CTC-DID: CTC-Based Arabic dialect identification for streaming applications

TL;DR

This paper introduces CTC-DID, a novel dialect identification method for Arabic that leverages CTC loss, demonstrating superior performance and streaming adaptability on low-resource datasets compared to existing models.

Contribution

The paper presents a new CTC-based dialect identification approach that is robust, streaming-compatible, and effective on low-resource Arabic dialect datasets, outperforming existing models.

Findings

CTC-DID outperforms fine-tuned Whisper and ECAPA-TDNN models.

The approach is more robust to shorter utterances.

It is easily adaptable for streaming, real-time applications.

Abstract

This paper proposes a Dialect Identification (DID) approach inspired by the Connectionist Temporal Classification (CTC) loss function as used in Automatic Speech Recognition (ASR). CTC-DID frames the dialect identification task as a limited-vocabulary ASR system, where dialect tags are treated as a sequence of labels for a given utterance. For training, the repetition of dialect tags in transcriptions is estimated either using a proposed Language-Agnostic Heuristic (LAH) approach or a pre-trained ASR model. The method is evaluated on the low-resource Arabic Dialect Identification (ADI) task, with experimental results demonstrating that an SSL-based CTC-DID model, trained on a limited dataset, outperforms both fine-tuned Whisper and ECAPA-TDNN models. Notably, CTC-DID also surpasses these models in zero-shot evaluation on the Casablanca dataset. The proposed approach is found to be more robust to shorter utterances and is shown to be easily adaptable for streaming, real-time applications, with minimal performance degradation.