Speech recognition in flight simulator

Aegean International Textile and Advanced Engineering Conference 2018

Rustamov, S.^1,3 ; Gasimov, E.^1 ; Hasanov, R.^1 ; Jahangirli, S.^2 ; Mustafayev, E.^3 ; Usikov, D.^2

ADA University, School of Information Technologies and Engineering, 11 Ahmadbey Aghaoglu St, Baku, Azerbaijan^1

Azerbaijan National Aviation Academy, Azerbaijan^2

Institute of Control Systems of ANAS, Azerbaijan ADA University, Azerbaijan^3

关键词: Feature extraction algorithms;    In-flight simulators;    Linear predictive coefficients;    Mel frequency cepstral co-efficient;    Multilayer artificial neural networks;    Offline modes;    Speech recognition systems;    Windows platform;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/459/1/012005/pdf
DOI  :  10.1088/1757-899X/459/1/012005

来源: IOP

【 摘 要 】

The article is devoted to the investigation of speech recognition in Flight Simulator cockpit. We have done research and developed software for speech recognition in Flight Simulator with limited vocabulary in C# from scratch. The speech recognition system works in real time and offline mode in Windows platform. We used Mel Frequency Cepstral Coefficients and Linear Predictive Coefficients feature extraction algorithms and trained the system by multilayer artificial neural networks. The User Interface of platform is highly functional and allows users to update system parameters through the interface. Our Speech Recognition system results are compared to the results of Microsoft Speech SDK and received satisfactory achievement.