{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T06:51:24Z","timestamp":1764399084966,"version":"3.46.0"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000646","name":"JSPS","doi-asserted-by":"publisher","award":["JP23K28147,JP22H00536"],"award-info":[{"award-number":["JP23K28147,JP22H00536"]}],"id":[{"id":"10.13039\/501100000646","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,22]]},"DOI":"10.1109\/apsipaasc65261.2025.11249116","type":"proceedings-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:40:26Z","timestamp":1764355226000},"page":"549-554","source":"Crossref","is-referenced-by-count":0,"title":["Reducing Orthographic Dependency on Paired Data by Probabilistic Integration via Syllabogram for Japanese Dialogue Speech Recognition"],"prefix":"10.1109","author":[{"given":"Ryu","family":"Takeda","sequence":"first","affiliation":[{"name":"SANKEN, The University of Osaka,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kazunori","family":"Komatani","sequence":"additional","affiliation":[{"name":"SANKEN, The University of Osaka,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/eurospeech.1999-60"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.06.002"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/tasl.2006.878269"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1442"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1320"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2019.8682918"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1209"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2017.01.014"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1392"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639619"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-719"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.sigdial-1.42"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-377"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447465"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-965"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-749"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-746"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-617"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383506"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref21","article-title":"Robust speech recognition via largescale weak supervision","volume-title":"Proc. of ICML","author":"Radford","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.787"},{"volume-title":"Rinna\/Nue-ASR","author":"Hono","key":"ref23"},{"key":"ref24","article-title":"Corpus of spontaneous Japanese: Its design and evaluation","volume-title":"Proc. of ISCA & IEEE Workshop on Spontaneous Speech Processing and Recognition","author":"Maekawa","year":"2003"},{"key":"ref25","article-title":"JVS corpus: Free Japanese multispeaker voice corpus","author":"Takamichi","year":"2019","journal-title":"arXiv"},{"key":"ref26","article-title":"MUSAN: A Music, Speech, and Noise Corpus","author":"Snyder","year":"2015","journal-title":"arXiv"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2821"},{"issue":"48","key":"ref28","first-page":"345","article-title":"Balanced corpus of contemporary written Japanese","author":"Kikuo","year":"2014","journal-title":"Language Resources and Evaluation"},{"key":"ref29","first-page":"2431","article-title":"Wiki-40B: Multilingual language model dataset","volume-title":"Proc. of LREC","author":"Guo","year":"2020"},{"key":"ref30","first-page":"230","article-title":"Applying conditional random fields to Japanese morphological analysis","volume-title":"Proc. of EMNLP","author":"Kudo","year":"2004"},{"key":"ref31","article-title":"Implementation of a word segmentation dictionary called mecab-ipadic-NEologd and study on how to use it effectively for information retrieval (in Japanese)","volume-title":"Proc. of Annual Meeting of the Association for NLP","author":"Sato","year":"2017"},{"key":"ref32","first-page":"911","article-title":"UniDic for early middle Japanese: A dictionary for morphological analysis of classical Japanese","volume-title":"Proc. of LREC","author":"Ogiso","year":"2012"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.sigdial-1.9"},{"key":"ref34","article-title":"Acoustical sound database in real environments for sound scene understanding and hands-free speech recognition","volume-title":"Proc. of LREC","author":"Nakamura","year":"2000"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/apsipaasc58517.2023.10317247"},{"issue":"1","key":"ref38","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of Machine Learning Research"},{"key":"ref39","article-title":"Decoupled weight decay regularization","volume-title":"Proc. of ICLR","author":"Loshchilov","year":"2018"},{"key":"ref40","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. of NAACL","author":"Devlin","year":"2019"},{"volume-title":"Rinna\/japanese-gpt-neox-small","author":"Zhao","key":"ref41"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2004.1326009"},{"key":"ref43","article-title":"The kaldi speech recognition toolkit","volume-title":"Proc. of SLT","author":"Povey","year":"2011"}],"event":{"name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2025,10,22]]},"location":"Singapore, Singapore","end":{"date-parts":[[2025,10,24]]}},"container-title":["2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11248853\/11248968\/11249116.pdf?arnumber=11249116","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T06:50:26Z","timestamp":1764399026000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249116\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc65261.2025.11249116","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}