{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T10:37:01Z","timestamp":1757587021200},"reference-count":12,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/icassp.2018.8462473","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T18:24:48Z","timestamp":1537554288000},"page":"5119-5123","source":"Crossref","is-referenced-by-count":6,"title":["Emphatic Speech Prosody Prediction with Deep Lstm Networks"],"prefix":"10.1109","author":[{"given":"Slava","family":"Shechtman","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Moran","family":"Mordechay","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"Hierarchical English Emphatic Speech Synthesis Based on HMM with Limited Training Data","year":"2012","author":"meng","key":"ref4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2003.1318525"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"2138","DOI":"10.21437\/Interspeech.2008-554","article-title":"Two-Stage prosody prediction for emotional text-to-speech synthesis","author":"tang","year":"2008","journal-title":"Proc INTERSPEECH"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-522"},{"key":"ref11","article-title":"crowdMOS: An Approach for Crowdsourcing Mean Opinion Score Studies","author":"ribeiro","year":"2011","journal-title":"Proc IEEE ICASSP"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-930"},{"key":"ref12","article-title":"Emphatic Speech Prosody Prediction with Deep LSTM Networks","author":"shechtman","year":"0","journal-title":"Media files for"},{"key":"ref8","article-title":"Using deep bidirectional recurrent neural networks for prosodic-target prediction in a unit-selection text-to-speech system","author":"fernandez","year":"2015","journal-title":"InterSpeech"},{"journal-title":"WaveNet A Generative Model for Raw Audio","year":"2016","author":"van den oord","key":"ref7"},{"key":"ref2","article-title":"Word-level Emphasis Modelling in HMM-based Speech Synthesis","author":"yu","year":"0","journal-title":"Proc ICASSP-2010"},{"key":"ref9","article-title":"The Prosogram: Semi-Automatic Transcription of Prosody based on a Tonal Perception Model","author":"mertens","year":"2004","journal-title":"Proceedings a\/Speech Prosody"},{"key":"ref1","article-title":"Modeling prominence and emphasis improves unit-selection synthesis","author":"strom","year":"2007","journal-title":"Proceedings of Interspeech"}],"event":{"name":"ICASSP 2018 - 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2018,4,15]]},"location":"Calgary, AB","end":{"date-parts":[[2018,4,20]]}},"container-title":["2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8450881\/8461260\/08462473.pdf?arnumber=8462473","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,2]],"date-time":"2022-09-02T06:49:29Z","timestamp":1662101369000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8462473\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":12,"URL":"https:\/\/doi.org\/10.1109\/icassp.2018.8462473","relation":{},"subject":[],"published":{"date-parts":[[2018,4]]}}}