Slashdot Mirror
Open Source Speech Recognition - With Source
Paul Lamere writes " This story
on ZD-Net and this recent story
on Slashdot
describes the recent open sourcing of IBM's voice
recognition software. This release, unfortunately, doesn't include
any source for the actual speech recognition engine. Olaf Schmidt, a
developer on the KDE Accessibility Project ,
is quoted as saying 'There is no speech-recognition system available
for Linux, which is a big gap.' In an attempt to close this gap, we
have just released Sphinx-4,
a state-of-the-art, speaker-independent, continuous
speech recognition system written entirely in the Java programming
language. It was created by researchers and engineers from Sun, CMU,
MERL, HP, MIT and UCSC. Despite (or because of) being written in the
Java programming language, Sphinx-4 performs as well as similar
systems written in C. Here are the release notes and
some performance data."
"Despite (or because of) being written in the Java programming language, Sphinx-4 performs as well as similar systems written in C"
It's amazing that the myth of Java being slow is so persistant. In fact, for computational tasks, many benchmarks have shown that a modern optimized JVM with JIT compilation is roughly equivalent with most implementations of C++, with some benchmarks being better for Java and some being better for C++.
Java *used* to be slow, in the days before optimized JIT JVMs. IMHO, another reason the myth persists is because Swing *is* slower than most UI toolkits in many cases, and it's easy to associate GUI slowness with overall slowness.
In my own case, for ease of cross-platform operation, I've ported several computationally intensive image processing programs from C to Java and have experienced a speed degradation of perhaps 10-15%. The Swing GUI, of course, feels more than 10-15% slower.