Automatic speech recognition for Moroccan dialect in noisy traffic environments

In this study, we explored the impact of traffic noise on speech recognition performance for the Moroccan Fessi dialect at varying noise levels. To achieve this, we developed a highly configurable, open-source speech recognition platform, designed to identify optimal parameters for handling the dialect’s unique characteristics. Our approach employs a stochastic hidden Markov model combined with Gaussian mixture models, specifically tailored for the low-resource Moroccan dialect. The novelty of this approach lies in its ability to enable parameter learning and adaptation with minimal prior knowledge of the dialect’s linguistic rules. We further analyzed the noise performance of the system in relation to the syllabic structure of words, assessing its effect on automatic speech recognition accuracy. Experimental results show a substantial degradation in recognition performance under noisy conditions, with a word error rate of 96.95% in noisy environments compared to 8.14% in clean settings. Additionally, we observed that specific syllables in the Moroccan dialect significantly influence the recognition system’s performance.