Abstract: A code generation program is provided that reads in the task-specific parameters of a speech recognition system and produces a source-language decoder program that is specialized to these parameters. The decoder program is then compiled and distributed. The process of profile-driven code optimization may be used to further enhance the output program. For ease of distribution, the system may be compiled in several parts, and assembled (linked) later, for example through the mechanism of dynamically loaded libraries.

Abstract: A trainable radio scanner, including a station monitoring circuit to scan a plurality of radio frequencies and extract audio samples of a predetermined duration from each one of the plurality of radio frequencies having a signal strength above a reception threshold; a memory storing audio classification data and the plurality of audio samples; and an audio analyzer to analyze each one of the plurality of audio samples using the audio classification data and classifies each audio sample into a musical style category; a style discriminator to control a radio station scanning operation of the radio receiver to tune only to preferred radio stations having a radio frequency at which the corresponding audio sample is classified in at least one preferred musical style category.