Home
Why Mobile?
Mobile Speech Recognizer
Persuasive Health Information
Mobile Language Learning

Berkeley Institute of Design

Mobile Speech Recognizer

We have ported CMU's Sphinx-3.X open-source recognizer for large-vocabulary continuous speech recognition to both the Windows Mobile and Linux platform.  We are using a fixed-point MFCC front-end, and have accelerated parts of the Gaussian evaluation in assembly. This significantly increases the recognizer's performance such that it can run in real-time or near it on Windows mobile smartphones and Linux mobile devices. 

To learn more or to download the system visit the SphinxTiny project

Divya Ramachandran
divya At eecs.berkeley.edu

Matthew Kam
mattkam At eecs.berkeley.edu

John Canny
jfc At eecs.berkeley.edu

Seth Horrigan
eomer At cs.berkeley.edu