October 2018
Intermediate to advanced
472 pages
10h 57m
English
We dove right into this deep-learning project in Python, creating and training an ASR model that understands speech data. We learned to feature engineer the speech data to extract various kinds of features from it and then build a speech recognition system that could detect a user's voice.
We're happy to have achieved our stated goal!
In this chapter, we built a system that recognizes English speech, using the DS2 model.
You learned following:
This caps off a major section of the deep-learning projects in this Python book that explores chatbots, NLP, and speech recognition with RNNs ...
Read now
Unlock full access