English
Related papers

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

200 papers

Flow matching offers a robust and stable approach to training diffusion models. However, directly applying flow matching to neural vocoders can result in subpar audio quality. In this work, we present WaveFM, a reparameterized flow matching…

Sound · Computer Science 2025-03-24 Tianze Luo , Xingchen Miao , Wenbo Duan

High-quality audio is essential in a wide range of applications, including online communication, virtual assistants, and the multimedia industry. However, degradation caused by noise, compression, and transmission artifacts remains a major…

High-resolution image synthesis remains a core challenge in generative modeling, particularly in balancing computational efficiency with the preservation of fine-grained visual detail. We present Latent Wavelet Diffusion (LWD), a…

Computer Vision and Pattern Recognition · Computer Science 2026-04-17 Luigi Sigillo , Shengfeng He , Danilo Comminiello

While diffusion-based generative models have made significant strides in visual content creation, conventional approaches face computational challenges, especially for high-resolution images, as they denoise the entire image from noisy…

Computer Vision and Pattern Recognition · Computer Science 2025-07-01 Haohang Xu , Longyu Chen , Yichen Zhang , Shuangrui Ding , Zhipeng Zhang

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 probability models have shown significant promise in offline reinforcement learning by directly modeling trajectory sequences. However, existing approaches primarily focus on time-domain features while overlooking frequency-domain…

Machine Learning · Computer Science 2025-09-25 Yifu Luo , Yongzhe Chang , Xueqian Wang

This Ph.D. thesis focuses on developing a system for high-quality speech synthesis and voice conversion. Vocoder-based speech analysis, manipulation, and synthesis plays a crucial role in various kinds of statistical parametric speech…

Sound · Computer Science 2021-01-26 Mohammed Salah Al-Radhi

Latent diffusion has become the default paradigm for visual generation, yet we observe a persistent reconstruction-generation trade-off as latent dimensionality increases: higher-capacity autoencoders improve reconstruction fidelity but…

Computer Vision and Pattern Recognition · Computer Science 2025-12-01 Bolin Lai , Xudong Wang , Saketh Rambhatla , James M. Rehg , Zsolt Kira , Rohit Girdhar , Ishan Misra

This paper introduces a discrete diffusion model (DDM) framework for text-aligned speech tokenization and reconstruction. By replacing the auto-regressive speech decoder with a discrete diffusion counterpart, our model achieves…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-25 Pin-Jui Ku , He Huang , Jean-Marie Lemercier , Subham Sekhar Sahoo , Zhehuai Chen , Ante Jukić

Nowadays more and more applications can benefit from edge-based text-to-speech (TTS). However, most existing TTS models are too computationally expensive and are not flexible enough to be deployed on the diverse variety of edge devices with…

Sound · Computer Science 2020-11-30 Bichen Wu , Qing He , Peizhao Zhang , Thilo Koehler , Kurt Keutzer , Peter Vajda

Recent advancements in music generation have garnered significant attention, yet existing approaches face critical limitations. Some current generative models can only synthesize either the vocal track or the accompaniment track. While some…

Audio and Speech Processing · Electrical Eng. & Systems 2025-03-04 Ziqian Ning , Huakang Chen , Yuepeng Jiang , Chunbo Hao , Guobin Ma , Shuai Wang , Jixun Yao , Lei Xie

Latent diffusion models (LDMs) have achieved remarkable success in a variety of image tasks, yet achieving fine-grained, disentangled control over global structures versus fine details remains challenging. This paper explores…

Computer Vision and Pattern Recognition · Computer Science 2025-05-30 Chao Huang , Susan Liang , Yunlong Tang , Jing Bi , Li Ma , Yapeng Tian , Chenliang Xu

Most state-of-the-art Text-to-Speech systems use the mel-spectrogram as an intermediate representation, to decompose the task into acoustic modelling and waveform generation. A mel-spectrogram is extracted from the waveform by a simple,…

Recent advancements in generative modeling have significantly enhanced the reconstruction of audio waveforms from various representations. While diffusion models are adept at this task, they are hindered by latency issues due to their…

Sound · Computer Science 2024-10-08 Peng Liu , Dongyang Dai , Zhiyong Wu

Neural vocoder using denoising diffusion probabilistic model (DDPM) has been improved by adaptation of the diffusion noise distribution to given acoustic features. In this study, we propose SpecGrad that adapts the diffusion noise so that…

Audio and Speech Processing · Electrical Eng. & Systems 2022-08-08 Yuma Koizumi , Heiga Zen , Kohei Yatabe , Nanxin Chen , Michiel Bacchiani

Automatic speech synthesis is a challenging task that is becoming increasingly important as edge devices begin to interact with users through speech. Typical text-to-speech pipelines include a vocoder, which translates intermediate audio…

Sound · Computer Science 2020-01-17 Bohan Zhai , Tianren Gao , Flora Xue , Daniel Rothchild , Bichen Wu , Joseph E. Gonzalez , Kurt Keutzer

This paper introduces WaveGrad 2, a non-autoregressive generative model for text-to-speech synthesis. WaveGrad 2 is trained to estimate the gradient of the log conditional density of the waveform given a phoneme sequence. The model takes an…

Audio and Speech Processing · Electrical Eng. & Systems 2021-06-22 Nanxin Chen , Yu Zhang , Heiga Zen , Ron J. Weiss , Mohammad Norouzi , Najim Dehak , William Chan

Recently, GAN based speech synthesis methods, such as MelGAN, have become very popular. Compared to conventional autoregressive based methods, parallel structures based generators make waveform generation process fast and stable. However,…

Audio and Speech Processing · Electrical Eng. & Systems 2020-11-25 Qiao Tian , Yi Chen , Zewang Zhang , Heng Lu , Linghui Chen , Lei Xie , Shan Liu

Extracting individual elements from music mixtures is a valuable tool for music production and practice. While neural networks optimized to mask or transform mixture spectrograms into the individual source(s) have been the leading approach,…

Sound · Computer Science 2025-11-26 Genís Plaja-Roglans , Yun-Ning Hung , Xavier Serra , Igor Pereira

In recent years, with the realistic generation results and a wide range of personalized applications, diffusion-based generative models gain huge attention in both visual and audio generation areas. Compared to the considerable advancements…

Computer Vision and Pattern Recognition · Computer Science 2024-05-27 Shiqi Yang , Zhi Zhong , Mengjie Zhao , Shusuke Takahashi , Masato Ishii , Takashi Shibuya , Yuki Mitsufuji