{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T16:59:15Z","timestamp":1781283555831,"version":"3.54.1"},"reference-count":35,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,3]]},"DOI":"10.1109\/icassp.2016.7472655","type":"proceedings-article","created":{"date-parts":[[2016,6,24]],"date-time":"2016-06-24T01:58:30Z","timestamp":1466733510000},"page":"5130-5134","source":"Crossref","is-referenced-by-count":14,"title":["Robust TTS duration modelling using DNNS"],"prefix":"10.1109","author":[{"given":"Gustav Eje","family":"Henter","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Srikanth","family":"Ronanki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Oliver","family":"Watts","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mirjam","family":"Wester","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhizheng","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Simon","family":"King","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","year":"2014","journal-title":"International Telecommunication Union Radiocommunication Assembly Geneva Switzerland Method for the subjective assessment of intermediate quality level of audio systems"},{"key":"ref32","year":"2011","journal-title":"International Telecommunication Union Telecommunication Standardization Sector Geneva Switzerland Objective measurement of active speech level"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.861820"},{"key":"ref30","first-page":"3","article-title":"Theano: A CPU and GPU math compiler in Python","author":"bergstra","year":"2010","journal-title":"Proc 9th Python in Science Conf"},{"key":"ref35","first-page":"56","article-title":"The effect of filled pauses and speaking rate on speech comprehension in natural, vo-coded and synthetic speech","author":"dall","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref34","first-page":"65","article-title":"A simple sequentially rejective multiple test procedure","volume":"6","author":"holm","year":"1979","journal-title":"Scand J Stat"},{"key":"ref10","article-title":"The HTK Book (for HTK Version 3.4)","author":"young","year":"2006"},{"key":"ref11","author":"huber","year":"2011"},{"key":"ref12","author":"hampel","year":"1986","journal-title":"Robust Statistics The Approach Based on Influence Functions"},{"key":"ref13","first-page":"1504","article-title":"Measuring the perceptual effects of modelling assumptions in speech synthesis using stimuli constructed from repeated natural speech","author":"henter","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1190\/1.3627747"},{"key":"ref15","article-title":"Prosodic analysis of Indian languages and its application to text to speech synthesis","author":"krishnan","year":"2015"},{"key":"ref16","article-title":"Blizzard Challenge 2015: Submission by DONLab, IIT Madras","author":"prakash","year":"2015","journal-title":"Proc Blizzard Challenge Workshop"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"1781","DOI":"10.21437\/Interspeech.2005-3","article-title":"Spontaneous speech: how people really talk and why engineers should care","author":"shriberg","year":"2005","journal-title":"Proc INTERSPEECH"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.21437\/SpeechProsody.2014-72","article-title":"Phonetic variations: Impact of the communicative situation","author":"brognaux","year":"2014","journal-title":"Speech Prosody"},{"key":"ref19","article-title":"Mixture density networks","author":"bishop","year":"1994","journal-title":"Tech Rep NCRG\/94\/004 Neural Computing Research Group Aston University"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1250\/ast.27.349"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1121\/1.395275"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1660155"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2013.2278492"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.04.004"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1176342503"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941031"},{"key":"ref8","first-page":"294","article-title":"The HMM-based speech synthesis system (HTS) version 2.0","author":"zen","year":"2007","journal-title":"Proc SSW6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s12046-011-0048-y"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"581","DOI":"10.21437\/Interspeech.2008-171","article-title":"Robustness of HMM-based speech synthesis","author":"yamagishi","year":"2008","journal-title":"Proc INTERSPEECH"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/5.18626"},{"key":"ref1","article-title":"The Blizzard Challenge 2013","author":"king","year":"2013","journal-title":"Proc Blizzard Challenge Workshop"},{"key":"ref20","first-page":"7962","article-title":"Statistical parametric speech synthesis using deep neural networks","author":"zen","year":"2013","journal-title":"Proc ICASSP"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854321"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178814"},{"key":"ref24","article-title":"Robustifying maximum likelihood estimation","author":"eguchi","year":"2001","journal-title":"Tech Rep Research Memo 802 Institute of Statistical Mathematics"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/85.3.549"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2081980"},{"key":"ref25","article-title":"Emma","author":"austen","year":"2006","journal-title":"LibriVox"}],"event":{"name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Shanghai","start":{"date-parts":[[2016,3,20]]},"end":{"date-parts":[[2016,3,25]]}},"container-title":["2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7465907\/7471614\/07472655.pdf?arnumber=7472655","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,2]],"date-time":"2022-07-02T03:42:13Z","timestamp":1656733333000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7472655\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,3]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icassp.2016.7472655","relation":{},"subject":[],"published":{"date-parts":[[2016,3]]}}}