Robust word spotting in adverse car environments

This paper presents a novel word recognition technique which allows hand-free dialing under adverse car environments. The algorithm is based on speaker dependent word spotting. The paper compared and investigated the methods of spectral subtraction, short time modi ed coherence, multi-microphone, dynamic and accelerated features, weighted distance measures and multi-templates by word recognition experiments. The experiments are carried out using real speech database uttered in adverse car environments. The experiments show that the method using sinusoidal weighted lifter and the method using multi-templates are robust against the adverse environments.