Recent advances in deep learning research, such as transformers, have
bo...
Electronic music artists and sound designers have unique workflow practi...
We describe a real-time system that receives a live audio stream from a ...
This paper envisions a multi-agent system for detecting the presence of ...
We present a system for generating novel lyrics lines conditioned on mus...
We present a novel iterative, edit-based approach to unsupervised senten...
Automatic sentence summarization produces a shorter version of a sentenc...
Learning disentangled representations of real world data is a challengin...
Wasserstein autoencoders are effective for text generation. They do not
...
Effective fusion of data from multiple modalities, such as video, speech...
Generating relevant/conditioned responses in dialog is challenging, and
...
Variational auto-encoders (VAEs) are widely used in natural language
gen...
In the natural language processing literature, neural networks are becom...
We present a system for generating song lyrics lines conditioned on the ...
This paper tackles the problem of disentangling the latent variables of ...
Probabilistic generation of natural language sentences is an important t...
The variational encoder-decoder (VED) encodes source information as a se...
This paper discusses the approach taken by the UWaterloo team to arrive ...