English
Related papers

Related papers: FreGrad: Lightweight and Fast Frequency-aware Diff…

200 papers

The application of diffusion transformers is suffering from their significant inference costs. Recently, feature caching has been proposed to solve this problem by reusing features from previous timesteps, thereby skipping computation in…

Most GAN(Generative Adversarial Network)-based approaches towards high-fidelity waveform generation heavily rely on discriminators to improve their performance. However, GAN methods introduce much uncertainty into the generation process and…

Sound · Computer Science 2022-03-22 Shengyuan Xu , Wenxiao Zhao , Jing Guo

Diffusion models have recently been shown to be relevant for high-quality speech generation. Most work has been focused on generating spectrograms, and as such, they further require a subsequent model to convert the spectrogram to a…

Sound · Computer Science 2024-03-12 Roi Benita , Michael Elad , Joseph Keshet

Multimodal medical images play a crucial role in the precise and comprehensive clinical diagnosis. Diffusion model is a powerful strategy to synthesize the required medical images. However, existing approaches still suffer from the problem…

Computer Vision and Pattern Recognition · Computer Science 2025-05-28 Jiahua Xu , Dawei Zhou , Lei Hu , Zaiyi Liu , Nannan Wang , Xinbo Gao

Sound morphing is the process of gradually and smoothly transforming one sound into another to generate novel and perceptually hybrid sounds that simultaneously resemble both. Recently, diffusion-based text-to-audio models have produced…

Audio and Speech Processing · Electrical Eng. & Systems 2024-08-15 Purnima Kamath , Chitralekha Gupta , Suranga Nanayakkara

Audio diffusion models can synthesize a wide variety of sounds. Existing models often operate on the latent domain with cascaded phase recovery modules to reconstruct waveform. This poses challenges when generating high-fidelity audio. In…

Sound · Computer Science 2023-11-21 Ge Zhu , Yutong Wen , Marc-André Carbonneau , Zhiyao Duan

Diffusion models have recently set new benchmarks in Speech Enhancement (SE). However, most existing score-based models treat speech spectrograms merely as generic 2D images, applying uniform processing that ignores the intrinsic structural…

Sound · Computer Science 2026-02-03 Ke Xue , Rongfei Fan , Kai Li , Shanping Yu , Puning Zhao , Jianping An

Audio-driven cospeech video generation typically involves two stages: speech-to-gesture and gesture-to-video. While significant advances have been made in speech-to-gesture generation, synthesizing natural expressions and gestures remains…

Computer Vision and Pattern Recognition · Computer Science 2025-04-14 Renda Li , Xiaohua Qi , Qiang Ling , Jun Yu , Ziyi Chen , Peng Chang , Mei HanJing Xiao

Advancements in artificial intelligence and machine learning have significantly improved synthetic speech generation. This paper explores diffusion models, a novel method for creating realistic synthetic speech. We create a diffusion…

Cryptography and Security · Computer Science 2025-01-15 Anton Firc , Kamil Malinka , Petr Hanáček

Diffusion-based audio and music generation models commonly perform generation by constructing an image representation of audio (e.g., a mel-spectrogram) and then convert it to audio using a phase reconstruction model or vocoder. Typical…

Sound · Computer Science 2024-10-08 Ge Zhu , Juan-Pablo Caceres , Zhiyao Duan , Nicholas J. Bryan

Generating high-quality speech efficiently remains a key challenge for generative models in speech synthesis. This paper introduces VQalAttent, a lightweight model designed to generate fake speech with tunable performance and…

Machine Learning · Computer Science 2024-11-25 Armani Rodriguez , Silvija Kokalj-Filipovic

Audio Super-Resolution is a set of techniques aimed at high-quality estimation of the given signal as if it would be sampled with higher sample rate. Among suggested methods there are diffusion and flow models (which are considered slower),…

Sound · Computer Science 2026-03-05 Nikita Kuznetsov , Maksim Kaledin

In this paper, we present a vocoder-free framework for audio super-resolution that employs a flow matching generative model to capture the conditional distribution of complex-valued spectral coefficients. Unlike conventional two-stage…

Audio and Speech Processing · Electrical Eng. & Systems 2026-02-06 Woongjib Choi , Sangmin Lee , Hyungseob Lim , Hong-Goo Kang

In text-to-speech (TTS) and voice conversion (VC), acoustic features, such as mel spectrograms, are typically used as synthesis or conversion targets owing to their compactness and ease of learning. However, because the ultimate goal is to…

Sound · Computer Science 2025-08-28 Takuhiro Kaneko , Hirokazu Kameoka , Kou Tanaka , Yuto Kondo

We introduce the Latent Fourier Transform (LatentFT), a framework that provides novel frequency-domain controls for generative music models. LatentFT combines a diffusion autoencoder with a latent-space Fourier transform to separate musical…

Sound · Computer Science 2026-04-21 Mason Wang , Cheng-Zhi Anna Huang

We present a novel generative modeling framework,Wavelet-Fourier-Diffusion, which adapts the diffusion paradigm to hybrid frequency representations in order to synthesize high-quality, high-fidelity images with improved spatial…

Computer Vision and Pattern Recognition · Computer Science 2025-04-08 Andrew Kiruluta , Andreas Lemos

We introduce EffiFusion-GAN (Efficient Fusion Generative Adversarial Network), a lightweight yet powerful model for speech enhancement. The model integrates depthwise separable convolutions within a multi-scale block to capture diverse…

Sound · Computer Science 2025-08-21 Bin Wen , Tien-Ping Tan

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

Diffusion models have been shown to implicitly generate visual content autoregressively in the frequency domain, where low-frequency components are generated earlier in the denoising process while high-frequency details emerge only in later…

Computer Vision and Pattern Recognition · Computer Science 2026-05-21 Howard Xiao , Brian Chao , Lior Yariv , Gordon Wetzstein

We introduce MDSGen, a novel framework for vision-guided open-domain sound generation optimized for model parameter size, memory consumption, and inference speed. This framework incorporates two key innovations: (1) a redundant video…

Sound · Computer Science 2025-02-14 Trung X. Pham , Tri Ton , Chang D. Yoo