Fact · Voice and AI
The PocketSphinx project says its algorithms and models are quite old, dating back to the 1970s in some cases, and that they remain useful because they are compact and efficient.
Checked against its source on October 17, 2026
In the source's own words
“Though the algorithms and models implemented by PocketSphinx are now quite old (dating back to the 1970s in some cases!) they are still useful in many applications due to their compactness and efficiency.”
PocketSphinx README (raw text, version 5.1.1), CMU Sphinx project, n.d., Introduction.
Open the original- What it measures
- PocketSphinx is an open-source speech recognition library from Carnegie Mellon University that runs on the user's own computer.
- What it does not show
- The introduction gives no accuracy figure, so the age of the models says nothing about how accurate they are compared with neural recognizers.