Advancing Singlish Understanding: Bridging the Gap with Datasets and Multimodal Models
This work addresses the gap in linguistic research for Singlish, a Creole language, by providing datasets and models for tasks like ASR and SQA, though it is incremental as it builds on existing multimodal and audio processing methods.
The authors tackled the underexplored spoken form of Singlish by standardizing and annotating the largest spoken Singlish corpus, the Multitask National Speech Corpus (MNSC), and proposed SingAudioLLM, a multi-task multimodal model that achieved state-of-the-art performance, outperforming prior models by 10-30%.
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.