English
Related papers

Related papers: iSEGAN: Improved Speech Enhancement Generative Adv…

200 papers

Neural network-based methods have recently demonstrated state-of-the-art results on image synthesis and super-resolution tasks, in particular by using variants of generative adversarial networks (GANs) with supervised feature losses.…

Sound · Computer Science 2019-03-22 Sung Kim , Visvesh Sathe

Semantically guided conditional Generative Adversarial Networks (cGANs) have become a popular approach for face editing in recent years. However, most existing methods introduce semantic masks as direct conditional inputs to the generator…

Computer Vision and Pattern Recognition · Computer Science 2022-06-17 Jiaze Sun , Binod Bhattarai , Zhixiang Chen , Tae-Kyun Kim

Low-light image enhancement exhibits an ill-posed nature, as a given image may have many enhanced versions, yet recent studies focus on building a deterministic mapping from input to an enhanced version. In contrast, we propose a…

Computer Vision and Pattern Recognition · Computer Science 2021-10-05 Xiaopeng Sun , Muxingzi Li , Tianyu He , Lubin Fan

In recent years, generative adversarial networks (GANs) have made significant progress in generating audio sequences. However, these models typically rely on bandwidth-limited mel-spectrograms, which constrain the resolution of generated…

Sound · Computer Science 2025-05-15 Zeeshan Ahmad , Shudi Bao , Meng Chen

We propose to implement speech enhancement by the regeneration of clean speech from a salient representation extracted from the noisy signal. The network that extracts salient features is trained using a set of weight-sharing clones of the…

Audio and Speech Processing · Electrical Eng. & Systems 2019-09-12 Michael Chinen , W. Bastiaan Kleijn , Felicia S. C. Lim , Jan Skoglund

We propose a unified signal compression framework that uses a generative adversarial network (GAN) to compress heterogeneous signals. The compressed signal is represented as a latent vector and fed into a generator network that is trained…

Signal Processing · Electrical Eng. & Systems 2021-09-24 Bowen Liu , Changwoo Lee , Ang Cao , Hun-Seok Kim

Deep neural networks have played an important role in automatic sleep stage classification because of their strong representation and in-model feature transformation abilities. However, class imbalance and individual heterogeneity which…

Signal Processing · Electrical Eng. & Systems 2023-07-12 Xuewei Cheng , Ke Huang , Yi Zou , Shujie Ma

Neural audio synthesis methods can achieve high-fidelity and realistic sound generation by utilizing deep generative models. Such models typically rely on external labels which are often discrete as conditioning information to achieve…

Sound · Computer Science 2024-06-12 Yunyi Liu , Craig Jin

The prevailing method for neural speech enhancement predominantly utilizes fully-supervised deep learning with simulated pairs of far-field noisy-reverberant speech and clean speech. Nonetheless, these models frequently demonstrate…

Audio and Speech Processing · Electrical Eng. & Systems 2025-04-16 Tong Lei , Qinwen Hu , Ziyao Lin , Andong Li , Rilin Chen , Meng Yu , Dong Yu , Jing Lu

Getting rid of the fundamental limitations in fitting to the paired training data, recent unsupervised low-light enhancement methods excel in adjusting illumination and contrast of images. However, for unsupervised low light enhancement,…

Computer Vision and Pattern Recognition · Computer Science 2022-07-05 Zhangkai Ni , Wenhan Yang , Hanli Wang , Shiqi Wang , Lin Ma , Sam Kwong

Efficient audio synthesis is an inherently difficult machine learning task, as human perception is sensitive to both global structure and fine-scale waveform coherence. Autoregressive models, such as WaveNet, model local structure at the…

Compensation for channel mismatch and noise interference is essential for robust automatic speech recognition. Enhanced speech has been introduced into the multi-condition training of acoustic models to improve their generalization ability.…

Sound · Computer Science 2022-11-24 Hung-Shin Lee , Pin-Yuan Chen , Yao-Fei Cheng , Yu Tsao , Hsin-Min Wang

This paper describes a real-time General Speech Reconstruction (Gesper) system submitted to the ICASSP 2023 Speech Signal Improvement (SSI) Challenge. This novel proposed system is a two-stage architecture, in which the speech restoration…

Sound · Computer Science 2023-06-16 Wenzhe Liu , Yupeng Shi , Jun Chen , Wei Rao , Shulin He , Andong Li , Yannan Wang , Zhiyong Wu

Numerous voice conversion (VC) techniques have been proposed for the conversion of voices among different speakers. Although good quality of the converted speech can be observed when VC is applied in a clean environment, the quality…

Audio and Speech Processing · Electrical Eng. & Systems 2023-01-20 Yun-Ju Chan , Chiang-Jen Peng , Syu-Siang Wang , Hsin-Min Wang , Yu Tsao , Tai-Shih Chi

Conditional Generative Adversarial Networks (cGAN) generate realistic images by incorporating class information into GAN. While one of the most popular cGANs is an auxiliary classifier GAN with softmax cross-entropy loss (ACGAN), it is…

Computer Vision and Pattern Recognition · Computer Science 2021-11-02 Minguk Kang , Woohyeon Shim , Minsu Cho , Jaesik Park

Previous works (Donahue et al., 2018a; Engel et al., 2019a) have found that generating coherent raw audio waveforms with GANs is challenging. In this paper, we show that it is possible to train GANs reliably to generate high quality…

Audio and Speech Processing · Electrical Eng. & Systems 2019-12-10 Kundan Kumar , Rithesh Kumar , Thibault de Boissiere , Lucas Gestin , Wei Zhen Teoh , Jose Sotelo , Alexandre de Brebisson , Yoshua Bengio , Aaron Courville

The human brain contextually exploits heterogeneous sensory information to efficiently perform cognitive tasks including vision and hearing. For example, during the cocktail party situation, the human auditory cortex contextually integrates…

Sound · Computer Science 2021-12-17 Mandar Gogate , Kia Dashtipour , Amir Hussain

Training generative adversarial networks requires balancing of delicate adversarial dynamics. Even with careful tuning, training may diverge or end up in a bad equilibrium with dropped modes. In this work, we improve CS-GAN with natural…

Machine Learning · Computer Science 2020-07-02 Yan Wu , Jeff Donahue , David Balduzzi , Karen Simonyan , Timothy Lillicrap

We propose a learning-based filter that allows us to directly modify a synthetic speech waveform into a natural speech waveform. Speech-processing systems using a vocoder framework such as statistical parametric speech synthesis and voice…

Audio and Speech Processing · Electrical Eng. & Systems 2018-10-02 Kou Tanaka , Takuhiro Kaneko , Nobukatsu Hojo , Hirokazu Kameoka

Generative Adversarial Networks (GANs) enjoy great success at image generation, but have proven difficult to train in the domain of natural language. Challenges with gradient estimation, optimization instability, and mode collapse have lead…

Computation and Language · Computer Science 2020-02-28 Cyprien de Masson d'Autume , Mihaela Rosca , Jack Rae , Shakir Mohamed