Extended Rhythm-Based Investigation of Saudi Dialects Using the Saudi Accented Arabic Voice Bank Corpus

In this study, we investigate the speech rhythm of five dialectal regions of the Kingdom of Saudi Arabia (KSA). The relations between different Interval Measures (IMs) and their capabilities of classifying the native origins of speakers, their gender (male/female), and type of sentence (question or statement) are studied. The Saudi Accented Arabic Voice Bank (SAAVB) corpus was used for all experiments. It contains a set of Arabic speech that represents native Arabic speakers from all the cities around Saudi Arabia. A number of rhythm metrics, namely, ΔV, ΔC, and % V, are calculated and measured in detail. The results show that ΔV metric can differentiate between question and statement sentences. Moreover, the %V detects a significant difference between male and female speakers. The results of the study demonstrate the uniqueness of the Riyadh dialect. In other words, the Riyadh dialect is different from all other investigated dialects. Moreover, a high similarity is observed between the dialects of Tabuk and Northern Border (NB) regions. These two regions are located in the north of Saudi Arabia and border Jordan and Iraq international states, which may explain the reason behind this similarity. Finally, a conclusion and general discussion on speech rhythm metrics is provided.