{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T14:26:27Z","timestamp":1760711187091,"version":"3.28.0"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095133","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":4,"title":["Hierarchical Softmax for End-To-End Low-Resource Multilingual Speech Recognition"],"prefix":"10.1109","author":[{"given":"Qianying","family":"Liu","sequence":"first","affiliation":[{"name":"Kyoto University,Graduate School of Informatics,Kyoto,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhuo","family":"Gong","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Graduate School of Engineering,Department of EEIS,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengdong","family":"Yang","sequence":"additional","affiliation":[{"name":"Kyoto University,Graduate School of Informatics,Kyoto,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhang","family":"Yang","sequence":"additional","affiliation":[{"name":"Xinjiang University,School of Information Science and Engineering,Urumqi,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sheng","family":"Li","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology (NICT),Kyoto,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenchen","family":"Ding","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology (NICT),Kyoto,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nobuaki","family":"Minematsu","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Graduate School of Engineering,Department of EEIS,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Huang","sequence":"additional","affiliation":[{"name":"Xinjiang University,School of Information Science and Engineering,Urumqi,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Cheng","sequence":"additional","affiliation":[{"name":"Kyoto University,Graduate School of Informatics,Kyoto,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenhui","family":"Chu","sequence":"additional","affiliation":[{"name":"Kyoto University,Graduate School of Informatics,Kyoto,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sadao","family":"Kurohashi","sequence":"additional","affiliation":[{"name":"Kyoto University,Graduate School of Informatics,Kyoto,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Unsupervised speech recognition","author":"baevski","year":"2021","journal-title":"Proc Neurlps"},{"key":"ref12","article-title":"wav2vec2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020","journal-title":"Proc Neurlps"},{"journal-title":"Wavlm Large-scale self-supervised pretraining for full stack speech processing","year":"2021","author":"chen","key":"ref15"},{"journal-title":"A fine-tuned wav2vec 2 0\/hubert benchmark for speech emotion recognition speaker verification and spoken language understanding","year":"2021","author":"wang","key":"ref14"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1983"},{"key":"ref30","article-title":"Specaug-ment: A simple augmentation method for automatic speech recognition","author":"park","year":"2019","journal-title":"InterSpeech"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1803"},{"article-title":"Learning phone recognition from unpaired audio and phone sequences based on generative adversarial network","year":"2021","author":"liu","key":"ref10"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"journal-title":"Covost 2 A massively multilingual speech-to-text translation corpus","year":"2020","author":"wang","key":"ref17"},{"key":"ref16","article-title":"Covost: A diverse multilingual speech-to-text translation corpus","author":"wang","year":"2020","journal-title":"Proc LREC"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413720"},{"key":"ref18","article-title":"Common voice: A massively-multilingual speech corpus","author":"ardila","year":"2020","journal-title":"Proc LREC"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846280"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICACCI.2018.8554637"},{"journal-title":"Conformer Convolution-augmented transformer for speech recognition","year":"2020","author":"gulati","key":"ref26"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2743344"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683536"},{"key":"ref22","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","author":"mikolov","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1073"},{"key":"ref28","article-title":"THCHS-30 : A free chinese speech corpus","volume":"abs 1512 1882","author":"wang","year":"2015","journal-title":"CoRR"},{"key":"ref27","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NIPS"},{"key":"ref29","first-page":"182","article-title":"THUYG-20: A free uyghur speech database","volume":"57","author":"aisikaer","year":"2017","journal-title":"Journal of Tsinghua University(Science and Technology)"},{"article-title":"Exploiting adapters for cross-lingual low-resource speech recognition","year":"2021","author":"hou","key":"ref8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2092"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2164"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref3","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","author":"graves","year":"2014","journal-title":"Proc ICML PMLR"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687966"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6341"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10095133.pdf?arnumber=10095133","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T19:00:01Z","timestamp":1699902001000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095133\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095133","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}