{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T16:00:29Z","timestamp":1759939229119},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096751","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":3,"title":["Speech Modeling with a Hierarchical Transformer Dynamical VAE"],"prefix":"10.1109","author":[{"given":"Xiaoyu","family":"Lin","sequence":"first","affiliation":[{"name":"Univ. Grenoble Alpes,Inria Grenoble Rhône-Alpes,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoyu","family":"Bie","sequence":"additional","affiliation":[{"name":"Univ. Grenoble Alpes,Inria Grenoble Rhône-Alpes,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Simon","family":"Leglaive","sequence":"additional","affiliation":[{"name":"IETR (UMR CNRS 6164),CentraleSupélec,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Laurent","family":"Girin","sequence":"additional","affiliation":[{"name":"Univ. Grenoble Alpes,CNRS, Grenoble-INP, GIPSA-Lab,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xavier","family":"Alameda-Pineda","sequence":"additional","affiliation":[{"name":"Univ. Grenoble Alpes,Inria Grenoble Rhône-Alpes,France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances Neural Inform Process Syst"},{"key":"ref12","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","author":"bengio","year":"2015","journal-title":"Advances Neural Inform Process Syst"},{"key":"ref15","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"arXiv preprint arXiv 2010 11419"},{"key":"ref14","article-title":"BERT: Pre-training of deep bidirectional Transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proc NAACL-HLT Conf"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.2.270"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3207349"},{"key":"ref2","article-title":"Stochastic backpropagation and approximate inference in deep generative models","author":"rezende","year":"2014","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref1","article-title":"Auto-encoding variational Bayes","author":"kingma","year":"2014","journal-title":"Proc Int Conf Learn Repres (ICLR)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2008.04-08-771"},{"key":"ref16","article-title":"HiT-DVAE: Human motion generation via Hierarchical Transformer Dynamical VAE","author":"bie","year":"2022","journal-title":"arXiv preprint arxiv 2204 01565"},{"key":"ref19","article-title":"CSR-I (WSJ0) Sennheiser LDC93S6B","author":"garofolo","year":"1993","journal-title":"Philadelphia Linguistic Data Consortium"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2011.2119315"},{"key":"ref24","article-title":"SGDR: Stochastic gradient de-scent with warm restarts","author":"loshchilov","year":"2017","journal-title":"Proc Int Conf Learn Repres (ICLR)"},{"key":"ref23","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Repres (ICLR)"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref25","article-title":"SDR – Half-baked or well done?","author":"le roux","year":"2019","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process (ICASSP)"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-159"},{"key":"ref22","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2019","journal-title":"Proc Int Conf Learn Repres (ICLR)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747180"},{"key":"ref28","article-title":"High fidelity speech synthesis with adversarial networks","author":"bi?kowski","year":"2020","journal-title":"Proc Int Conf Learn Repres (ICLR) virtual conference"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref29","article-title":"Deep Speech 2: End-to-end speech recognition in English and Mandarin","author":"amodei","year":"2016","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-256"},{"key":"ref7","article-title":"Unsupervised learning of disentangled and interpretable representations from sequential data","author":"hsu","year":"2017","journal-title":"Advances Neural Inform Process Syst"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053164"},{"key":"ref4","article-title":"Deep Kalman filters","author":"krishnan","year":"2015","journal-title":"arXiv preprint arXiv 1511 05271"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1561\/2200000089"},{"key":"ref6","article-title":"Sequential neural models with stochastic layers","author":"fraccaro","year":"2016","journal-title":"Advances Neural Inform Process Syst"},{"key":"ref5","article-title":"A recurrent latent variable model for sequential data","author":"chung","year":"2015","journal-title":"Advances Neural Inform Process Syst"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096751.pdf?arnumber=10096751","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:06:07Z","timestamp":1700507167000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096751\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096751","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}