{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T05:42:21Z","timestamp":1769751741445,"version":"3.49.0"},"reference-count":25,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447530","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"6495-6499","source":"Crossref","is-referenced-by-count":4,"title":["Variational Connectionist Temporal Classification for Order-Preserving Sequence Modeling"],"prefix":"10.1109","author":[{"given":"Zheng","family":"Nan","sequence":"first","affiliation":[{"name":"University of New South Wales,School of Electrical Engineering and Telecommunications,Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ting","family":"Dang","sequence":"additional","affiliation":[{"name":"University of New South Wales,School of Electrical Engineering and Telecommunications,Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vidhyasaharan","family":"Sethu","sequence":"additional","affiliation":[{"name":"University of New South Wales,School of Electrical Engineering and Telecommunications,Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Beena","family":"Ahmed","sequence":"additional","affiliation":[{"name":"University of New South Wales,School of Electrical Engineering and Telecommunications,Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10448335"},{"key":"ref3","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"Proc. International Conference on Machine Learning","author":"Kim"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_28"},{"key":"ref5","article-title":"Unsupervised cross-modal alignment of speech and text embedding spaces","volume-title":"Advances in Neural Information Processing Systems","volume":"31","author":"Chung"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.26.041002.131047"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000050"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"issue":"3","key":"ref10","first-page":"235","article-title":"Sequence transduction with recurrent neural networks","volume":"58","author":"Graves","year":"2012","journal-title":"Computer Science"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-862"},{"key":"ref12","article-title":"Auto-encoding variational bayes","volume-title":"Proc. International Conference on Machine learning","author":"Kingma"},{"key":"ref13","article-title":"Learning structured output representation using deep conditional generative models","volume-title":"Advances in Neural Information Processing Systems","volume":"28","author":"Sohn"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2016.7472621"},{"key":"ref15","article-title":"Attention-based models for speech recognition","volume-title":"Advances in Neural Information Processing Systems","volume":"28","author":"Chorowski"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054663"},{"key":"ref18","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"},{"key":"ref19","article-title":"A recurrent latent variable model for sequential data","volume-title":"Advances in Neural Information Processing Systems","volume":"28","author":"Chung"},{"key":"ref20","first-page":"1672","article-title":"Variational attention for sequence-to-sequence models","volume-title":"Proc. International Conference on Computational Linguistics","author":"Bahuleyan"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3390\/e23101277"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1222"},{"key":"ref23","first-page":"4531","article-title":"Deep graph random process for relational-thinking-based speech recognition","volume-title":"Proc. International Conference on Machine Learning","author":"Huang"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3409383"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1002\/9781119387596"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10447530.pdf?arnumber=10447530","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:46:27Z","timestamp":1722577587000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447530\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447530","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}