English
Related papers

Related papers: It's Raw! Audio Generation with State-Space Models

200 papers

Audio super-resolution is the task of constructing a high-resolution (HR) audio from a low-resolution (LR) audio by adding the missing band. Previous methods based on convolutional neural networks and mean squared error training objective…

Sound · Computer Science 2021-06-17 Kexun Zhang , Yi Ren , Changliang Xu , Zhou Zhao

Symbolic music generation is a challenging task in multimedia generation, involving long sequences with hierarchical temporal structures, long-range dependencies, and fine-grained local details. Though recent diffusion-based models produce…

The generation of room impulse responses (RIRs) using deep neural networks has attracted growing research interest due to its applications in virtual and augmented reality, audio postproduction, and related fields. Most existing approaches…

Sound · Computer Science 2025-07-17 Silvia Arellano , Chunghsin Yeh , Gautam Bhattacharya , Daniel Arteaga

Large language models show that simple autoregressive training can yield scalable and coherent generation, but extending this paradigm to speech remains challenging due to the entanglement of semantic and acoustic information. Most existing…

Machine Learning · Computer Science 2026-03-06 Luca Della Libera , Cem Subakan , Mirco Ravanelli

Models for audio generation are typically trained on hours of recordings. Here, we illustrate that capturing the essence of an audio source is typically possible from as little as a few tens of seconds from a single training signal.…

Sound · Computer Science 2021-10-27 Gal Greshler , Tamar Rott Shaham , Tomer Michaeli

Recently, diffusion models have achieved great success in mono-channel audio generation. However, when it comes to stereo audio generation, the soundscapes often have a complex scene of multiple objects and directions. Controlling stereo…

Sound · Computer Science 2025-02-26 Peiwen Sun , Sitong Cheng , Xiangtai Li , Zhen Ye , Huadai Liu , Honggang Zhang , Wei Xue , Yike Guo

Speech representation and modelling in high-dimensional spaces of acoustic waveforms, or a linear transformation thereof, is investigated with the aim of improving the robustness of automatic speech recognition to additive noise. The…

Computation and Language · Computer Science 2015-03-31 Matthew Ager , Zoran Cvetkovic , Peter Sollich

We introduce a new system for data-driven audio sound model design built around two different neural network architectures, a Generative Adversarial Network(GAN) and a Recurrent Neural Network (RNN), that takes advantage of the unique…

Sound · Computer Science 2022-06-28 Lonce Wyse , Purnima Kamath , Chitralekha Gupta

Far-field speech recognition in noisy and reverberant conditions remains a challenging problem despite recent deep learning breakthroughs. This problem is commonly addressed by acquiring a speech signal from multiple microphones and…

Audio and Speech Processing · Electrical Eng. & Systems 2018-10-17 Zhong Meng , Shinji Watanabe , John R. Hershey , Hakan Erdogan

Autoregressive (AR) diffusion enables streaming, interactive long-video generation by producing frames causally, yet maintaining coherence over minute-scale horizons remains challenging due to accumulated errors, motion drift, and content…

Computer Vision and Pattern Recognition · Computer Science 2025-12-05 Yifei Yu , Xiaoshan Wu , Xinting Hu , Tao Hu , Yangtian Sun , Xiaoyang Lyu , Bo Wang , Lin Ma , Yuewen Ma , Zhongrui Wang , Xiaojuan Qi

Despite its widespread adoption as the prominent neural architecture, the Transformer has spurred several independent lines of work to address its limitations. One such approach is selective state space models, which have demonstrated…

Sound · Computer Science 2024-06-11 Sarthak Yadav , Zheng-Hua Tan

Real-time magnetic resonance imaging (rtMRI) of speech production enables non-invasive visualization of dynamic vocal-tract motion and is valuable for speech science and clinical assessment. However, rtMRI is fundamentally constrained by…

Audio super-resolution (SR), i.e., upsampling the low-resolution (LR) waveform to the high-resolution (HR) version, has recently been explored with diffusion and bridge models, while previous methods often suffer from sub-optimal upsampling…

Sound · Computer Science 2026-01-01 Chang Li , Zehua Chen , Liyuan Wang , Jun Zhu

In this paper, we compare different audio signal representations, including the raw audio waveform and a variety of time-frequency representations, for the task of audio synthesis with Generative Adversarial Networks (GANs). We conduct the…

Audio and Speech Processing · Electrical Eng. & Systems 2020-06-18 Javier Nistal , Stefan Lattner , Gaël Richard

Recent progress in diffusion-based audio generation and restoration has substantially improved performance across heterogeneous conditioning regimes, including text-conditioned audio generation and audio-conditioned super-resolution.…

Sound · Computer Science 2026-05-07 Xuanhao Zhang , Chang Li

Time series modeling is a well-established problem, which often requires that methods (1) expressively represent complicated dependencies, (2) forecast long horizons, and (3) efficiently train over long sequences. State-space models (SSMs)…

Machine Learning · Computer Science 2023-03-17 Michael Zhang , Khaled K. Saab , Michael Poli , Tri Dao , Karan Goel , Christopher Ré

Recent work has shown that recurrent neural networks can be trained to separate individual speakers in a sound mixture with high fidelity. Here we explore convolutional neural network models as an alternative and show that they achieve…

Sound · Computer Science 2018-05-29 Shariq Mobin , Brian Cheung , Bruno Olshausen

Sound modelling is the process of developing algorithms that generate sound under parametric control. There are a few distinct approaches that have been developed historically including modelling the physics of sound production and…

Audio and Speech Processing · Electrical Eng. & Systems 2020-11-26 M. Huzaifah , L. Wyse

One key step in audio signal processing is to transform the raw signal into representations that are efficient for encoding the original information. Traditionally, people transform the audio into spectral representations, as a function of…

Sound · Computer Science 2016-11-30 Shuhui Qu , Juncheng Li , Wei Dai , Samarjit Das

We introduce MAGNeT, a masked generative sequence modeling method that operates directly over several streams of audio tokens. Unlike prior work, MAGNeT is comprised of a single-stage, non-autoregressive transformer. During training, we…