SEPARATION OF DRY SOUND AND ENVIRONMENTAL SOUND

摘要

To provide a method for separating a dry sound from an environmental sound.SOLUTION: The present invention relates to a method of separating a speech input signal into a dry signal component and an environmental signal component, and the method includes : generating a conversion input signal which includes converting a speech input signal into a frequency space; applying a smoothing filter to the conversion input signal to generate an estimated environmental signal component; identifying a dry signal component based on the estimated environmental signal component; and identifying the environmental signal component based on the identified dry signal component and the speech input signal.SELECTED DRAWING: Figure 2