Advancing Singlish Understanding: Bridging the Gap with Datasets and Multimodal Models

TL;DR

This paper introduces a standardized spoken Singlish corpus and a multimodal model, SingAudioLLM, enabling advanced multilingual speech tasks and achieving state-of-the-art results in Singlish understanding.

Contribution

The work provides the largest annotated spoken Singlish dataset and a novel multimodal model, advancing research in low-resource, multilingual speech processing.

Findings

Achieved 10-30% performance improvements over previous models.

Created the largest standardized spoken Singlish corpus with annotations.

Demonstrated the effectiveness of multimodal models in Singlish tasks.

Abstract

Singlish, a Creole language rooted in English, is a key focus in linguistic research within multilingual and multicultural contexts. However, its spoken form remains underexplored, limiting insights into its linguistic structure and applications. To address this gap, we standardize and annotate the largest spoken Singlish corpus, introducing the Multitask National Speech Corpus (MNSC). These datasets support diverse tasks, including Automatic Speech Recognition (ASR), Spoken Question Answering (SQA), Spoken Dialogue Summarization (SDS), and Paralinguistic Question Answering (PQA). We release standardized splits and a human-verified test set to facilitate further research. Additionally, we propose SingAudioLLM, a multi-task multimodal model leveraging multimodal large language models to handle these tasks concurrently. Experiments reveal our models adaptability to Singlish context, achieving state-of-the-art performance and outperforming prior models by 10-30% in comparison with other AudioLLMs and cascaded solutions.