{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T05:41:59Z","timestamp":1764222119949,"version":"3.46.0"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/sped67700.2025.11251920","type":"proceedings-article","created":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T19:00:27Z","timestamp":1764183627000},"page":"69-74","source":"Crossref","is-referenced-by-count":0,"title":["Latent Insights: Exploring Phoneme Diversity in Natural and Synthetic Speech through Latent Representations"],"prefix":"10.1109","author":[{"given":"Diptasree","family":"Debnath","sequence":"first","affiliation":[{"name":"University College Dublin,School of Computer Science,Dublin,Ireland"}]},{"given":"Helard Becerra","family":"Martinez","sequence":"additional","affiliation":[{"name":"University College Dublin,School of Computer Science,Dublin,Ireland"}]},{"given":"Andrew","family":"Hines","sequence":"additional","affiliation":[{"name":"University College Dublin,School of Computer Science,Dublin,Ireland"}]}],"member":"263","reference":[{"issue":"97","key":"ref1","first-page":"1","article-title":"Scaling speech technology to 1,000+ languages","volume":"25","author":"Pratap","year":"2024","journal-title":"Journal of Machine Learning Research"},{"key":"ref2","first-page":"28 492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Radford"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLPRO.2025.3530270"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/SynData4GenAI.2024-21"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/WNYIPW.2019.8923082"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3537674.3554742"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/SpeechProsody.2022-91"},{"key":"ref9","article-title":"A survey on neural speech synthesis","author":"Tan","year":"2021","journal-title":"arXiv preprint arXiv:2106.15561"},{"key":"ref10","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"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3207050"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707705"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747162"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3207050"},{"key":"ref16","first-page":"58","article-title":"Dinosr: Self-distillation and online clustering for self-supervised speech representation learning","volume":"36","author":"Liu","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2131"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/AICS60730.2023.10470644"},{"key":"ref19","first-page":"83","article-title":"Domain-informed probing of wav2vec 2.0 embeddings for phonetic features","volume-title":"Proceedings of the 19th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology","author":"Cormac English"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1985"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"International Conference on Machine Learning (ICML). JMLR-JOURNAL MACHINE LEARNING RESEARCH","author":"Kim","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"article-title":"Fullstop: Multilingual deep models for punctuation prediction","volume-title":"Proceedings of the Swiss Text Analytics Conference 2021","author":"Guhr","key":"ref24"},{"issue":"3","key":"ref25","first-page":"192","article-title":"Prosodylab-aligner: A tool for forced alignment of laboratory speech","volume":"39","author":"Gorman","year":"2011","journal-title":"Canadian Acoustics"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1121\/1.1908022"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX51781.2021.9465410"}],"event":{"name":"2025 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)","start":{"date-parts":[[2025,10,19]]},"location":"Cluj-Napoca, Romania","end":{"date-parts":[[2025,10,22]]}},"container-title":["2025 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11251505\/11251597\/11251920.pdf?arnumber=11251920","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T05:37:30Z","timestamp":1764221850000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11251920\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/sped67700.2025.11251920","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}