Related papers: Wavespace: A Highly Explorable Wavetable Generator

Generative AI models for music and the arts in general are increasingly complex and hard to understand. The field of eXplainable AI (XAI) seeks to make complex and opaque AI models such as neural networks more understandable to people. One…

Evolving software is challenging, even more when it exists in many different variants. Such software evolves not only in time, but also in space--another dimension of complexity. While evolution in space is supported by a variety of…

Generative modeling aims at producing new datapoints whose statistical properties resemble the ones in a training dataset. In recent years, there has been a burst of machine learning techniques and settings that can achieve this goal with…

State-of-the-art statistical parametric speech synthesis (SPSS) generally uses a vocoder to represent speech signals and parameterize them into features for subsequent modeling. Magnitude spectrum has been a dominant feature over the years.…

While proprietary systems such as Seedance-2.0 have achieved remarkable success in omni-capable video generation, open-source alternatives significantly lag behind. Most academic models remain heavily fragmented, and the few existing…

Here we show that there exist internal gravity waves that are inherently unstable, that is, they cannot exist in nature for a long time. The instability mechanism is a one-way (irreversible) harmonic-generation resonance that permanently…

We present a VAE architecture for encoding and generating high dimensional sequential data, such as video or audio. Our deep generative model learns a latent representation of the data which is split into a static and dynamic part, allowing…

The present work proposes an inflow turbulence generation strategy using deep learning methods. This is achieved with the help of an autoencoder architecture with two different types of operational layers in the latent-space: a fully…

Metamaterials can enable peculiar static and dynamic behavior (such as negative effective mass density, dynamical stiffness, and Poisson's ratio) due to their geometry rather than their chemical composition. The geometry of these…

In this paper we explore techniques for generating new music using a Variational Autoencoder (VAE) neural network that was trained on a corpus of specific style. Instead of randomly sampling the latent states of the network to produce free…

An ability to model a generative process and learn a latent representation for speech in an unsupervised fashion will be crucial to process vast quantities of unlabelled speech data. Recently, deep probabilistic generative models such as…

We investigate the feasibility of a singing voice synthesis (SVS) system by using a decomposed framework to improve flexibility in generating singing voices. Due to data-driven approaches, SVS performs a music score-to-waveform mapping;…

To date, axisymmetric internal wave fields, which have relevance to atmospheric internal wave fields generated by storm cells and oceanic near-inertial wave fields generated by surface storms, have been experimentally realized using an…

We introduce InspireMusic, a framework integrated super resolution and large language model for high-fidelity long-form music generation. A unified framework generates high-fidelity music, songs, and audio, which incorporates an…

The recent success in StyleGAN demonstrates that pre-trained StyleGAN latent space is useful for realistic video generation. However, the generated motion in the video is usually not semantically meaningful due to the difficulty of…

Consider a movie studio aiming to produce a set of new movies for summer release: What types of movies it should produce? Who would the movies appeal to? How many movies should it make? Similar issues are encountered by a variety of…

To date, various speech technology systems have adopted the vocoder approach, a method for synthesizing speech waveform that shows a major role in the performance of statistical parametric speech synthesis. WaveNet one of the best models…

We construct few deep generative models of gravitational waveforms based on the semi-supervising scheme of conditional autoencoders and their variational extensions. Once the training is done, we find that our best waveform model can…

Developing algorithms for sound classification, detection, and localization requires large amounts of flexible and realistic audio data, especially when leveraging modern machine learning and beamforming techniques. However, most existing…

Generating synthetic tabular data under severe class imbalance is essential for domains where rare but high-impact events drive decision-making. However, most generative models either overlook minority groups or fail to produce samples that…