Robust speech recognition technology for speech recorded and transmitted over
narrow-band channels requires advances in several components of a speech
recognition system: signal processing techniques that produce invariant
feature sets; acoustic modeling and training that produce channel-independent
acoustic models; noise cancellation techniques that mitigate the effects of
impulsive and application-dependent transient noise.
DARPA Communicator Server (v2.0): This release features some enhancements: n-best hypothesis support, capacity of receiving "GAL_BINARY" audio data, ability to compile on both Sparc and Pentium machines.
Multiple-CPU Eval Package (v1.0):
This package allows users to easily run complete experiments using multiple cpus.
Download the latest versions of our recognition software and resource
Access background information related to this project.
A quick look at the overall performance of the baseline system using a variety
of robust front ends.
Please direct questions or comments to