Talking Drums: Generating drum grooves with neural networks

06/29/2017
by   P. Hutchings, et al.
0

Presented is a method of generating a full drum kit part for a provided kick-drum sequence. A sequence to sequence neural network model used in natural language translation was adopted to encode multiple musical styles and an online survey was developed to test different techniques for sampling the output of the softmax function. The strongest results were found using a sampling technique that drew from the three most probable outputs at each subdivision of the drum pattern but the consistency of output was found to be heavily dependent on style.

READ FULL TEXT
research
03/05/2017

Neural Machine Translation and Sequence-to-sequence Models: A Tutorial

This tutorial introduces a new and powerful set of techniques variously ...
research
07/09/2019

Sequence-to-Sequence Natural Language to Humanoid Robot Sign Language

This paper presents a study on natural language to sign language transla...
research
05/14/2019

Sparse Sequence-to-Sequence Models

Sequence-to-sequence models are a powerful workhorse of NLP. Most varian...
research
05/01/2017

Efficient Natural Language Response Suggestion for Smart Reply

This paper presents a computationally efficient machine-learned method f...
research
12/10/2018

Von Mises-Fisher Loss for Training Sequence to Sequence Models with Continuous Outputs

The Softmax function is used in the final layer of nearly all existing s...
research
06/18/2020

Adversarially Trained Multi-Singer Sequence-To-Sequence Singing Synthesizer

This paper presents a high quality singing synthesizer that is able to m...
research
08/18/2023

Exploring Sampling Techniques for Generating Melodies with a Transformer Language Model

Research in natural language processing has demonstrated that the qualit...

Please sign up or login with your details

Forgot password? Click here to reset