ADDITIONAL NOISE REMOVING APPARATUS USING HUMAN AUDITORY MODEL FOR IMPROVING PERFORMANCE OF SPEECH RECOGNITION SYSTEM

摘要

PURPOSE: An additional noise removing apparatus using a human auditory model is provided to improve the performance of a speech recognition system by applying the human auditory model to an input audio signal at a pre-processing step for removing an additional noise. CONSTITUTION: An additional noise removing apparatus using a human auditory model includes a buffering an framing unit(10), a human auditory model application unit(100), a frequency spectrum estimator(40), an additional noise estimator(30), and an additional noise removing unit(50). The buffering and framing unit buffers an input audio signal and segments the audio signal into frames at a predetermined time interval. The human auditory model application unit applies the human auditory model to the input audio signal. The frequency spectrum estimator transforms the input audio signal into a frequency domain to generate a frequency spectrum composed of an amplitude component and a phase component. The additional noise estimator estimate spectrum information of a noise added to the audio signal using the frequency spectrum. The additional noise removing unit removes the additional noise estimated by the additional noise estimator from the frequency spectrum.