Category Archives: Speech recognition

speechdecode – speech decoding based on CMU Sphinx for rtndf data flow pipelines

speechdecode¬†is a new PPE based on CMU Sphinx can be added to an rtndf data flow pipeline to decode speech in an audio stream. It’s the first PPE written in C++ and the infrastructure will be used for PPEs that are a bit too heavy to work well in Python or integrate better with C and C++ libraries.

A simple pipeline is:

audio -> speechdecode

speechdecode outputs any recognized phrases in the stream. It is possible to use customized sets of phrases to limit the the range of speech recognized to key phrases and commands.