English
Related papers

Related papers: SpecGrad: Diffusion Probabilistic Model based Neur…

200 papers

Preference optimization for diffusion models aims to align them with human preferences for images. Previous methods typically use Vision-Language Models (VLMs) as pixel-level reward models to approximate human preferences. However, when…

Computer Vision and Pattern Recognition · Computer Science 2025-10-03 Tao Zhang , Cheng Da , Kun Ding , Huan Yang , Kun Jin , Yan Li , Tingting Gao , Di Zhang , Shiming Xiang , Chunhong Pan

This paper revisits the neural vocoder task through the lens of audio restoration and propose a novel diffusion vocoder called BridgeVoC. Specifically, by rank analysis, we compare the rank characteristics of Mel-spectrum with other common…

Sound · Computer Science 2025-11-11 Andong Li , Tong Lei , Rilin Chen , Kai Li , Meng Yu , Xiaodong Li , Dong Yu , Chengshi Zheng

Denoising Diffusion Probabilistic Models (DDPMs) have emerged as powerful tools for generative modeling. However, their sequential computation requirements lead to significant inference-time bottlenecks. In this work, we utilize the…

Machine Learning · Computer Science 2025-08-08 Hengyuan Hu , Aniket Das , Dorsa Sadigh , Nima Anari

Deep learning models leak significant amounts of information about their training datasets. Previous work has investigated training models with differential privacy (DP) guarantees through adding DP noise to the gradients. However, such…

Machine Learning · Computer Science 2020-07-23 Milad Nasr , Reza Shokri , Amir houmansadr

Diffusion models are state-of-the-art generative models on data modalities such as images, audio, proteins and materials. These modalities share the property of exponentially decaying variance and magnitude in the Fourier domain. Under the…

The audio spectrogram is a time-frequency representation that has been widely used for audio classification. One of the key attributes of the audio spectrogram is the temporal resolution, which depends on the hop size used in the Short-Time…

Sound · Computer Science 2024-01-15 Haohe Liu , Xubo Liu , Qiuqiang Kong , Wenwu Wang , Mark D. Plumbley

Purely neural network (NN) based speech separation and enhancement methods, although can achieve good objective scores, inevitably cause nonlinear speech distortions that are harmful for the automatic speech recognition (ASR). On the other…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-03 Yong Xu , Meng Yu , Shi-Xiong Zhang , Lianwu Chen , Chao Weng , Jianming Liu , Dong Yu

Deep generative models are key-enabling technology to computer vision, text generation, and large language models. Denoising diffusion probabilistic models (DDPMs) have recently gained much attention due to their ability to generate diverse…

Quantum Physics · Physics 2026-02-02 Bingzhi Zhang , Peng Xu , Xiaohui Chen , Quntao Zhuang

Despite the rapid development of neural vocoders in recent years, they usually suffer from some intrinsic challenges like opaque modeling, and parameter-performance trade-off. In this study, we propose an innovative time-frequency (T-F)…

Sound · Computer Science 2025-07-29 Andong Li , Tong Lei , Zhihang Sun , Rilin Chen , Erwei Yin , Xiaodong Li , Chengshi Zheng

Existing customization methods require access to multiple reference examples to align pre-trained diffusion probabilistic models (DPMs) with user-provided concepts. This paper aims to address the challenge of DPM customization when the only…

Computer Vision and Pattern Recognition · Computer Science 2024-03-21 Jiachun Pan , Jun Hao Liew , Vincent Y. F. Tan , Jiashi Feng , Hanshu Yan

Recently, SpecAugment, an augmentation scheme for automatic speech recognition that acts directly on the spectrogram of input utterances, has shown to be highly effective in enhancing the performance of end-to-end networks on public…

Audio and Speech Processing · Electrical Eng. & Systems 2019-12-12 Daniel S. Park , Yu Zhang , Chung-Cheng Chiu , Youzheng Chen , Bo Li , William Chan , Quoc V. Le , Yonghui Wu

Denoising Diffusion Probabilistic Models (DDPMs) have significantly advanced generative AI, achieving impressive results in high-quality image and data generation. However, enhancing fidelity without compromising semantic content remains a…

Minimum Variance Distortionless Response (MVDR) is a classical adaptive beamformer that theoretically ensures the distortionless transmission of signals in the target direction, which makes it popular in real applications. Its noise…

Sound · Computer Science 2024-09-16 Jinglin Bai , Hao Li , Xueliang Zhang , Fei Chen

This paper describes speech enhancement for realtime automatic speech recognition (ASR) in real environments. A standard approach to this task is to use neural beamforming that can work efficiently in an online manner. It estimates the…

In this paper, we present a novel diffusion model-based monaural speech enhancement method. Our approach incorporates the separate estimation of speech spectra's magnitude and phase in two diffusion networks. Throughout the diffusion…

Sound · Computer Science 2024-12-13 Yi Li , Yang Sun , Plamen Angelov

Recently, Denoising Diffusion Probabilistic Models (DDPMs) have attained leading performances across a diverse range of generative tasks. However, in the field of speech synthesis, although DDPMs exhibit impressive performance, their long…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-25 Xiangyu Zhang , Daijiao Liu , Hexin Liu , Qiquan Zhang , Hanyu Meng , Leibny Paola Garcia , Eng Siong Chng , Lina Yao

Diffusion model, a new generative modelling paradigm, has achieved great success in image, audio, and video generation. However, considering the discrete categorical nature of text, it is not trivial to extend continuous diffusion models to…

Computation and Language · Computer Science 2023-05-23 Hongyi Yuan , Zheng Yuan , Chuanqi Tan , Fei Huang , Songfang Huang

Time-variant factors often occur in real-world full-duplex communication applications. Some of them are caused by the complex environment such as non-stationary environmental noises and varying acoustic path while some are caused by the…

Audio and Speech Processing · Electrical Eng. & Systems 2023-02-28 Chengyu Zheng , Yuan Zhou , Xiulian Peng , Yuan Zhang , Yan Lu

Diffusion models are a class of generative models that have been recently used for speech enhancement with remarkable success but are computationally expensive at inference time. Therefore, these models are impractical for processing…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-15 Bunlong Lay , Rostislav Makarov , Timo Gerkmann

Currently, most speech processing techniques use magnitude spectrograms as front-end and are therefore by default discarding part of the signal: the phase. In order to overcome this limitation, we propose an end-to-end learning method for…

Sound · Computer Science 2018-02-01 Dario Rethage , Jordi Pons , Xavier Serra