{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T05:34:29Z","timestamp":1767850469117,"version":"3.49.0"},"reference-count":41,"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\/icassp49357.2023.10096796","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":15,"title":["Speaker-Independent Acoustic-to-Articulatory Speech Inversion"],"prefix":"10.1109","author":[{"given":"Peter","family":"Wu","sequence":"first","affiliation":[{"name":"University of California,Berkeley"}]},{"given":"Li-Wei","family":"Chen","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"Cheol Jun","family":"Cho","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"Louis","family":"Goldstein","sequence":"additional","affiliation":[{"name":"University of Southern California"}]},{"given":"Alan W","family":"Black","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"Gopala K.","family":"Anumanchipalli","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}]}],"member":"263","reference":[{"key":"ref35","article-title":"Chunked autoregressive gan for conditional waveform synthesis","author":"morrison","year":"2022","journal-title":"ICLRE"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3168"},{"key":"ref34","author":"rumelhart","year":"1986","journal-title":"Learning Internal Representations by Error Propagation"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1159\/000261913"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11164"},{"key":"ref36","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","author":"kong","year":"2020","journal-title":"NeurIPS"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2004-410"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref33","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"chung","year":"2014","journal-title":"NeurIPS"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1121\/1.4987629"},{"key":"ref32","article-title":"SpeechBrain: A general-purpose speech toolkit","author":"ravanelli","year":"2021"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-316"},{"key":"ref2","article-title":"Neural analysis and synthesis: Reconstructing speech from self-supervised representations","author":"choi","year":"2021","journal-title":"NeurIPS"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcomdis.2022.106213"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3390\/app11199056"},{"key":"ref38","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1386","article-title":"Montreal forced aligner: Trainable text-speech alignment using kaldi","author":"mcauliffe","year":"2017","journal-title":"InterSpeech"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746125"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1429"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2012-263"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133218"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2018.04.031"},{"key":"ref26","article-title":"The CMU Arctic speech databases","author":"kominek","year":"2004","journal-title":"Fifth ISCA workshop on speech synthesis"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413742"},{"key":"ref20","article-title":"Autoregressive articulatory wavenet flow for speaker-independent acoustic-to-articulatory inversion","author":"bozorg","year":"2021","journal-title":"SPED"},{"key":"ref41","article-title":"Espnet2-tts: Extending the edge of tts research","author":"hayashi","year":"2021","journal-title":"arXiv preprint arXiv 2110 07058"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1375"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413625"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10892"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016-31"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwx105"},{"key":"ref8","article-title":"The mocha-timit articulatory database","author":"wrench","year":"1999"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-009-2037-8_7"},{"key":"ref9","article-title":"A multi-channel\/multi-speaker articulatory database for continuous speech recognition research","author":"wrench","year":"2000","journal-title":"PHONUS"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1119-1"},{"key":"ref3","article-title":"Speech Resynthesis from Discrete Disentan-gled Self-Supervised Representations","author":"polyak","year":"2021","journal-title":"InterSpeech"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1121\/1.386780"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/S0095-4470(19)30318-3"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-179"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"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\/10096796.pdf?arnumber=10096796","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T18:57:02Z","timestamp":1700506622000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096796\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096796","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}