Improving the efficiency of voice control robots based on adaptive procedures

Zhadyra T. Zhumasheva, Aidana S. Kyzdarbekova, Maulenbek T. Abdulkhairov

2017

Closed access Metadata (CSL-JSON)
DOI 10.1109/ctsys.2017.8109563
Data confidence 70 medium
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

The paper considers the task of improving the efficiency of voice control of robots on the basis of adaptive procedures. This problem is considered in the context of noise resistance processing of speech signals for voice recognition subsystems. A solution to this problem is found in classes of adaptive algorithms for filtering voice signals based on sequential filtering. This model allows to improve the adaptation of speech commands to the modern “aggressive” noise environment and to increase the accuracy of recognition of the planned movement of mobile robots. The simulation results of the proposed algorithm demonstrate a reduction in measurement error and errors in the detection of voice commands for mobile robot voice control subsystems.