Phase sensitive masking-based single channel speech enhancement using conditional generative adversarial network

S Routray, Q Mao - Computer Speech & Language, 2022 - Elsevier
We propose PSMGAN, an efficient phase sensitive masking-based single-channel speech
enhancement technique using a conditional generative adversarial network (cGAN). The …

Improved speech enhancement using a time-domain GAN with mask learning

J Lin, S Niu, AJ Wijngaarden, JL McClendon… - … of Interspeech 2020, 2020 - par.nsf.gov
Speech enhancement is an essential component in robust automatic speech recognition
(ASR) systems. Most speech enhancement methods are nowadays based on neural …

Speech enhancement using forked generative adversarial networks with spectral subtraction

J Lin, S Niu, Z Wei, X Lan, AJ Wijngaarden… - … of Interspeech 2019, 2019 - par.nsf.gov
Speech enhancement techniques that use a generative adversarial network (GAN) can
effectively suppress noise while allowing models to be trained end-to-end. However, such …

Time-frequency masking-based speech enhancement using generative adversarial network

MH Soni, N Shah, HA Patil - 2018 IEEE international …, 2018 - ieeexplore.ieee.org
The success of time-frequency (TF) mask-based approaches is dependent on the accuracy
of predicted mask given the noisy spectral features. The state-of-the-art methods in TF …

Perception-guided generative adversarial network for end-to-end speech enhancement

Y Li, M Sun, X Zhang - Applied Soft Computing, 2022 - Elsevier
Single channel speech enhancement has reached a great progress recently with the
development of deep learning. However, it is still a challenging problem to achieve …

CP-GAN: Context pyramid generative adversarial network for speech enhancement

G Liu, K Gong, X Liang, Z Chen - ICASSP 2020-2020 IEEE …, 2020 - ieeexplore.ieee.org
The topic of speech enhancement has been largely improved recently, especially with the
development of generative adversarial networks (GANs). However prior methods simply …

Time-frequency mask-based speech enhancement using convolutional generative adversarial network

N Shah, HA Patil, MH Soni - 2018 Asia-Pacific Signal and …, 2018 - ieeexplore.ieee.org
Speech Enhancement (SE) system deals with improving the perceptual quality and
preserving the speech intelligibility of the noisy mixture. The Time-Frequency (TF) masking …

A two-stage complex network using cycle-consistent generative adversarial networks for speech enhancement

G Yu, Y Wang, H Wang, Q Zhang, C Zheng - Speech Communication, 2021 - Elsevier
Cycle-consistent generative adversarial networks (CycleGAN) have shown their promising
performance for speech enhancement (SE), while one intractable shortcoming of these …

Towards generalized speech enhancement with generative adversarial networks

S Pascual, J Serrà, A Bonafonte - arXiv preprint arXiv:1904.03418, 2019 - arxiv.org
The speech enhancement task usually consists of removing additive noise or reverberation
that partially mask spoken utterances, affecting their intelligibility. However, little attention is …

A parallel-data-free speech enhancement method using multi-objective learning cycle-consistent generative adversarial network

Y Xiang, C Bao - IEEE/ACM Transactions on Audio, Speech …, 2020 - ieeexplore.ieee.org
Recently, deep neural networks (DNNs) have become the mainstream strategy for speech
enhancement task because it can achieve the higher speech quality and intelligibility than …