Improved dialect recognition for colloquial Arabic speakers

Ziedan, Rania R.; Micheal, Michael N.; Alsammak, Abdulwahab K.; Mursi, Mona F. M.; Elmaghraby, Adel

doi:10.1109/isspit.2016.7886002

Cited by 1 publication

(1 citation statement)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Multiple speech datasets have been collected for Arabic dialects, and a number of dialect classification models have been proposed using these datasets. Ziedan et al [11], [12] have collected a dataset of Arabic spontaneous speech from YouTube videos in three different dialects: the dialects of Levant, Egypt, and Arabian Peninsula, and have named the dataset as the spoken Arabic Regional archive (SARA). Subsequently, the authors have proposed a dialect classification model using acoustic cepstral features together with delta coefficients as input to the universal background Gaussian mixture model (UBM-GMM).…”

Section: Introductionmentioning

confidence: 99%

Dialect classification using acoustic and linguistic features in Arabic speech

Humayun

Yassin

Abas

2023

IJ-AI

View full text Add to dashboard Cite

<span lang="EN-US">Speech dialects refer to linguistic and pronunciation variations in the speech of the same language. Automatic dialect classification requires considerable acoustic and linguistic differences between different dialect categories of speech. This paper proposes a classification model composed of a combination of classifiers for the Arabic dialects by utilizing both the acoustic and linguistic features of spontaneous speech. The acoustic classification comprises of an ensemble of classifiers focusing on different frequency ranges within the short-term spectral features, as well as a classifier utilizing the ‘i-vector’, whilst the linguistic classifiers use features extracted by transformer models pre-trained on large Arabic text datasets. It has been shown that the proposed fusion of multiple classifiers achieves a classification accuracy of 82.44% for the identification task of five Arabic dialects. This represents the highest accuracy reported on the dataset, despite the relative simplicity of the proposed model, and has shown its applicability and relevance for dialect identification tasks. </span>

show abstract

Section: Introductionmentioning

confidence: 99%