Textual Data Augmentation for Arabic-English Code-Switching Speech Recognition

TL;DR

This paper introduces a zero-shot learning approach for Arabic-English code-switching speech recognition by augmenting monolingual data with artificially generated code-switched text, significantly improving recognition performance.

Contribution

It proposes a novel data augmentation method using lexical replacements and equivalence constraints to generate grammatically valid code-switching text for ASR training.

Findings

65.5% reduction in language model perplexity

7.7% improvement in ASR WER

Over 80% of generated text deemed of adequate quality

Abstract

The pervasiveness of intra-utterance code-switching (CS) in spoken content requires that speech recognition (ASR) systems handle mixed language. Designing a CS-ASR system has many challenges, mainly due to data scarcity, grammatical structure complexity, and domain mismatch. The most common method for addressing CS is to train an ASR system with the available transcribed CS speech, along with monolingual data. In this work, we propose a zero-shot learning methodology for CS-ASR by augmenting the monolingual data with artificially generating CS text. We based our approach on random lexical replacements and Equivalence Constraint (EC) while exploiting aligned translation pairs to generate random and grammatically valid CS content. Our empirical results show a 65.5% relative reduction in language model perplexity, and 7.7% in ASR WER on two ecologically valid CS test sets. The human evaluation of the generated text using EC suggests that more than 80% is of adequate quality.