Voice Communication in Noisy Environments in a Smart House Using Hybrid LMS+ICA Algorithm.

Radek Martinek,Jan Nedoma,Aleksandra Kawala-Sterniuk,Jan Vanus,Michael Fridrich,Jaroslav Frnda

doi:10.3390/s20216022

Abstract

This publication describes an innovative approach to voice control of operational and technical functions in a real Smart Home (SH) environment, where, for voice control within SH, it is necessary to provide robust technological systems for building automation and for technology visualization, software for recognition of individual voice commands, and a robust system for additive noise canceling. The KNX technology for building automation is used and described in the article. The LabVIEW SW tool is used for visualization, data connectivity to the speech recognizer, connection to the sound card, and the actual mathematical calculations within additive noise canceling. For the actual recognition of commands, the SW tool for recognition within the Microsoft Windows OS is used. In the article, the least mean squares algorithm (LMS) and independent component analysis (ICA) are used for additive noise canceling from the speech signal measured in a real SH environment. Within the proposed experiments, the success rate of voice command recognition for different types of additive interference (television, vacuum cleaner, washing machine, dishwasher, and fan) in the real SH environment was compared. The recognition success rate was greater than 95% for the selected experiments.

Highlights

Spoken communication is the basic and most widely used way of transmitting information between people
We do not have ambitions to develop algorithms of recognition, but we present a way how to improve the effectiveness of speech recognizer via the mentioned adaptive systems
This study was focused on an innovative method of processing speech signals used for voice control of operational and technical functions in Smart Home, with subsequent testing of selected filtering methods

Summary

Introduction

Spoken communication is the basic and most widely used way of transmitting information between people. The computer industry, where the goal is to make the computer a fully-fledged partner of human beings in spoken language, is no exception. This goal is pursued mainly because such a way of communication can be beneficial and can significantly facilitate a person’s life. Voice communication systems are increasingly used in industrial and social practice. Various systems of machine and equipment control using voice commands or automatic dictation transcription are generally applicable. These systems are especially suitable in cases where a person’s eyes and hands are employed in other activities

Objectives

Methods

Findings

Discussion

Conclusion