Methods to Improve the Efficiency of Recognition of Speech Signals in Voice Control Systems

Цель исследования состоит в повышении защищенности элементов распределенной компьютерной системы автоматического распознавания голосовых команд от возможного неверного определения команды за счет создания алгоритмического обеспечения оценки и регулирования рисков неверной идентификации голосовой команды для сравнения реализации двух алгоритмов: алгоритм динамической трансформации временной шкалы и алгоритм на основе скрытых Марковских процессов.Полученные результаты могут быть использованы или адаптированы при необходимости повышения стойкости систем автоматического распознавания голосовых команд на этапах проектирования и модернизации, а также при необходимости восстановления эффективности функционирования после компрометации или взлома. The aim of the study is to increase the security of the elements of a distributed computer system for automatic recognition of voice commands from possible incorrect identification of the command by creating algorithmic support for assessing and managing the risks of incorrect identification of the voice command to compare the implementation of two algorithms: the algorithm for dynamic transformation of the timeline and the algorithm based on hidden Markov processes.The obtained results can be used or adapted if it is necessary to increase the stability of automatic voice recognition systems at the design and modernization stages, as well as if it is necessary to restore the efficiency of functioning after a compromise or hacking.

Download Full-text

The Effects of Voice System Design Components on Driver Workload

Transportation Research Record Journal of the Transportation Research Board ◽

10.1177/0361198118777382 ◽

2018 ◽

Vol 2672 (37) ◽

pp. 94-100 ◽

Cited By ~ 2

Author(s):

Douglas Getty ◽

Francesco Biondi ◽

Shae D. Morgan ◽

Joel M. Cooper ◽

David L. Strayer

Keyword(s):

System Design ◽

Control Systems ◽

Past Research ◽

Delay System ◽

Steering Wheel ◽

Total System ◽

System Delay ◽

Voice Control ◽

Task Time

In-vehicle voice control systems are standard in most new vehicles. However, despite auditory-vocal interaction allowing drivers to keep their hands on the steering wheel and eyes on the forward roadway, recent findings indicate the potential for these systems to increase levels of workload and lead to lengthy interaction times. Although many studies have examined the distraction potential of interacting with in-vehicle voice control systems, more research is needed to understand the relationship between different system design components and workload. In this study, we investigate the role of system delay, system accuracy, and menu depth in determining the overall level of demand and interaction times on eight different 2017 model-year vehicles. Voice system accuracy was measured via playback of a pre-recorded sample of voice commands through a studio monitor mounted near the headrest. Menu depth and system delay were calculated by measuring, respectively, the number of interaction steps and total system processing time required to access common infotainment functions. These measures were validated through linear and multiple regression analyses with workload and task time collected in an on-road study. We found system delay and system accuracy to be significant predictors of task time and subjective measures of workload from the NASA Task Load Index and the Driving Activity Load Index. A In addition to providing valuable information on the role of separate voice control system design components on resulting levels of workload, these results extend past research by generalizing findings to multiple current auditory-vocal systems.

Download Full-text