{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T08:04:41Z","timestamp":1764403481574,"version":"build-2065373602"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,8,31]],"date-time":"2025-08-31T00:00:00Z","timestamp":1756598400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,31]],"date-time":"2025-08-31T00:00:00Z","timestamp":1756598400000},"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":[[2025,8,31]]},"DOI":"10.1109\/mlsp62443.2025.11204240","type":"proceedings-article","created":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T17:15:52Z","timestamp":1761326152000},"page":"1-6","source":"Crossref","is-referenced-by-count":1,"title":["Diffusion-Based Connectionist Temporal Classification"],"prefix":"10.1109","author":[{"given":"Jen-Tzung","family":"Chien","sequence":"first","affiliation":[{"name":"Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University,Taiwan"}]},{"given":"Chia-Kai","family":"Yeh","sequence":"additional","affiliation":[{"name":"Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University,Taiwan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2197156"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref3","article-title":"Sequence transduction with recurrent neural networks","author":"Graves","year":"2012","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3407533"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-675"},{"key":"ref7","article-title":"Align-refine: Nonautoregressive speech recognition via iterative realignment","author":"Chi","year":"2020","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"Mask CTC: Non-autoregressive end-toend ASR with CTC and mask predict","author":"Higuchi","year":"2020","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-545"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746770"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10446807"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10887605"},{"key":"ref13","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. of International Conference on Machine Learning","author":"Sohl-Dickstein","year":"2015"},{"key":"ref14","first-page":"6840","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref15","article-title":"Diffusion models beat GANs on image synthesis","author":"Dhariwal","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref16","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"Proc. of International Conference on Learning Representations","author":"Song","year":"2021"},{"key":"ref17","article-title":"Grad-TTS: A diffusion probabilistic model for text-tospeech","volume-title":"Proc. of International Conference on Machine Learning","author":"Popov","year":"2021"},{"key":"ref18","first-page":"11119","article-title":"Guided-TTS: A diffusion model for text-to-speech via classifier guidance","volume-title":"Proc. of International Conference on Machine Learning","author":"Kim","year":"2022"},{"key":"ref19","first-page":"12454","article-title":"Argmax flows and multinomial diffusion: Learning categorical distributions,","author":"Hoogeboom","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref20","first-page":"17981","article-title":"Structured denoising diffusion models in discrete statespaces","author":"Austin","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref21","first-page":"4328","article-title":"Diffusion-LM improves controllable text generation","author":"Li","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref22","article-title":"Diffuseq: Sequence to sequence text generation with diffusion models","volume-title":"Proc. of International Conference on Learning Representations","author":"Gong","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1090\/S0002-9904-1954-09848-8"},{"key":"ref24","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. of International Conference on Machine Learning","author":"Radford","year":"2023"},{"key":"ref25","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"Baevski","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref29","article-title":"Common Voice: A massively-multilingual speech corpus","volume-title":"Proc. of Language Resources and Evaluation Conference","author":"Ardila","year":"2020"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1898"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446258"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781107295360"},{"key":"ref33","article-title":"Discrete diffusion modeling by estimating the ratios of the data distribution","volume-title":"Proc. of International Conference on Machine Learning","author":"Lou","year":"2024"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687925"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-4006"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888688"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10890818"},{"key":"ref38","article-title":"Patched denoising diffusion models for high-resolution image synthesis","volume-title":"Proc. of International Conference on Learning Representations","author":"Ding","year":"2024"}],"event":{"name":"2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP)","start":{"date-parts":[[2025,8,31]]},"location":"Istanbul, Turkiye","end":{"date-parts":[[2025,9,3]]}},"container-title":["2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11204201\/11204202\/11204240.pdf?arnumber=11204240","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T18:37:32Z","timestamp":1762367852000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11204240\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,31]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/mlsp62443.2025.11204240","relation":{},"subject":[],"published":{"date-parts":[[2025,8,31]]}}}