Recently, convolution-augmented transformer (Conformer) has achieved promising
performance in automatic speech recognition (ASR) and time-domain speech enhancement …

In this work, we further develop the conformer-based metric generative adversarial network
(CMGAN) model 1 for speech enhancement (SE) in the time-frequency (TF) domain. This …

In recent years, Generative Adversarial Networks (GANs) have produced significantly
improved results in speech enhancement (SE) tasks. They are difficult to train, however. In …

Deep learning has become a de facto method of choice for speech enhancement tasks with
significant improvements in speech quality. However, real-time processing with reduced size …

Speech enhancement is critical for improving speech intelligibility and quality in various
audio devices. In recent years, deep learning-based methods have significantly improved …

Recent speech enhancement work, which makes use of neural networks trained with a loss
derived in part using an adversarial metric prediction network, has shown to be very …

Abstract In recent years, Generative Adversarial Networks (GANs) have made significant
progress in the field of speech enhancement. However, due to the high training difficulty of …

In the speech enhancement (SE) model, using auxiliary loss based on acoustic parameters
can improve enhancement effects. However, currently used acoustic parameters focus on …

The success of deep learning has significantly benefited single-channel speech
enhancement in terms of intelligibility and perceptual quality. Traditional approaches have …

Speech enhancement tasks are methods that improve the quality and intelligibility of noisy
audio signals. To that end, speech enhancement models are trained to distinguish between …