Echo suppressor for a speech input dialogue system

H - Electricity – 04 – R

Patent

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

H04R 3/02 (2006.01) G10L 21/02 (2006.01) H04B 3/23 (2006.01) H04M 1/20 (2006.01)

Patent

CA 2227478

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.

Suppresseur d'écho et méthode d'exploitation de ce dernier dans un système à entrées vocales, particulièrement adapté pour des systèmes à entrées vocales ayant des trajets d'écho extrêmement longs (environ 50 ms). Une demande d'entrée du système de reconnaissance vocale ainsi que le signal vocal d'entrée (qui a été corrompu par la demande d'entrée) font l'objet d'une transformation de Fourier rapide. Les signaux transformés sont divisés en un certain nombre de sous-bandes afin d'estimer les signaux d'échos de sous-bande correspondants. Cela se fait à l'aide d'étages de filtrage adaptatif individuels utilisant l'algorithme NLMS. La division en sous-bandes et la réduction du nombre de ces sous-bandes réduisent les calculs et peuvent limiter le taux d'échantillonnage. La procédure de calcul associée à l'estimation du signal d'écho est ainsi réduite. Après estimation du signal d'écho pour les sous-bandes individuelles, le signal d'origine ainsi rétabli est soustrait du signal vocal corrompu de sorte que seul un signal vocal pur soit transmis à l'étage chargé de la reconnaissance des caractéristiques dans le système de reconnaissance de la parole.

LandOfFree

Say what you really think

Search LandOfFree.com for Canadian inventors and patents. Rate them and share your experience with other people.

Rating

Echo suppressor for a speech input dialogue system does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Echo suppressor for a speech input dialogue system, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Echo suppressor for a speech input dialogue system will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFCA-PAI-O-1977188

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.