English
Related papers

Related papers: High-Resolution Speech Restoration with Latent Dif…

200 papers

Latent diffusion models offer an attractive alternative to discrete diffusion for non-autoregressive text generation by operating on continuous text representations and denoising entire sequences in parallel. The major challenge in latent…

Computation and Language · Computer Science 2026-05-11 Viacheslav Meshchaninov , Alexander Shabalin , Egor Chimbulatov , Nikita Gushchin , Ilya Koziev , Alexander Korotin , Dmitry Vetrov

High dynamic range (HDR) video reconstruction aims to generate HDR videos from low dynamic range (LDR) frames captured with alternating exposures. Most existing works solely rely on the regression-based paradigm, leading to adverse effects…

Computer Vision and Pattern Recognition · Computer Science 2024-06-13 Yuanshen Guan , Ruikang Xu , Mingde Yao , Ruisheng Gao , Lizhi Wang , Zhiwei Xiong

Diffusion priors have been used for blind face restoration (BFR) by fine-tuning diffusion models (DMs) on restoration datasets to recover low-quality images. However, the naive application of DMs presents several key limitations. (i) The…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Senmao Li , Kai Wang , Joost van de Weijer , Fahad Shahbaz Khan , Chun-Le Guo , Shiqi Yang , Yaxing Wang , Jian Yang , Ming-Ming Cheng

Diffusion-based generative models have greatly impacted the speech processing field in recent years, exhibiting high speech naturalness and spawning a new research direction. Their application in real-time communication is, however, still…

Signal Processing · Electrical Eng. & Systems 2026-04-22 Simon Welker , Bunlong Lay , Maris Hillemann , Tal Peer , Timo Gerkmann

The generative priors of pre-trained latent diffusion models (DMs) have demonstrated great potential to enhance the visual quality of image super-resolution (SR) results. However, the noise sampling process in DMs introduces randomness in…

Image and Video Processing · Electrical Eng. & Systems 2024-09-26 Lingchen Sun , Rongyuan Wu , Jie Liang , Zhengqiang Zhang , Hongwei Yong , Lei Zhang

Speech super-resolution (SR) reconstructs high-fidelity wideband speech from low-resolution inputs-a task that necessitates reconciling global harmonic coherence with local transient sharpness. While diffusion-based generative models yield…

Sound · Computer Science 2026-01-01 Jiajun Yuan , Xiaochen Wang , Yuhang Xiao , Yulin Wu , Chenhao Hu , Xueyang Lv

The tremendous progress in neural image generation, coupled with the emergence of seemingly omnipotent vision-language models has finally enabled text-based interfaces for creating and editing images. Handling generic images requires a…

Computer Vision and Pattern Recognition · Computer Science 2023-07-27 Omri Avrahami , Ohad Fried , Dani Lischinski

Diffusion Language models (DLMs) are a promising avenue for text generation due to their practical properties on tractable controllable generation. They also have the advantage of not having to predict text autoregressively. However,…

Machine Learning · Computer Science 2024-02-13 Sofia Maria Lo Cicero Vaina , Nikita Balagansky , Daniil Gavrilov

Optical coherence tomography (OCT) image analysis plays an important role in the field of ophthalmology. Current successful analysis models rely on available large datasets, which can be challenging to be obtained for certain tasks. The use…

Image and Video Processing · Electrical Eng. & Systems 2024-05-28 Kun Huang , Xiao Ma , Yuhan Zhang , Na Su , Songtao Yuan , Yong Liu , Qiang Chen , Huazhu Fu

Along with the prosperity of generative artificial intelligence (AI), its potential for solving conventional challenges in wireless communications has also surfaced. Inspired by this trend, we investigate the application of the advanced…

Information Theory · Computer Science 2026-03-10 Xingyu Zhou , Le Liang , Jing Zhang , Peiwen Jiang , Yong Li , Shi Jin

Deep generative models can generate high-fidelity audio conditioned on various types of representations (e.g., mel-spectrograms, Mel-frequency Cepstral Coefficients (MFCC)). Recently, such models have been used to synthesize audio waveforms…

Diffusion-based Generative Models (DGMs) have achieved unparalleled performance in synthesizing high-quality visual content, opening up the opportunity to improve image super-resolution (SR) tasks. Recent solutions for these tasks often…

Computer Vision and Pattern Recognition · Computer Science 2023-06-02 Ruibin Li , Qihua Zhou , Song Guo , Jie Zhang , Jingcai Guo , Xinyang Jiang , Yifei Shen , Zhenhua Han

In this work, we present DiffVoice, a novel text-to-speech model based on latent diffusion. We propose to first encode speech signals into a phoneme-rate latent representation with a variational autoencoder enhanced by adversarial training,…

Audio and Speech Processing · Electrical Eng. & Systems 2023-04-25 Zhijun Liu , Yiwei Guo , Kai Yu

Recently, denoising diffusion models have demonstrated remarkable performance among generative models in various domains. However, in the speech domain, the application of diffusion models for synthesizing time-varying audio faces…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-13 Ji-Sang Hwang , Sang-Hoon Lee , Seong-Whan Lee

In this paper, we propose a novel framework for solving high-definition video inverse problems using latent image diffusion models. Building on recent advancements in spatio-temporal optimization for video inverse problems using image…

Computer Vision and Pattern Recognition · Computer Science 2025-03-10 Taesung Kwon , Jong Chul Ye

Speech enhancement is designed to enhance the intelligibility and quality of speech across diverse noise conditions. Recently, diffusion model has gained lots of attention in speech enhancement area, achieving competitive results. Current…

Sound · Computer Science 2025-01-23 Chengzhong Wang , Jianjun Gu , Dingding Yao , Junfeng Li , Yonghong Yan

Generative models have shown robust performance on speech enhancement and restoration tasks, but most prior approaches operate offline with high latency, making them unsuitable for streaming applications. In this work, we investigate the…

Audio and Speech Processing · Electrical Eng. & Systems 2025-10-21 Tsun-An Hsieh , Sebastian Braun

Image rescaling aims to learn the optimal low-resolution (LR) image that can be accurately reconstructed to its original high-resolution (HR) counterpart, providing an efficient image processing and storage method for ultra-high definition…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Ce Wang , Zhenyu Hu , Wanjie Sun , Zhenzhong Chen

Autonomous driving demands high-quality LiDAR data, yet the cost of physical LiDAR sensors presents a significant scaling-up challenge. While recent efforts have explored deep generative models to address this issue, they often consume…

Computer Vision and Pattern Recognition · Computer Science 2024-09-11 Qianjiang Hu , Zhimin Zhang , Wei Hu

In medical imaging, the diffusion models have shown great potential for synthetic image generation tasks. However, these approaches often lack the interpretable connections between the generated and real images and can create anatomically…

Image and Video Processing · Electrical Eng. & Systems 2026-02-12 Jian-Qing Zheng , Yuanhan Mo , Yang Sun , Jiahua Li , Fuping Wu , Ziyang Wang , Tonia Vincent , Bartłomiej W. Papież