The Old Way: An Acoustic Model, a Pronunciation Model, and a Language Model are the old-fashioned way of doing speech recognition. The old way of building speech recognition models is intuitive to humans and is motivated to some extent by how linguists think about language, it’s highly lossy to engineers. The old method is brittle because the models lack expressiveness and capacity.
Table of contents
The Old Way: An Acoustic Model, a Pronunciation Model, and a Language Model—Oh my!The best way: End-to-end deep learning for speech recognitionConclusion2 Impressions