{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:50:23Z","timestamp":1730231423342,"version":"3.28.0"},"reference-count":31,"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\/icasspw62465.2024.10669904","type":"proceedings-article","created":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T18:23:22Z","timestamp":1725992602000},"page":"858-862","source":"Crossref","is-referenced-by-count":0,"title":["Exploring the Multidimensional Representation of Unidimensional Speech Acoustic Parameters Extracted by Deep Unsupervised Models"],"prefix":"10.1109","author":[{"given":"Maxime","family":"Jacquelin","sequence":"first","affiliation":[{"name":"Univ. Grenoble Alpes, CNRS, Grenoble INP, GIPSA-Lab,Grenoble,France,F-38000"}]},{"given":"Ma\u00ebva","family":"Garnier","sequence":"additional","affiliation":[{"name":"Univ. Grenoble Alpes, CNRS, Grenoble INP, GIPSA-Lab,Grenoble,France,F-38000"}]},{"given":"Laurent","family":"Girin","sequence":"additional","affiliation":[{"name":"Univ. Grenoble Alpes, CNRS, Grenoble INP, GIPSA-Lab,Grenoble,France,F-38000"}]},{"given":"R\u00e9my","family":"Vincent","sequence":"additional","affiliation":[{"name":"Vogo,Bernin,France,F-38190"}]},{"given":"Olivier","family":"Perrotin","sequence":"additional","affiliation":[{"name":"Univ. Grenoble Alpes, CNRS, Grenoble INP, GIPSA-Lab,Grenoble,France,F-38000"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1515\/9783110873429"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1044\/jshr.1403.565"},{"article-title":"Auto-encoding variational bayes","volume-title":"Int. Conf. on Learning Representations","author":"Kingma","key":"ref3"},{"key":"ref4","first-page":"6306","article-title":"Neural discrete representation learning","volume-title":"Advances in Neural Information Processing Systems","author":"Van Der Oord"},{"key":"ref5","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, virtual conf","author":"Baevski"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref7","first-page":"1336","article-title":"On generative spoken language modeling from raw audio","volume":"9","author":"Lakhotia","year":"2021","journal-title":"Trans. of the Association for Computational Linguistics"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2021-22"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1830"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1769"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1183"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-349"},{"key":"ref13","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","volume-title":"Int. Conf. on Machine Learning","author":"Wang"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683623"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1426"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3390\/info13030102"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-759"},{"key":"ref18","first-page":"21927","article-title":"Self-supervised models of audio effectively explain human cortical responses to speech","volume-title":"Int. Conf. on Machine Learning","author":"Vaidya"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2023.02.005"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-475"},{"article-title":"CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit (version 0.92)","year":"2019","author":"Yamagishi","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/SpeechProsody.2020-152"},{"article-title":"Adam: A method for stochastic optimization","volume-title":"Int. Conf. on Learning Representations","author":"Kingma","key":"ref23"},{"key":"ref24","first-page":"1","article-title":"Notes on the use of variational autoencoders for speech and audio spectrogram modeling","volume-title":"Int. Conf. on Digital Audio Effects","author":"Girin"},{"article-title":"\u03b2-VAE: Learning basic visual concepts with a constrained variational framework","volume-title":"Int. Conf. on Learning Representations","author":"Higgins","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3758\/s13428-018-1095-7"},{"key":"ref27","first-page":"341","article-title":"Praat, a system for doing phonetics by computer","volume":"5","author":"Boersma","year":"2001"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvoice.2003.12.010"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1121\/1.2208451"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10865"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/JEP.2022-83"}],"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\/10669904.pdf?arnumber=10669904","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T17:29:40Z","timestamp":1726075780000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10669904\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icasspw62465.2024.10669904","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}