Automatic speech recognition performance for training on noised speech

Performances of some training techniques of automatic speech recognition system are compared in this paper. Speech recognition accuracy was used as measure of performance. Different kinds of outdoor and indoor noise were used for studying. It is shown the superiority of training on noised speech methods over the competitive technique of training on clear speech. It has been found that training by means of noised speech allows reach high, abut 95...97%, recognition accuracy for about 5...10 dB signal-to-noise ratio. At the same time, training by means of clean speech allows reach the same accuracy for about 20...25 dB.