Real-time interactive sequence generation and control with Recurrent Neural Network ensembles

Recurrent Neural Networks (RNN), particularly Long Short Term Memory (LSTM) RNNs, are a popular and very successful method for learning and generating sequences. However, current generative RNN techniques do not allow real-time interactive control of the sequence generation process, thus aren't...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2017-02
Main Authors: Memo Akten, Grierson, Mick
Format: Article
Language:English
Subjects:
Interactive control
Neural networks
Real time
Recurrent neural networks
Short term
Steering
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Recurrent Neural Networks (RNN), particularly Long Short Term Memory (LSTM) RNNs, are a popular and very successful method for learning and generating sequences. However, current generative RNN techniques do not allow real-time interactive control of the sequence generation process, thus aren't well suited for live creative expression. We propose a method of real-time continuous control and 'steering' of sequence generation using an ensemble of RNNs and dynamically altering the mixture weights of the models. We demonstrate the method using character based LSTM networks and a gestural interface allowing users to 'conduct' the generation of text.
ISSN:2331-8422