Automatic Dialect Detection in Arabic Broadcast Speech

We investigate different approaches for dialect identification in Arabic broadcast speech, using phonetic, lexical features obtained from a speech recognition system, and acoustic features using the i-vector framework. We studied both generative and discriminate classifiers, and we combined these features using a multi-class Support Vector Machine (SVM). We validated our results on an Arabic/English language identification task, with an accuracy of 100%. We used these features in a binary classifier to discriminate between Modern Standard Arabic (MSA) and Dialectal Arabic, with an accuracy of 100%. We further report results using the proposed method to discriminate between the five most widely used dialects of Arabic: namely Egyptian, Gulf, Levantine, North African, and MSA, with an accuracy of 52%. We discuss dialect identification errors in the context of dialect code-switching between Dialectal Arabic and MSA, and compare the error pattern between manually labeled data, and the output from our classifier. We also release the train and test data as standard corpus for dialect identification.

PDF Abstract

Datasets


  Add Datasets introduced or used in this paper
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Spoken language identification Untranscribed mixed-speech dataset SVM ACC 45.2% # 1
PRC 44.8% # 1
RCL 45.4% # 2
Spoken language identification Untranscribed mixed-speech dataset Max Ent ACC 40% # 3
PRC 40% # 3
RCL 40.6% # 4
Spoken language identification Untranscribed mixed-speech dataset Naive Bayes ACC 37.9% # 4
PRC 37.5% # 4
RCL 50.2% # 1
Spoken language identification Untranscribed mixed-speech dataset n-gram Language Model ACC 40.4% # 2
PRC 40.2% # 2
RCL 41.3% # 3

Methods


No methods listed for this paper. Add relevant methods here