Learning Intonation Pattern Embeddings for Arabic Dialect Identification

TL;DR

This paper introduces an end-to-end system using intonation patterns and hybrid neural networks for Arabic Dialect Identification, achieving state-of-the-art results with robustness to limited data.

Contribution

It demonstrates that intonation patterns alone can effectively identify Arabic dialects, outperforming systems relying on multiple features, and emphasizes the sufficiency of information in acoustic modeling.

Findings

Achieved state-of-the-art results on VarDial 17 ADI dataset.

Intonation patterns alone provide sufficient information for dialect identification.

The proposed pipeline is robust to data sparsity.

Abstract

This article presents a full end-to-end pipeline for Arabic Dialect Identification (ADI) using intonation patterns and acoustic representations. Recent approaches to language and dialect identification use linguistic-aware deep architectures that are able to capture phonetic differences amongst languages and dialects. Specifically, in ADI tasks, different combinations of linguistic features and acoustic representations have been successful with deep learning models. The approach presented in this article uses intonation patterns and hybrid residual and bidirectional LSTM networks to learn acoustic embeddings with no additional linguistic information. Results of the experiments show that intonation patterns for Arabic dialects provide sufficient information to achieve state-of-the-art results on the VarDial 17 ADI dataset, outperforming single-feature systems. The pipeline presented is robust to data sparsity, in contrast to other deep learning approaches that require large quantities of data. We conjecture on the importance of sufficient information as a criterion for optimality in a deep learning ADI task, and more generally, its application to acoustic modeling problems. Small intonation patterns, when sufficient in an information-theoretic sense, allow deep learning architectures to learn more accurate speech representations.