{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:58:19Z","timestamp":1740103099945,"version":"3.37.3"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003816","name":"Huawei Technologies","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003816","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icasspw62465.2024.10669906","type":"proceedings-article","created":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T18:23:22Z","timestamp":1725992602000},"page":"868-872","source":"Crossref","is-referenced-by-count":0,"title":["Exploring Dominant Paths in CTC-Like ASR Models: Unraveling the Effectiveness of Viterbi Decoding"],"prefix":"10.1109","author":[{"given":"Zeyu","family":"Zhao","sequence":"first","affiliation":[{"name":"University of Edinburgh,Centre for Speech Technology Research,UK"}]},{"given":"Peter","family":"Bell","sequence":"additional","affiliation":[{"name":"University of Edinburgh,Centre for Speech Technology Research,UK"}]},{"given":"Ond\u0159ej","family":"Klejch","sequence":"additional","affiliation":[{"name":"University of Edinburgh,Centre for Speech Technology Research,UK"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2016.7472621"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018\u20131423"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2016-595"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"article-title":"Squeezeformer: An Efficient Transformer for Automatic Speech Recognition","year":"2022","author":"Kim","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref9","first-page":"12449","article-title":"Wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Baevski","year":"2020"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746275"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1561\/2000000004"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/5.18626"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022967"},{"journal-title":"First-Pass Large Vocabulary Continuous Speech Recognition using Bi-Directional Recurrent DNNs","year":"2014","author":"Hannun","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053010"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1073"},{"article-title":"Wav2Letter: An End-to-End ConvNet-based Speech Recognition System","year":"2016","author":"Collobert","key":"ref17"},{"journal-title":"Differentiable Weighted Finite-State Transducers","year":"2020","author":"Hannun","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-49127-9_28"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404790"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746821"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288848"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683535"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"issue":"CONF","key":"ref26","article-title":"The Kaldi speech recognition toolkit","volume-title":"IEEE 2011 Workshop on Automatic Speech Recognition and Understanding","author":"Povey"},{"key":"ref27","first-page":"8024","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume-title":"Advances in Neural Information Processing Systems 32","author":"Paszke","year":"2019"}],"event":{"name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2024,4,19]]}},"container-title":["2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10625769\/10625780\/10669906.pdf?arnumber=10669906","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T17:29:38Z","timestamp":1726075778000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10669906\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icasspw62465.2024.10669906","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}