder , convolutional neural network , autoregressive model , generative adversarial network , pattern recognition (psychology) , mathematics , fourier analysis , noise reduction , mathematical analysis , power (physics) , telecommunications , physics , sound pressure , quantum mechanics , operating system , econometrics
This paper focuses on speech derverberation using a single microphone. We investigate the applicability of fully convolutional networks (FCN) to enhance the speech signal represented by short-time Fourier transform (STFT) images in light of their recent success in many image processing applications. We present two variants: a "U-Net," which is an encoder-decoder network with skip connections, and a generative adversarial network (GAN) with the U-Net as the generator, which produces a more intuitive cost function for training. To assess our method, we used data from the REVERB challenge and compared our results to those of other methods tested under the same conditions. In most cases, we discovered that our method outperforms the competing methods.