Turkish Voice Commands based Chess Game using Gammatone Cepstral Coefficients

TL;DR

This paper develops a voice command recognition system for a chess game using Gammatone Cepstral Coefficients, enabling accessible play for individuals with limited mobility, with high classification accuracy.

Contribution

It introduces a novel voice command recognition approach for chess using GTCC and compares multiple classifiers, improving accessibility for users with mobility challenges.

Findings

Person-based classification accuracy: 75%-98%

General classification accuracy: over 84%

GTCC features outperform MFCC in recognition tasks

Abstract

This study was carried out to enable individuals with limited mobility skills to play chess in real time and to play games with the individuals around them without being under any social distress or stress. Voice recordings were taken from 50 people (23 men and 27 women). While recording the sound, 29 words from each person were used which are determined as necessary for playing the game. Mel Frequency Coefficients (MFCC) and Gammatone Cepstral Coefficients (GTCC) qualification methods were used. In addition, k-NN, Naive Bayes and Neural Network classification methods were used for classification. Two different classification procedures were applied, namely, person-based and general. While the performance rate in person-based classification ranged from 75% to 98%, a performance over 84% was achieved in general classification.