相关论文: Neural Wavetable: a playable wavetable synthesizer…

The reasonable definition of semantic interpretability presents the core challenge in explainable AI. This paper proposes a method to modify a traditional convolutional neural network (CNN) into an interpretable compositional CNN, in order…

We introduce the Differentiable Weightless Neural Network (DWN), a model based on interconnected lookup tables. Training of DWNs is enabled by a novel Extended Finite Difference technique for approximate differentiation of binary values. We…

Non-volatile Memory (NVM) technologies present a promising alternative to traditional volatile memories such as SRAM and DRAM. Due to the limited availability of real NVM devices, simulators play a crucial role in architectural exploration…

Neural networks have emerged as a tool for solving differential equations in many branches of engineering and science. But their progress in frequency domain acoustics is limited by the vanishing gradient problem that occurs at higher…

We propose Parallel WaveGAN, a distillation-free, fast, and small-footprint waveform generation method using a generative adversarial network. In the proposed method, a non-autoregressive WaveNet is trained by jointly optimizing…

We present the results of a combined experimental and numerical study of the generation of internal waves using the novel internal wave generator design of Gostiaux et al. (2007). This mechanism, which involves a tunable source comprised of…

An artificial neural-network-based subgrid-scale model using the resolved stress, which is capable of predicting untrained decaying isotropic turbulence, is developed. Providing the grid-scale strain-rate tensor alone as input leads the…

Recent promises of generative deep learning lately brought interest to its potential uses in neural engineering. In this paper we firstly review recently emerging studies on generating artificial electroencephalography (EEG) signals with…

Disruption Tolerant Networks (DTNs) are employed in applications where the network is likely to be disrupted due to environmental conditions or where the network topology makes it impossible to find a direct route from the sender to the…

We propose a novel type of a spin wave computing device, based on a bilayer structure which includes a bias layer, made from a hard magnetic material and a propagation layer, made from a magnetic material with low damping, for example,…

Recently, autoregressive neural vocoders have provided remarkable performance in generating high-fidelity speech and have been able to produce synthetic speech in real-time. However, autoregressive neural vocoders such as WaveFlow are…

A model of music needs to have the ability to recall past details and have a clear, coherent understanding of musical structure. Detailed in the paper is a neural network architecture that predicts and generates polyphonic music aligned…

In this paper we propose WaveGlow: a flow-based network capable of generating high quality speech from mel-spectrograms. WaveGlow combines insights from Glow and WaveNet in order to provide fast, efficient and high-quality audio synthesis,…

In this work, we introduce a novel deep learning architecture, Variable Length Embeddings (VLEs), an autoregressive model that can produce a latent representation composed of an arbitrary number of tokens. As a proof of concept, we…

This paper introduces an improved generative model for statistical parametric speech synthesis (SPSS) based on WaveNet under a multi-task learning framework. Different from the original WaveNet model, the proposed Multi-task WaveNet employs…

The hierarchy of integrable equations are considered. The dynamical approach to the theory of nonlinear waves is proposed. The special solutions(nonlinear waves) of considered equations are derived. We use powerful methods of computer…

Visual illusions are a very useful tool for vision scientists, because they allow them to better probe the limits, thresholds and errors of the visual system. In this work we introduce the first ever framework to generate novel visual…

Recent advances in neural network -based text-to-speech have reached human level naturalness in synthetic speech. The present sequence-to-sequence models can directly map text to mel-spectrogram acoustic features, which are convenient for…

Recent studies show the ability of unsupervised models to learn invertible audio representations using Auto-Encoders. They enable high-quality sound synthesis but a limited control since the latent spaces do not disentangle timbre…

The concurrent rise of artificial intelligence and quantum information poses opportunity for creating interdisciplinary technologies like quantum neural networks. Quantum reservoir processing, introduced here, is a platform for quantum…