A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Unsupervised learning of speech representations using WaveNet autoencoders.
How to model distribution of sequential data, including but not limited to speech and human motions, is an important ongoing research problem. It has been demonstrated that model capacity can be significantly enhanced by introducing stochastic latent variables in the hidden states of recurrent neural networks. Simultan…
NSF models generate speech waveforms faster and better than WaveNet.
Recent speech technology research has seen a growing interest in using WaveNets as statistical vocoders, i.e., generating speech waveforms from acoustic features. These models have been shown to improve the generated speech quality over classical vocoders in many tasks, such as text-to-speech synthesis and voice conver…
Solution for voice conversion with limited data using hierarchical seq2seq and attention models.
Recent progress in deep learning for audio synthesis opens the way to models that directly produce the waveform, shifting away from the traditional paradigm of relying on vocoders or MIDI synthesizers for speech or music generation. Despite their successes, current state-of-the-art neural audio synthesizers such as Wav…
We present a method for translating music across musical instruments, genres, and styles. This method is based on a multi-domain wavenet autoencoder, with a shared encoder and a disentangled latent space that is trained end-to-end on waveforms. Employing a diverse training dataset and large net capacity, the domain-ind…
Normalizing flows and autoregressive models have been successfully combined to produce state-of-the-art results in density estimation, via Masked Autoregressive Flows (MAF), and to accelerate state-of-the-art WaveNet-based speech synthesis to 20x faster than real-time, via Inverse Autoregressive Flows (IAF). We unify a…
Express Wavenet reduces neural network parameters to 1% of standard networks.
Neural network VQ-VAE with WaveNet decodes speech at 1.6 kbps with high quality.
Neural waveform models such as the WaveNet are used in many recent text-to-speech systems, but the original WaveNet is quite slow in waveform generation because of its autoregressive (AR) structure. Although faster non-AR models were recently reported, they may be prohibitively complicated due to the use of a distillin…
Joint training model for TTS and VC tasks using Tacotron and WaveNet.
The state-of-the-art in text-to-speech synthesis has recently improved considerably due to novel neural waveform generation methods, such as WaveNet. However, these methods suffer from their slow sequential inference process, while their parallel versions are difficult to train and even more expensive computationally. …
GANSynth uses GANs to efficiently synthesize high-fidelity audio.
Graph WaveNet models spatial-temporal graphs by learning hidden dependencies and long sequences.
Recent neural networks such as WaveNet and sampleRNN that learn directly from speech waveform samples have achieved very high-quality synthetic speech in terms of both naturalness and speaker similarity even in multi-speaker text-to-speech synthesis systems. Such neural networks are being used as an alternative to voco…
The superior temporal gyrus (STG) region of cortex critically contributes to speech recognition. In this work, we show that a proposed WaveNet, with limited available data, is able to reconstruct speech stimuli from STG intracranial recordings. We further investigate the impulse response of the fitted model for each re…
WaveCycleGAN2 improves speech synthesis quality by reducing aliasing.
The recent success of raw audio waveform synthesis models like WaveNet motivates a new approach for music synthesis, in which the entire process --- creating audio samples from a score and instrument information --- is modeled using generative neural networks. This paper describes a neural music synthesis model with fl…
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, without the need for auto-regression. WaveGlow is implemented using only a singl…
Recent advances in speech synthesis suggest that limitations such as the lossy nature of the amplitude spectrum with minimum phase approximation and the over-smoothing effect in acoustic modeling can be overcome by using advanced machine learning approaches. In this paper, we build a framework in which we can fairly co…
New findings on how convolutional architectures approximate time series data.
We present a meta-learning approach for adaptive text-to-speech (TTS) with few data. During training, we learn a multi-speaker model using a shared conditional WaveNet core and independent learned embeddings for each speaker. The aim of training is not to produce a neural network with fixed weights, which is then deplo…
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 prevalent approach; these models can capture long-range dependencies of melodic st…
In this work, we address the problem of musical timbre transfer, where the goal is to manipulate the timbre of a sound sample from one instrument to match another instrument while preserving other musical content, such as pitch, rhythm, and loudness. In principle, one could apply image-based style transfer techniques t…
Improved audio classification with limited labels using multitask and self-supervised learning.
Activates speech DNNs to generate understandable examples.
This research improves neural synthesizers for music sounds from speech data.
trVAE improves conditional out-of-sample generation for unpaired data.
Seq-U-Net improves sequence modeling efficiency with dilated U-Net.
Convolutional autoregressive models have recently demonstrated state-of-the-art performance on a number of generation tasks. While fast, parallel training methods have been crucial for their success, generation is typically implemented in a naïve fashion where redundant computations are unnecessarily repeated. This res…
Universal audio perturbations fool ASR systems.
New autoencoder framework learns structured latent priors.
Variational autoencoders learn deep latent models.
Feature extraction becomes increasingly important as data grows high dimensional. Autoencoder as a neural network based feature extraction method achieves great success in generating abstract features of high dimensional data. However, it fails to consider the relationships of data samples which may affect experimental…
Autoencoders compress and reconstruct data for various applications.
Proposes a Bayesian Autoencoder with sparse Gaussian process priors to capture data correlations.
Study on dynamics of non-linear autoencoders learning principal components.
Chart autoencoders learn latent features preserving manifold topology and geometry, with robust denoising capabilities.
POTATOES improves autoencoder UOD accuracy without tuning.
InfoMax Autoencoder maximizes mutual information for robust data representation.
In this paper we propose a Deep Autoencoder MIxture Clustering (DAMIC) algorithm based on a mixture of deep autoencoders where each cluster is represented by an autoencoder. A clustering network transforms the data into another space and then selects one of the clusters. Next, the autoencoder associated with this clust…
New autoencoder generates better images by estimating latent distribution.
AEGCN uses autoencoder constraints to improve graph node classification.
BAE uses boosting to improve autoencoder ensembles for robust outlier detection.
GE-autoencoder identifies spontaneous symmetry breaking in systems.
Regularization preserves topological data structure in autoencoders.
A new autoencoder method uses empirical beta copulas for generating data.