Echo suppressor for the speach input of a dialogue system

摘要

In an echo suppressor and a method for the operation thereof in a speech input system, particularly suited for use in speech input systems having extremely long echo paths (approximately 50 ms), an input request of the speech recognition system as well as the incoming speech signal (which has been corrupted by the input request) are fast-Fourier transformed, and the transformed signals are divided into a number of sub-bands in order to estimate corresponding sub-band echo signals. This occurs with individual adaptive filter stages that utilize the NLMS algorithm. Due to the division into sub-bands and a reduction of the number of these sub-bands, the calculating outlay is minimized and the sampling rate can be reduced. The calculating procedure in the estimating of the echo signal part is thus reduced. After estimating the echo signal for the individual sub-bands, the original signal is restored as a superimposition of the individual echo signal components, and the echo signal restored in this way is subtracted from the corrupted speech signal, so that only a pure speech signal is supplied to the feature extraction stage of the speech recognition system.