Proceedings of the 6th Computer Science Research Days, JRI 2023, 18-20 December 2023, Ouagadougou, Burkina Faso

Research Article

Voice Interaction in Moore Language Study on Isolated Word Recognition in Audio Samples

Download110 downloads
  • @INPROCEEDINGS{10.4108/eai.18-12-2023.2348169,
        author={Moumini  Kabore and Rodrique  Kafando and Aminata  Sabane and Abdoul Kader  Kabore and T\^{e}gawend\^{e} F.  Bissyande},
        title={Voice Interaction in Moore Language Study on Isolated Word Recognition in Audio Samples},
        proceedings={Proceedings of the 6th Computer Science Research Days, JRI 2023, 18-20 December 2023, Ouagadougou, Burkina Faso},
        publisher={EAI},
        proceedings_a={JRI},
        year={2024},
        month={6},
        keywords={isolated word recognition rnn mel-frequency cepstral coefficient},
        doi={10.4108/eai.18-12-2023.2348169}
    }
    
  • Moumini Kabore
    Rodrique Kafando
    Aminata Sabane
    Abdoul Kader Kabore
    Tégawendé F. Bissyande
    Year: 2024
    Voice Interaction in Moore Language Study on Isolated Word Recognition in Audio Samples
    JRI
    EAI
    DOI: 10.4108/eai.18-12-2023.2348169
Moumini Kabore1,*, Rodrique Kafando2, Aminata Sabane2, Abdoul Kader Kabore2, Tégawendé F. Bissyande2
  • 1: CITADEL-Université Virtuelle du Burkina Faso
  • 2: Université Joseph KI-ZERBO
*Contact email: ka.munkab@gmail.com

Abstract

This paper explores the optimization of telephone functionalities through voice interaction in the Moore language, prevalent in Burkina Faso. Data gathered from 492 individuals in Ouagadougou, representing diverse dialects and vocal intensities across age groups, informs the study. Employing K-Nearest Neighbor (KNN), Random Forest (RF), and Recurrent Neural Networks (RNNs), the analysis focuses on 29 Moore language commands, prioritizing practicality and user interaction. The findings suggest promising prospects for RNNs, achieving a 63% accuracy in recognizing isolated words. This success hints at potential advancements in RNNs, incorporating attention mechanisms and end-to-end technology, catering to the voice-controlled mobile device needs of Moore speakers.