{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:04:00Z","timestamp":1775199840546,"version":"3.50.1"},"reference-count":30,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11434668","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["Evaluating Japanese Dialect Robustness Across Speech and Text-based Large Language Models"],"prefix":"10.1109","author":[{"given":"Tomoya","family":"Mizumoto","sequence":"first","affiliation":[{"name":"SB Intuitions,Tokyo,Japan"}]},{"given":"Yusuke","family":"Fujita","sequence":"additional","affiliation":[{"name":"SB Intuitions,Tokyo,Japan"}]},{"given":"Hao","family":"Shi","sequence":"additional","affiliation":[{"name":"SB Intuitions,Tokyo,Japan"}]},{"given":"Lianbo","family":"Liu","sequence":"additional","affiliation":[{"name":"SB Intuitions,Tokyo,Japan"}]},{"given":"Atsushi","family":"Kojima","sequence":"additional","affiliation":[{"name":"SB Intuitions,Tokyo,Japan"}]},{"given":"Yui","family":"Sudo","sequence":"additional","affiliation":[{"name":"SB Intuitions,Tokyo,Japan"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Qwen2.5 Technical Report","volume-title":"arXiv:2412.15115","author":"Qwen","year":"2025"},{"key":"ref2","article-title":"The Llama 3 Herd of Models","author":"Grattafiori","year":"2024","journal-title":"arXiv:2407.21783"},{"key":"ref3","article-title":"DeepSeek-V3 Technical Report","volume-title":"arXiv:2412.19437","author":"Liu","year":"2024"},{"key":"ref4","article-title":"GPT-4 Technical Report","volume-title":"arXiv:2303.08774","author":"OpenAI","year":"2024"},{"key":"ref5","article-title":"PaLM 2 Technical Report","volume-title":"arXiv:2305.10403","author":"Anil","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.317"},{"key":"ref7","article-title":"Assessing Thai Dialect Performance in LLMs with Automatic Benchmarks and Human Evaluation","author":"Limkonchotiwat","year":"2025","journal-title":"arXiv:2504.05898"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.vardial-1.11"},{"key":"ref9","article-title":"AudioPaLM: A Large Language Model That Can Speak and Listen","author":"Rubenstein","year":"2023","journal-title":"arXiv:2306.12925"},{"key":"ref10","article-title":"Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models","author":"Chu","year":"2023","journal-title":"arXiv:2311.07919"},{"key":"ref11","article-title":"Qwen2-Audio Technical Report","volume-title":"arXiv:2407.10759","author":"Chu","year":"2024"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.923"},{"key":"ref13","article-title":"Multi-dialect Neural Machine Translation and Dialectometry","volume-title":"Proceedings of the 32nd Pacific Asia Conference on Language, Information and Computation","author":"Abe"},{"key":"ref14","article-title":"Building Parallel Monolingual Gan Chinese Dialects Corpus","volume-title":"Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)","author":"Xu"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2463"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.1018"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/BigData62323.2024.10826131"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.704"},{"key":"ref20","article-title":"LoRA: Low-Rank Adaptation of Large Language Models","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Hu"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.787"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447605"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446898"},{"key":"ref24","first-page":"1134","article-title":"ReazonSpeech: A free and massive corpus for Japanese ASR","volume-title":"Proceedings of the 29th Annual Meeting of the Association for Natural Language Processing (Domestic Conference","author":"Yin"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.72"},{"key":"ref26","article-title":"CoVoST 2: A Massively Multilingual Speech-to-Text Translation Corpus","author":"Wang","year":"2020","journal-title":"arXiv:2007.10310"},{"key":"ref27","article-title":"CPJD Corpus: Crowdsourced Parallel Speech Corpus of Japanese Dialects","volume-title":"Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)","author":"Takamichi"},{"key":"ref28","article-title":"Building a Large Japanese Web Corpus for Large Language Models","author":"Okazaki"},{"key":"ref29","article-title":"Continual pre-training for cross-lingual 11 m adaptation: Enhancing japanese language capabilities","volume-title":"Proceedings of the First Conference on Language Modeling","author":"Fujii"},{"key":"ref30","article-title":"Robust Speech Recognition via Large-Scale Weak Supervision","author":"Radford","year":"2022","journal-title":"arXiv:2212.04356"}],"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\/11434668.pdf?arnumber=11434668","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:57:59Z","timestamp":1775192279000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434668\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434668","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}