This letter proposes a perceptual metric for speech quality evaluation, which is suitable, as a
loss function, for training deep learning methods. This metric, derived from the perceptual …

Deep learning-based speech enhancement for real-time applications recently made large
advancements. Due to the lack of a tractable perceptual optimization target, many myths …

Deep generative models have recently achieved impressive performance in speech and
music synthesis. However, compared to the generation of those domain-specific sounds …

Deep learning has recently made a breakthrough in the speech enhancement process.
Some architectures are based on a time domain representation, while others operate in the …

Speech enhancement algorithms based on deep learning have been improved in terms of
speech intelligibility and perceptual quality greatly. Many methods focus on enhancing the …

Conventional audio coding technologies commonly leverage human perception of sound, or
psychoacoustics, to reduce the bitrate while preserving the perceptual quality of the …

Speech enhancement employing deep neural networks (DNNs) for denoising is called deep
noise suppression (DNS). The DNS trained with mean squared error (MSE) losses cannot …

From a statistical perspective, the conventional minimum mean squared error (MMSE)
criterion can be considered as the maximum likelihood (ML) solution under an assumed …

Estimating time-frequency domain masks for speech enhancement using deep learning
approaches has recently become a popular field in research. In this paper, we propose a …

Single-channel speech enhancement with deep neural networks (DNNs) has shown
promising performance and is thus intensively being studied. In this paper, instead of …