paper-with-me

Papers

Diffiner: A Versatile Diffusion-based Generative Refiner for Speech Enhancement

2022-10-27 · Ryosuke Sawata, Naoki Murata, Yuhta Takida, Toshimitsu Uesaka, Takashi Shibuya, Shusuke Takahashi, Yuki Mitsufuji

Although deep neural network (DNN)-based speech enhancement (SE) methods outperform the previous non-DNN-based ones, they often degrade the perceptual quality of generated outputs. To tackle this problem, we introduce a DNN-based generative refiner, Diffiner, aiming to improve perceptual speech quality pre-processed by an SE method. We train a diffusion-based generative model by utilizing a dataset consisting of clean speech only. Then, our refiner effectively mixes clean parts newly generated via denoising diffusion restoration into the degraded and distorted parts caused by a preceding SE method, resulting in refined speech. Once our refiner is trained on a set of clean speech, it can be applied to various SE methods without additional training specialized for each SE module. Therefore, our refiner can be a versatile post-processing module w.r.t. SE methods and has high potential in terms of modularity. Experimental results show that our method improved perceptual speech quality regardless of the preceding SE methods used.

📄 PDF Abstract BibTeX arXiv:2210.17287

Code (1)

sony/diffiner 공식 구현 pytorch

Tasks

DenoisingSpeech Enhancement

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Diffusion-based Signal Refiner for Speech Separation

2023-05-10 · Masato Hirano, Kazuki Shimada, Yuichiro Koyama, Shusuke Takahashi 외

We have developed a diffusion-based speech refiner that improves the reference-free perceptual quality of the audio predicted by preceding single-channel speech separation models. Although modern deep neural network-base…

DenoisingSpeech EnhancementSpeech Separation

SpeechRefiner: Towards Perceptual Quality Refinement for Front-End Algorithms

2025-06-16 · Sirui Li, Shuai Wang, Zhijun Liu, Zhongjie Jiang 외

Speech pre-processing techniques such as denoising, de-reverberation, and separation, are commonly employed as front-ends for various downstream speech processing tasks. However, these methods can sometimes be inadequate…

Denoising

DiffRefiner: Coarse to Fine Trajectory Planning via Diffusion Refinement with Semantic Interaction for End to End Autonomous Driving

2025-11-21 · Liuhan Yin, Runkun Ju, Guodong Guo, Erkang Cheng arxiv

Unlike discriminative approaches in autonomous driving that predict a fixed set of candidate trajectories of the ego vehicle, generative methods, such as diffusion models, learn the underlying distribution of future moti…

Trajectory PredictionTrajectory PlanningAutonomous Driving

Noise Estimation for Generative Diffusion Models

2021-04-06 · Robin San-Roman, Eliya Nachmani, Lior Wolf

Generative diffusion models have emerged as leading models in speech and image generation. However, in order to perform well with a small number of denoising steps, a costly tuning of the set of noise parameters is neede…

DenoisingImage GenerationNoise Estimation

AudioSR: Versatile Audio Super-resolution at Scale

2023-09-13 · Haohe Liu, Ke Chen, Qiao Tian, Wenwu Wang 외

Audio super-resolution is a fundamental task that predicts high-frequency components for low-resolution audio, enhancing audio quality in digital applications. Previous methods have limitations such as the limited scope …

Audio Super-ResolutionSuper-Resolution