DeepAI AI Chat
Log In Sign Up

Weakly Supervised Deep Recurrent Neural Networks for Basic Dance Step Generation

by   Nelson Yalta, et al.

A deep recurrent neural network with audio input is applied to model basic dance steps. The proposed model employs multilayered Long Short-Term Memory (LSTM) layers and convolutional layers to process the audio power spectrum. Then, another deep LSTM layer decodes the target dance sequence. This end-to-end approach has an auto-conditioned decode configuration that reduces accumulation of feedback error. Experimental results demonstrate that, after training using a small dataset, the model generates basic dance steps with low cross entropy and maintains a motion beat F-measure score similar to that of a baseline dancer. In addition, we investigate the use of a contrastive cost function for music-motion regulation. This cost function targets motion direction and maps similarities between music frames. Experimental result demonstrate that the cost function improves the motion beat f-score.


page 1

page 2

page 3

page 4


Bach in 2014: Music Composition with Recurrent Neural Network

We propose a framework for computer music composition that uses resilien...

Multi-Language Identification Using Convolutional Recurrent Neural Network

Language Identification, being an important aspect of Automatic Speaker ...

Music Generation Using an LSTM

Over the past several years, deep learning for sequence modeling has gro...

Dance Dance Convolution

Dance Dance Revolution (DDR) is a popular rhythm-based video game. Playe...

A holistic approach to polyphonic music transcription with neural networks

We present a framework based on neural networks to extract music scores ...

Deep Learning Scooping Motion using Bilateral Teleoperations

We present bilateral teleoperation system for task learning and robot mo...

Direct detection of pixel-level myocardial infarction areas via a deep-learning algorithm

Accurate detection of the myocardial infarction (MI) area is crucial for...

Code Repositories


Sequential Learning for Dance generation

view repo