SampleRNN: An Unconditional End-to-End Neural Audio Generation Model

Autor:	Mehri, Soroush, Kumar, Kundan, Gulrajani, Ishaan, Kumar, Rithesh, Jain, Shubham, Sotelo, Jose, Courville, Aaron, Bengio, Yoshua
Rok vydání:	2016
Předmět:	Computer Science - Sound Computer Science - Artificial Intelligence
Druh dokumentu:	Working Paper
Popis:	In this paper we propose a novel model for unconditional audio generation based on generating one audio sample at a time. We show that our model, which profits from combining memory-less modules, namely autoregressive multilayer perceptrons, and stateful recurrent neural networks in a hierarchical structure is able to capture underlying sources of variations in the temporal sequences over very long time spans, on three datasets of different nature. Human evaluation on the generated samples indicate that our model is preferred over competing models. We also show how each component of the model contributes to the exhibited performance. Comment: Published as a conference paper at ICLR 2017
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1612.07837 Zobrazit plný text záznamu View this record from Arxiv