{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T08:03:50Z","timestamp":1764403430281,"version":"3.33.0"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"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":[[2024,12,2]]},"DOI":"10.1109\/slt61566.2024.10832327","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"279-285","source":"Crossref","is-referenced-by-count":1,"title":["Advancing CTC Models for Better Speech Alignment: A Topological Approach"],"prefix":"10.1109","author":[{"given":"Zeyu","family":"Zhao","sequence":"first","affiliation":[{"name":"University of Edinburgh,The Centre for Speech Technology Research,United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peter","family":"Bell","sequence":"additional","affiliation":[{"name":"University of Edinburgh,The Centre for Speech Technology Research,United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref2","first-page":"1764","article-title":"Towards End-To-End Speech Recognition with Recurrent Neural Networks","volume-title":"Proceedings of the 31st International Conference on Machine Learning","author":"Graves"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746821"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022967"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10854"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095813"},{"key":"ref7","article-title":"Why does CTC result in peaky behavior?","volume":"abs\/2105.14849","author":"Zeyer","year":"2021","journal-title":"CoRR"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746880"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2186"},{"key":"ref10","article-title":"Differentiable Weighted Finite-State Transducers","author":"Hannun","year":"2020","journal-title":"arXiv:2010.01003 [cs, stat]"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-49127-9_28"},{"article-title":"Revisiting the Entropy Semiring for Neural Speech Recognition","volume-title":"The Eleventh International Conference on Learning Representations","author":"Chang","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404790"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288848"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/5.18626"},{"key":"ref16","first-page":"12 449","article-title":"Wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"CONF","key":"ref17","article-title":"The Kaldi speech recognition toolkit","volume-title":"IEEE 2011 Workshop on Automatic Speech Recognition and Understanding","author":"Povey"},{"key":"ref18","first-page":"8024","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688056"}],"event":{"name":"2024 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2024,12,2]]},"location":"Macao","end":{"date-parts":[[2024,12,5]]}},"container-title":["2024 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10830790\/10830793\/10832327.pdf?arnumber=10832327","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T08:03:12Z","timestamp":1737100992000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832327\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832327","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}