Hierarchical Classification for Spoken Arabic Dialect Identification using Prosody: Case of Algerian Dialects
This work addresses dialect identification for Arabic speakers, particularly in under-resourced contexts like Algerian dialects, representing an incremental advance in the field.
The paper tackles the problem of automatically identifying under-resourced Algerian Arabic dialects, which is challenging with conventional methods, by proposing a hierarchical classification approach (HADID) using prosody features and deep neural networks. The results show a 63.5% improvement in precision over a baseline flat classification system and effective performance with test utterances under 6 seconds.
In daily communications, Arabs use local dialects which are hard to identify automatically using conventional classification methods. The dialect identification challenging task becomes more complicated when dealing with an under-resourced dialects belonging to a same county/region. In this paper, we start by analyzing statistically Algerian dialects in order to capture their specificities related to prosody information which are extracted at utterance level after a coarse-grained consonant/vowel segmentation. According to these analysis findings, we propose a Hierarchical classification approach for spoken Arabic algerian Dialect IDentification (HADID). It takes advantage from the fact that dialects have an inherent property of naturally structured into hierarchy. Within HADID, a top-down hierarchical classification is applied, in which we use Deep Neural Networks (DNNs) method to build a local classifier for every parent node into the hierarchy dialect structure. Our framework is implemented and evaluated on Algerian Arabic dialects corpus. Whereas, the hierarchy dialect structure is deduced from historic and linguistic knowledges. The results reveal that within {\HD}, the best classifier is DNNs compared to Support Vector Machine. In addition, compared with a baseline Flat classification system, our HADID gives an improvement of 63.5% in term of precision. Furthermore, overall results evidence the suitability of our prosody-based HADID for speaker independent dialect identification while requiring less than 6s test utterances.