English
Related papers

Related papers: Few-step Adversarial Schr\"{o}dinger Bridge for Ge…

200 papers

Conditional generative models represent a significant advancement in the field of machine learning, allowing for the controlled synthesis of data by incorporating additional information into the generation process. In this work we introduce…

Machine Learning · Statistics 2024-09-27 Hanwen Huang

Generative adversarial networks (GAN) have recently been shown to be efficient for speech enhancement. However, most, if not all, existing speech enhancement GANs (SEGAN) make use of a single generator to perform one-stage enhancement…

Machine Learning · Computer Science 2020-10-28 Huy Phan , Ian V. McLoughlin , Lam Pham , Oliver Y. Chén , Philipp Koch , Maarten De Vos , Alfred Mertins

The dynamic Schr\"odinger bridge problem seeks a stochastic process that defines a transport between two target probability measures, while optimally satisfying the criteria of being closest, in terms of Kullback-Leibler divergence, to a…

Machine Learning · Statistics 2023-12-25 Stefano Peluchetti

A method for statistical parametric speech synthesis incorporating generative adversarial networks (GANs) is proposed. Although powerful deep neural networks (DNNs) techniques can be applied to artificially synthesize speech waveform, the…

Sound · Computer Science 2017-09-26 Yuki Saito , Shinnosuke Takamichi , Hiroshi Saruwatari

Although recent speech processing technologies have achieved significant improvements in objective metrics, there still remains a gap in human perceptual quality. This paper proposes Diffiner, a novel solution that utilizes the powerful…

Audio and Speech Processing · Electrical Eng. & Systems 2026-02-11 Masato Hirano , Ryosuke Sawata , Naoki Murata , Shusuke Takahashi , Yuki Mitsufuji

Recently, score-based generative models have been successfully employed for the task of speech enhancement. A stochastic differential equation is used to model the iterative forward process, where at each step environmental noise and white…

Audio and Speech Processing · Electrical Eng. & Systems 2023-05-31 Bunlong Lay , Simon Welker , Julius Richter , Timo Gerkmann

Generative diffusion models use time-forward and backward stochastic differential equations to connect the data and prior distributions. While conventional diffusion models (e.g., score-based models) only learn the backward process, more…

Machine Learning · Computer Science 2024-12-25 Kentaro Kaba , Reo Shimizu , Masayuki Ohzeki , Yuki Sughiyama

The intelligibility of speech severely degrades in the presence of environmental noise and reverberation. In this paper, we propose a novel deep learning based system for modifying the speech signal to increase its intelligibility under the…

Audio and Speech Processing · Electrical Eng. & Systems 2021-09-17 Haoyu Li , Junichi Yamagishi

The Schr\"odinger Bridge (SB) problem offers a powerful framework for combining optimal transport and diffusion models. A promising recent approach to solve the SB problem is the Iterative Markovian Fitting (IMF) procedure, which alternates…

Machine Learning · Computer Science 2024-11-06 Nikita Gushchin , Daniil Selikhanovych , Sergei Kholkin , Evgeny Burnaev , Alexander Korotin

Progressively applying Gaussian noise transforms complex data distributions to approximately Gaussian. Reversing this dynamic defines a generative model. When the forward noising process is given by a Stochastic Differential Equation (SDE),…

Machine Learning · Statistics 2023-04-06 Valentin De Bortoli , James Thornton , Jeremy Heng , Arnaud Doucet

Metasurface inverse design is challenged by the intricate relationship between structural parameters and electromagnetic responses, as well as the high dimensionality of the optimization space. Local models, while commonly employed, quickly…

This paper aims to conduct a comprehensive theoretical analysis of current diffusion models. We introduce a novel generative learning methodology utilizing the Schr{\"o}dinger bridge diffusion model in latent space as the framework for…

Machine Learning · Statistics 2024-12-24 Yuling Jiao , Lican Kang , Huazhen Lin , Jin Liu , Heng Zuo

Diffusion models have become the go-to method for large-scale generative models in real-world applications. These applications often involve data distributions confined within bounded domains, typically requiring ad-hoc thresholding…

Machine Learning · Statistics 2024-01-09 Wei Deng , Yu Chen , Nicole Tianjiao Yang , Hengrong Du , Qi Feng , Ricky T. Q. Chen

Deep Ensemble (DE) approach is a straightforward technique used to enhance the performance of deep neural networks by training them from different initial points, converging towards various local optima. However, a limitation of this…

Machine Learning · Computer Science 2024-04-25 Hyunsu Kim , Jongmin Yoon , Juho Lee

The dynamic Schr\"odinger bridge problem provides an appealing setting for solving constrained time-series data generation tasks posed as optimal transport problems. It consists of learning non-linear diffusion processes using efficient…

Machine Learning · Computer Science 2023-11-27 Ella Tamir , Martin Trapp , Arno Solin

The design of mean and variance schedules for the perturbed signal is a fundamental challenge in generative models. While score-based and Schr\"odinger bridge-based models require careful selection of the stochastic differential equation to…

Sound · Computer Science 2025-09-10 Taihui Wang , Rilin Chen , Tong Lei , Andong Li , Jinzheng Zhao , Meng Yu , Dong Yu

Diffusion-based speech enhancement has shown promising results, but can suffer from a slower inference time. Initializing the diffusion process with the enhanced audio generated by a regression-based model can be used to reduce the…

Sound · Computer Science 2024-06-11 Thanapat Trachu , Chawan Piansaddhayanon , Ekapol Chuangsuwanich

Current speech enhancement techniques operate on the spectral domain and/or exploit some higher-level feature. The majority of them tackle a limited number of noise conditions and rely on first-order statistics. To circumvent these issues,…

Machine Learning · Computer Science 2017-06-12 Santiago Pascual , Antonio Bonafonte , Joan Serrà

Generative Semantic Communication (GSC) is a promising solution for image transmission over narrow-band and high-noise channels. However, existing GSC methods rely on long, indirect transport trajectories from a Gaussian to an image…

Image and Video Processing · Electrical Eng. & Systems 2026-04-21 Dahua Gao , Ruichao Liu , Minxi Yang , Shuai Ma , Youlong Wu , Guangming Shi

Score-based generative models exhibit state of the art performance on density estimation and generative modeling tasks. These models typically assume that the data geometry is flat, yet recent extensions have been developed to synthesize…