An intuitive interaction system for fire safety using a speech recognition technology

Abstract

We propose an intuitive interaction system, which is a part of Cooperative Fire Security System using HARMS (CFS 2 H), to readily deal with fire in a high-rise building. The interaction system is a bridge connecting human, as an operator, to the whole system. Utilizing a natural language processing (NLP) technology using Microsoft Kinect makes the interaction system intuitive and has human-oriented operations. HumanAgent-Robot-Machine-Sensor (HARMS) provides a distributed network so that the systems are able to communicate with a highlevel communication protocol. We established a scenario to verify the interaction system along with the system as a whole. The result of the verification left several technical issues and challenges.

Human-Agent Teaming: A System-Theoretic Overview

“…This is because the ironies of automation and/or autonomy [19], [20] can systematize problems with automation and ultimately encourage human error and/or the rejection of useful technology. As such, HAI emphasizes the need for interfaces, protocols, and guidelines that match the cognitive and perceptual abilities of human users [29], [30]. As such, HAI aims to engineer more natural, intuitive, and easier systems to use, while accounting for the specific problems that can arise from autonomous agents interacting with people [31].…”

“…With auditory and textual communication, comes the need for natural language processing (NLP) [73], [74]. NLP application for HAT encompasses several major areas, such as speech recognition [30], natural language understanding [75], natural language generation [73], [76], dialogue management [77], [78], and multimodal interaction [79], [80]. The goal is to make HAT more effective and efficient in various tasks by developing natural language models and platforms that allow for human-like communication [73].…”

Wavelet Based Feature Extraction for The Indonesian CV Syllables Sound

“…It is different with loudness normalization which adjusts a signal's gain so that the signal's loudness level equals some desired level. The peak normalization equation can be written: (1) with X'= output data of peak normalization, X max = maximum value of the input data, X i = input data that will be normalized, X min = minimum value of the input data.…”

Wavelet Based Feature Extraction for The Indonesian CV Syllables Sound

“…The attempt to realize an intelligent pattern recognition system requires the ancillary systems development that are effective, reliable, and efficient to be integrated well in an intuitive interaction system [1]. One of the pattern recognition support system that has been so much developed is a speech recognition system [1]- [3].…”

“…The attempt to realize an intelligent pattern recognition system requires the ancillary systems development that are effective, reliable, and efficient to be integrated well in an intuitive interaction system [1]. One of the pattern recognition support system that has been so much developed is a speech recognition system [1]- [3]. Challenges in creating a good speech recognition systems include feature extraction [3]- [4], namely how to find the unique features of a speech sound signal that distinguishes it from other speech signals so that a collection of these unique features which will constructing a reference database to identify each certain speech signal as an input command from the user.…”