{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:06:11Z","timestamp":1775199971827,"version":"3.50.1"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001321","name":"National Research Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001321","name":"National Research Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11434704","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["MNSC: Advancing Singlish Speech Understanding with Carefully Curated Corpora"],"prefix":"10.1109","author":[{"given":"Bin","family":"Wang","sequence":"first","affiliation":[{"name":"Institute for Infocomm Research(I2R)A*STAR,Singapore"}]},{"given":"Xunlong","family":"Zou","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research(I2R)A*STAR,Singapore"}]},{"given":"Shuo","family":"Sun","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research(I2R)A*STAR,Singapore"}]},{"given":"Wenyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research(I2R)A*STAR,Singapore"}]},{"given":"Yingxu","family":"He","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research(I2R)A*STAR,Singapore"}]},{"given":"Zhuohan","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research(I2R)A*STAR,Singapore"}]},{"given":"Chengwei","family":"Wei","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research(I2R)A*STAR,Singapore"}]},{"given":"Nancy F.","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research(I2R)A*STAR,Singapore"}]},{"given":"AiTi","family":"Aw","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research(I2R)A*STAR,Singapore"}]}],"member":"263","reference":[{"key":"ref1","article-title":"The kaldi speech recognition toolkit","volume-title":"IEEE 2011 workshop on automatic speech recognition and understanding.","author":"Povey"},{"key":"ref2","first-page":"28492","article-title":"Robust speech recognition via largescale weak supervision","volume-title":"International Conference on Machine Learning.","author":"Radford"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MCAS.2011.941079"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688085"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref6","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv preprint arXiv:2312.11805"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888128"},{"key":"ref8","article-title":"Baichuan-omni technical report","volume-title":"arXiv preprint arXiv:2410.08565","author":"Li","year":"2024"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.682"},{"key":"ref10","article-title":"Qwen2audio technical report","volume-title":"arXiv preprint arXiv:2407.10759","author":"Chu","year":"2024"},{"key":"ref11","article-title":"Spirit-lm: Interleaved spoken and written language model","author":"Nguyen","year":"2024","journal-title":"arXiv preprint arXiv:2402.05755"},{"key":"ref12","article-title":"Meralion-audiollm: Technical report","volume-title":"arXiv preprint arXiv:2412.09818","author":"He","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-long.218"},{"issue":"1","key":"ref15","first-page":"2","article-title":"The nie corpus of spoken singapore english (niecsse)","volume":"56","author":"Deterding","year":"2001","journal-title":"SAAL Quarterly"},{"key":"ref16","article-title":"The development of a singapore english call resource","volume-title":"Oriental COCOSDA","author":"Chen"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-563"},{"key":"ref18","article-title":"Spontaneous speech elicitation for large speech corpus in multilingual singapore","author":"Tan","year":"2019","journal-title":"IPSS"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1525"},{"key":"ref20","article-title":"A survey on speech large language models","author":"Peng","year":"2024","journal-title":"arXiv preprint arXiv:2410.18908"},{"key":"ref21","article-title":"Wavchat: A survey of spoken dialogue models","author":"Ji","year":"2024","journal-title":"arXiv preprint arXiv:2411.13577"},{"key":"ref22","article-title":"Audiopalm: A large language model that can speak and listen","author":"Rubenstein","year":"2023","journal-title":"arXiv preprint arXiv:2306.12925"},{"key":"ref23","article-title":"Moshi: a speech-text foundation model for real-time dialogue","author":"D\u00e9fossez","year":"2024","journal-title":"arXiv preprint arXiv:2410.00037"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-1346"},{"key":"ref25","article-title":"Paralinguistics-aware speech-empowered large language models for natural conversation","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Kim"},{"key":"ref26","article-title":"SALMONN: Towards generic hearing abilities for large language models","volume-title":"International Conference on Learning Representations (ICLR)","author":"Tang"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10889444"},{"key":"ref28","article-title":"Building a taiwanese mandarin spoken language model: A first attempt","author":"Yang","year":"2024","journal-title":"arXiv preprint arXiv:2411.07111"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.lingua.2023.103513"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1075\/tsl.95.16lim"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1080\/01434632.2015.1133628"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3390\/languages7030203"},{"key":"ref33","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint arXiv:2407.21783"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.754"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.474"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00671"},{"key":"ref37","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning.","author":"Li"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2017.12.012"},{"key":"ref39","article-title":"Gemma: Open models based on gemini research and technology","author":"Team","year":"2024","journal-title":"arXiv preprint arXiv:2403.08295"},{"key":"ref40","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv preprint arXiv:2106.09685"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.263"},{"key":"ref42","article-title":"Qwen-audio: Advancing universal audio understanding via unified large-scale audio-language models","author":"Chu","year":"2023","journal-title":"arXiv preprint arXiv:2311.07919"}],"event":{"name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,12,6]]},"end":{"date-parts":[[2025,12,10]]}},"container-title":["2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11434577\/11433836\/11434704.pdf?arnumber=11434704","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:58:34Z","timestamp":1775192314000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434704\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434704","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}