{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T16:02:52Z","timestamp":1730304172372,"version":"3.28.0"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,22]],"date-time":"2023-10-22T00:00:00Z","timestamp":1697932800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,22]],"date-time":"2023-10-22T00:00:00Z","timestamp":1697932800000},"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":[[2023,10,22]]},"DOI":"10.1109\/waspaa58266.2023.10248099","type":"proceedings-article","created":{"date-parts":[[2023,9,15]],"date-time":"2023-09-15T17:31:37Z","timestamp":1694799097000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Differentiable Representation of Warping Based on Lie Group Theory"],"prefix":"10.1109","author":[{"given":"Atsushi","family":"Miyashita","sequence":"first","affiliation":[{"name":"Nagoya University,Graduate School of Informatics"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomoki","family":"Toda","sequence":"additional","affiliation":[{"name":"Nagoya University,Information Technology Center"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","first-page":"9","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3047262"},{"key":"ref14","first-page":"23","article-title":"End-to-end adversarial text-to-speech","author":"jeff","year":"2021","journal-title":"ICLRE"},{"key":"ref11","first-page":"5530","article-title":"Conditional variational autoen-coder with adversarial learning for end-to-end text-to-speech","volume":"139","author":"kim","year":"2021","journal-title":"Proc ICML"},{"key":"ref10","first-page":"8067","article-title":"Glow-tts: A generative flow for text-to-speech via monotonic alignment search","volume":"33","author":"kim","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054106"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1972.8727"},{"key":"ref17","first-page":"43","article-title":"Generating sequences with recurrent neural networks","author":"graves","year":"2013"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683282"},{"key":"ref19","first-page":"16","article-title":"Monotonic chunkwise attention","author":"chiu","year":"2018","journal-title":"ICLRE"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462020"},{"key":"ref24","first-page":"27403","article-title":"DARPA TIMIT acoustic-phonetic continous speech corpus CD-ROM. NIST speech disc 1-1.1","author":"garofolo","year":"1993"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1999.759778"},{"key":"ref25","first-page":"15","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053915"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54375-8"},{"article-title":"Melnet: A generative model for audio in the frequency domain","year":"2019","author":"vasquez","key":"ref21"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/5.18626"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.848881"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2013.2251852"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1978.1163055"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3001456"},{"key":"ref6","first-page":"1043","article-title":"Melgeneralized cepstral analysis – a unified approach to speech spectral estimation","author":"tokuda","year":"1994","journal-title":"ICSLP"},{"key":"ref5","first-page":"894","article-title":"Soft-DTW: a differentiable loss function for time-series","volume":"70","author":"cuturi","year":"2017","journal-title":"Proc ICML"}],"event":{"name":"2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","start":{"date-parts":[[2023,10,22]]},"location":"New Paltz, NY, USA","end":{"date-parts":[[2023,10,25]]}},"container-title":["2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10248019\/10248047\/10248099.pdf?arnumber=10248099","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,2]],"date-time":"2023-10-02T17:40:55Z","timestamp":1696268455000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10248099\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,22]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/waspaa58266.2023.10248099","relation":{},"subject":[],"published":{"date-parts":[[2023,10,22]]}}}