PUBLISHED PAPERS #31
| Rustam MAMMADLI, Ali PARSAYAN. Intelligent car interior components controlling by means of Azeri (Azerbaijani) spoken language words |
|---|
| Abstract. This paper aims to design a control system for car interior components by means of some Azeri (Azerbaijani) spoken language selected command words. By using Google Speech API various existing languages can be integrated, however, different approach is followed to implement a system that recognizes sone command words in Azeri (Azerbaijani) spoken language. The proposed method consists of two MFCC and RASTA-PLP based feature extraction and a CNN based classification algorithms. Four command words from Azeri (Azerbaijani) spoken language are considered as “Aç”, “Bağla”, “Qoş”, and “Söndür”. A Raspberry-Pi based embedded system recognizes the command words and sends the decision commands to the STM32 based embedded system thorough the UART protocol for controlling. The simulations and implementation resulted 91.6% recognition accuracy in utilizing of the MFCC feature extractor. |
| Keywords: Speech Recognition; MFCC; RASTA-PLP; CNN; Raspberry-Pi; STM32.; Intelligent Car Interior Components Controlling; Azeri (Azerbaijani) Spoken Language |
 Download PDF |
| DOI: https://doi.org/10.54381/plmo2023.31 |