TEAM

Holst

Jonathan Doane, Joanne Dong

clear.png

The goal of this project was to work with audio clips of human speech and accurately count the number of words in the recording by splitting the audio clip based one the number of silences. We extracted audio features from the recordings. Jonathan created a model that predicts the word count based on these audio features. Joanne created a model that predicts the word count based on demographic information of the speaker.

Screen Shot 2022-06-03 at 11.31.35 AM.png
github URL