Related papers: Source coding of audio signals with a generative m…
There has been fascinating work on creating artistic transformations of images by Gatys. This was revolutionary in how we can in some sense alter the 'style' of an image while generally preserving its 'content'. In our work, we present a…
This paper reports on recent results related to audiophonic signals encoding using time-scale and time-frequency transform. More precisely, non-linear, structured approximations for tonal and transient components using local cosine and…
We present a scalable and efficient neural waveform coding system for speech compression. We formulate the speech coding problem as an autoencoding task, where a convolutional neural network (CNN) performs encoding and decoding as a neural…
Deep generative modeling of natural languages has achieved many successes, such as producing fluent sentences and translating from one language into another. However, the development of generative modeling techniques for paraphrase…
In this work, we propose a symbolic music generation model with the song structure graph analysis network. We construct a graph that uses information such as note sequence and instrument as node features, while the correlation between note…
This paper investigates the use of generative adversarial network (GAN)-based models for converting the spectrogram of a speech signal into that of a singing one, without reference to the phoneme sequence underlying the speech. This is…
A sound source was proposed for acoustic measurements of physical models of the human vocal tract. The physical models are produced by Fast Prototyping, based on Magnetic Resonance Imaging during prolonged vowel production. The sound…
Code generation maps a program description to executable source code in a programming language. Existing approaches mainly rely on a recurrent neural network (RNN) as the decoder. However, we find that a program contains significantly more…
Neural autoencoders underpin generative models. Practical, large-scale use of neural autoencoders for generative modeling necessitates fast encoding, low latent rates, and a single model across representations. Existing approaches are…
The energy bottleneck in Wireless Sensor Network(WSN) can be reduced by limiting communication overhead. Application specific source coding schemes for the sensor networks provide fewer bits to represent the same amount of information…
This paper introduces WaveGrad, a conditional model for waveform generation which estimates gradients of the data density. The model is built on prior work on score matching and diffusion probabilistic models. It starts from a Gaussian…
Quantum random number generators can provide genuine randomness by appealing to the fundamental principles of quantum mechanics. In general, a physical generator contains two parts---a randomness source and its readout. The source is…
Modeling long-term dependencies for audio signals is a particularly challenging problem, as even small-time scales yield on the order of a hundred thousand samples. With the recent advent of Transformers, neural architectures became good at…
We define salient features as features that are shared by signals that are defined as being equivalent by a system designer. The definition allows the designer to contribute qualitative information. We aim to find salient features that are…
I developed a neural audio codec model based on the residual quantized variational autoencoder architecture. I train the model on the Slakh2100 dataset, a standard dataset for musical source separation, composed of multi-track audio. The…
Recently, audio-visual separation approaches have taken advantage of the natural synchronization between the two modalities to boost audio source separation performance. They extracted high-level semantics from visual inputs as the guidance…
Existing automatic music generation approaches that feature deep learning can be broadly classified into two types: raw audio models and symbolic models. Symbolic models, which train and generate at the note level, are currently the more…
There are several approaches for encoding source code in the input vectors of neural models. These approaches attempt to include various syntactic and semantic features of input programs in their encoding. In this paper, we investigate…
Modern audio generation predominantly relies on latent-space compression, introducing additional complexity and potential information loss. In this work, we challenge this paradigm with WavFlow, a framework that generates high-fidelity…
We propose Composition Sampling, a simple but effective method to generate diverse outputs for conditional generation of higher quality compared to previous stochastic decoding strategies. It builds on recently proposed plan-based neural…