Time-Frequency Masking-Based Speech Enhancement Using Generative Adversarial Network

By Meet H. Soni, Neil Shah, Hemant A. Patil. 2018

218 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

In Signal Processing

Citations in the corpus

Real Time Speech Enhancement in the Waveform Domain (2020, background): “Over the last years, there has been a growing interest towards DNN based methods for speech enhancement [34, 35, 36, 37, 20, 38, 39, 22, 40, 7, 41, 8, 42, 21, 37].”
MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancement (2019, methodology): “MMSE-GAN (Soni et al., 2018) is a time-frequency masking-based method that uses a GAN objective along with L 2 loss.”
PHASEN: A Phase-and-Harmonics-Aware Speech Enhancement Network (2019, methodology): “Also, our method shows great improvement over time-frequency domain method like MMSE-GAN (Soni, Shah, and Patil 2018) on all metrics, indicating the superiority of our network de-sign.”
High Fidelity Speech Regeneration with Application to Speech Enhancement (2021, methodology): “Deep generative models such as Generative Adversarial Network (GAN) or WaveNet were also suggested for the task [6, 7, 8].”
Conditional Diffusion Probabilistic Model for Speech Enhancement (2022, background): “Well-known examples along this direction include generative adversarial networks (GANs) [11, 12], Bayesian wavenet [13], variational autoencoders [14], and flow-based models [15].”
Interactive Speech and Noise Modeling for Speech Enhancement (2020, methodology): “SEGAN (Pascual, Bonafonte, and Serra 2017) and MMSE-GAN (Soni, Shah, and Patil 2018) are two GAN-based methods.”
Phase-aware Speech Enhancement with Deep Complex U-Net (2019, methodology): “For all experiments, we used the same experimental setups as previous works in order to perform direct performance comparison (Pascual et al., 2017; Rethage et al., 2018; Soni et al., 2018; Germain et al., 2018).”
A Survey on Audio Diffusion Models: Text To Speech Synthesis and Enhancement in Generative AI (2023, unknown): “A discriminative method minimizes the difference between enhanced and clean speech [13, 16, 17, 42], while generative models are optimized by estimating the distribution of clean signals [51, 80, 86, 106, 108].”
Deep Residual-Dense Lattice Network for Speech Enhancement (2020, methodology): “A GAN was employed for speech enhancement in the time-domain (SEGAN), which used encoder-decoder CNNs for both the generator and discriminator (Pascual, Bonafonte, and Serra 2017).”