The workshop

Generating audio based on tweets!

In this workshop, we'll look at unique ways to create generative projects with text, including extracting emotion from text and using text to generate music & audio. We'll examine standard tools, such as Python's Natural Language Toolkit (NLTK), as well as other APIs. We'll briefly talk about creating/curating text datasets and about the idea of "subjective datasets," and what that means for our practice. Hannah will show her work on using the texts of novels, debates, news articles, and country constitutions as inputs to generate music. The output of the workshop will be a Twitter bot that reads tweets and generates audio based on the grammatical structure of the tweet. This workshop will be conducted in Python, and will go at a pace suitable for beginner programmers.

Learn more about

closed - Hannah Davis

Practical informations

04 Nov

Sat., 2:00 - 4:00 - Place d'Armes

Hannah Davis is a programmer, generative musician, and data scientist from NYC. Her work falls along the lines of music generation, data visualization/sonification/analysis, natural language processing, machine learning, and storytelling in various formats. Her work on generative music - particularly her algorithm TransProse, which translates novels and other large works of text into music - has been written up in TIME, Popular Science, Wired, and others. A human-computer collaboration, where she analyzed the sentiment of articles talking about technology over time, was performed by an orchestra at The Louvre this past fall. Hannah is currently working on creating unique datasets for art and machine learning, and is also working on a project to generatively score films.