Abstract
DNN-based Speech Enhancement (SE) models suffer from significant performance degradation in real recordings due to the mismatch between the synthetic datasets employed for training and real test sets. To solve this problem, we propose a new Generative Adversarial Network framework for Noise Modeling (NM-GAN) that creates realistic paired training sets by imitating real noise distribution. The proposed framework combines a novel 7-layer U-Net with two bidirectional long short-term memory (LSTM) layers that act as a generator to construct complex noise. NM-GAN generates enough recall (diversity) and precision (noise quality) in its samples through adversarial and alternate training, effectively simulating real noise, which is then utilized to compose realistic paired training sets. Extensive experiments employing various qualitative and quantitative evaluation metrics verify the effectiveness of the generated noise samples and training sets, demonstrating our framework’s capabilities.
Highlights
IntroductionAcademic Editors: Andrea Prati, Published: 11 February 2022
Academic Editors: Andrea Prati, Published: 11 February 2022Speech enhancement [1] (SE) is the extraction of speech signals while suppressing sources of interference and eliminating noise
Given the importance of realistic datasets, this paper focuses on developing a Generative Adversarial Nets (GANs) that effectively models noise and creates synthetic but highly credible training sets
Summary
Academic Editors: Andrea Prati, Published: 11 February 2022. Speech enhancement [1] (SE) is the extraction of speech signals while suppressing sources of interference and eliminating noise. SE plays an important role in improving the intelligibility and quality of noisy speech recordings. Deep Neural Network (DNN)-based SE methods have received significant attention as part of a broader interest in learning-related Artificial Intelligence (AI). Neural Networks (RNNs) [2,3] and Generative Adversarial Nets (GANs) [4,5], along with other DNN-based architectures [6,7,8] that have already been explored in SE tasks. Problem Statement with regard to jurisdictional claims in
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.