English
Related papers

Related papers: Full-band General Audio Synthesis with Score-based…

200 papers

Diffusion autoencoders (DAs) are variants of diffusion generative models that use an input-dependent latent variable to capture representations alongside the diffusion process. These representations, to varying extents, can be used for…

Machine Learning · Computer Science 2025-06-03 Magdalena Proszewska , Nikolay Malkin , N. Siddharth

Existing NAS methods suffer from either an excessive amount of time for repetitive sampling and training of many task-irrelevant architectures. To tackle such limitations of existing NAS methods, we propose a paradigm shift from NAS to a…

Machine Learning · Computer Science 2024-03-26 Sohyun An , Hayeon Lee , Jaehyeong Jo , Seanie Lee , Sung Ju Hwang

Creating synthetic voices with found data is challenging, as real-world recordings often contain various types of audio degradation. One way to address this problem is to pre-enhance the speech with an enhancement model and then use the…

Audio and Speech Processing · Electrical Eng. & Systems 2023-10-03 Yusheng Tian , Wei Liu , Tan Lee

Vocal-to-accompaniment (V2A) generation, which aims to transform a raw vocal recording into a fully arranged accompaniment, inherently requires jointly addressing an accompaniment trilemma: preserving acoustic authenticity, maintaining…

Sound · Computer Science 2026-04-14 Qi Wang , Zhexu Shen , Meng Chen , Guoxin Yu , Chaoxu Pang , Weifeng Zhao , Wenjiang Zhou

Existing generative models for unsupervised anomalous sound detection are limited by their inability to fully capture the complex feature distribution of normal sounds, while the potential of powerful diffusion models in this domain remains…

Sound · Computer Science 2026-02-03 Chengyuan Ma , Peng Jia , Hongyue Guo , Wenming Yang

Large-scale multimodal generative modeling has created milestones in text-to-image and text-to-video generation. Its application to audio still lags behind for two main reasons: the lack of large-scale datasets with high-quality text-audio…

In this work, we propose a full-band real-time speech enhancement system with GAN-based stochastic regeneration. Predictive models focus on estimating the mean of the target distribution, whereas generative models aim to learn the full…

Audio and Speech Processing · Electrical Eng. & Systems 2025-05-30 Sanberk Serbest , Tijana Stojkovic , Milos Cernak , Andrew Harper

Developing generative models to create or conditionally create symbolic music presents unique challenges due to the combination of limited data availability and the need for high precision in note pitch. To address these challenges, we…

Sound · Computer Science 2025-06-09 Tingyu Zhu , Haoyu Liu , Ziyu Wang , Zhimin Jiang , Zeyu Zheng

We present Bit Diffusion: a simple and generic approach for generating discrete data with continuous state and continuous time diffusion models. The main idea behind our approach is to first represent the discrete data as binary bits, and…

Computer Vision and Pattern Recognition · Computer Science 2023-03-02 Ting Chen , Ruixiang Zhang , Geoffrey Hinton

Text-to-image diffusion models have achieved state-of-the-art results in synthesis tasks; however, there is a growing concern about their potential misuse in creating harmful content. To mitigate these risks, post-hoc model intervention…

Computer Vision and Pattern Recognition · Computer Science 2025-03-20 Feifei Li , Mi Zhang , Yiming Sun , Min Yang

In music-driven dance motion generation, most existing methods use hand-crafted features and neglect that music foundation models have profoundly impacted cross-modal content generation. To bridge this gap, we propose a diffusion-based…

Sound · Computer Science 2025-02-28 Xinran Liu , Zhenhua Feng , Diptesh Kanojia , Wenwu Wang

Spatial audio is a crucial component in creating immersive experiences. Traditional simulation-based approaches to generate spatial audio rely on expertise, have limited scalability, and assume independence between semantic and spatial…

Sound · Computer Science 2025-07-16 Saksham Singh Kushwaha , Jianbo Ma , Mark R. P. Thomas , Yapeng Tian , Avery Bruni

Diffusion-based generative models have had a high impact on the computer vision and speech processing communities these past years. Besides data generation tasks, they have also been employed for data restoration tasks like speech…

Audio and Speech Processing · Electrical Eng. & Systems 2023-03-17 Jean-Marie Lemercier , Julius Richter , Simon Welker , Timo Gerkmann

Multi-Source Diffusion Models (MSDM) allow for compositional musical generation tasks: generating a set of coherent sources, creating accompaniments, and performing source separation. Despite their versatility, they require estimating the…

Sound · Computer Science 2024-03-19 Emilian Postolache , Giorgio Mariani , Luca Cosmo , Emmanouil Benetos , Emanuele Rodolà

Current deep networks are very data-hungry and benefit from training on largescale datasets, which are often time-consuming to collect and annotate. By contrast, synthetic data can be generated infinitely using generative models such as…

Computer Vision and Pattern Recognition · Computer Science 2023-10-11 Weijia Wu , Yuzhong Zhao , Hao Chen , Yuchao Gu , Rui Zhao , Yefei He , Hong Zhou , Mike Zheng Shou , Chunhua Shen

With the advancement of audio generation, generative models can produce highly realistic audios. However, the proliferation of deepfake general audio can pose negative consequences. Therefore, we propose a new task, deepfake general audio…

Sound · Computer Science 2024-06-13 Zeyu Xie , Baihan Li , Xuenan Xu , Zheng Liang , Kai Yu , Mengyue Wu

Diffusion models have achieved remarkable success as generative models. However, even a well-trained model can accumulate errors throughout the generation process. These errors become particularly problematic when arbitrary guidance is…

Machine Learning · Computer Science 2025-10-14 Youngrok Park , Hojung Jung , Sangmin Bae , Se-Young Yun

Existing audio-text retrieval (ATR) methods are essentially discriminative models that aim to maximize the conditional likelihood, represented as p(candidates|query). Nevertheless, this methodology fails to consider the intrinsic data…

Sound · Computer Science 2024-10-18 Yifei Xin , Xuxin Cheng , Zhihong Zhu , Xusheng Yang , Yuexian Zou

We present a supervised learning framework of training generative models for density estimation. Generative models, including generative adversarial networks, normalizing flows, variational auto-encoders, are usually considered as…

Machine Learning · Computer Science 2023-10-24 Yanfang Liu , Minglei Yang , Zezhong Zhang , Feng Bao , Yanzhao Cao , Guannan Zhang

Compositional generalization requires models to produce novel configurations from familiar parts. In diffusion models, prior compositional generation methods typically assume that the relevant concepts or conditioning signals are already…

Machine Learning · Computer Science 2026-05-11 Zekun Wang , Anant Gupta , Tianyi Zhu , Christopher J. MacLellan