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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Wang, Bin, Zou, Xunlong, Sun, Shuo, Zhang, Wenyu, He, Yingxu, Liu, Zhuohan, Wei, Chengwei, Chen, Nancy F., Aw, AiTi
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916562454183936
author Wang, Bin
Zou, Xunlong
Sun, Shuo
Zhang, Wenyu
He, Yingxu
Liu, Zhuohan
Wei, Chengwei
Chen, Nancy F.
Aw, AiTi
author_facet Wang, Bin
Zou, Xunlong
Sun, Shuo
Zhang, Wenyu
He, Yingxu
Liu, Zhuohan
Wei, Chengwei
Chen, Nancy F.
Aw, AiTi
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2501_01034
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Advancing Singlish Understanding: Bridging the Gap with Datasets and Multimodal Models
Wang, Bin
Zou, Xunlong
Sun, Shuo
Zhang, Wenyu
He, Yingxu
Liu, Zhuohan
Wei, Chengwei
Chen, Nancy F.
Aw, AiTi
Computation and Language
Sound
Audio and Speech Processing
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.
title Advancing Singlish Understanding: Bridging the Gap with Datasets and Multimodal Models
topic Computation and Language
Sound
Audio and Speech Processing
url https://arxiv.org/abs/2501.01034