papers AI Learner
The Github is limit! Click to go to the new site.

Analysing Deep Learning-Spectral Envelope Prediction Methods for Singing Synthesis

2019-03-04
Frederik Bous, Axel Roebel

Abstract

We conduct an investigation on various hyper-parameters regarding neural networks used to generate spectral envelopes for singing synthesis. Two perceptive tests, where the first compares two models directly and the other ranks models with a mean opinion score, are performed. With these tests we show that when learning to predict spectral envelopes, 2d-convolutions are superior over previously proposed 1d-convolutions and that predicting multiple frames in an iterated fashion during training is superior over injecting noise to the input data. An experimental investigation whether learning to predict a probability distribution vs.\ single samples was performed but turned out to be inconclusive. A network architecture is proposed that incorporates the improvements which we found to be useful and we show in our experiments that this network produces better results than other stat-of-the-art methods.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1903.01161

PDF

http://arxiv.org/pdf/1903.01161


Comments

Content