{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T12:31:03Z","timestamp":1730291463249,"version":"3.28.0"},"reference-count":28,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,5]]},"DOI":"10.1109\/qomex.2018.8463392","type":"proceedings-article","created":{"date-parts":[[2018,9,13]],"date-time":"2018-09-13T21:42:29Z","timestamp":1536874949000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Towards a Neuro-Inspired No-Reference Instrumental Quality Measure for Text-to-Speech Systems"],"prefix":"10.1109","author":[{"given":"Rishabh","family":"Gupta","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anderson","family":"Avila","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tiago H.","family":"Falk","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"ref11","article-title":"Towards perceptual quality modeling of synthesized audiobooks-blizzard challenge 2012","author":"christoph","year":"0","journal-title":"The Blizzard Challenge 2012 Workshop"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"2177","DOI":"10.21437\/Interspeech.2011-570","article-title":"Perceptual Quality Dimensions of Text-to-Speech Systems","author":"hinterleitner","year":"2011","journal-title":"InterSpeech"},{"key":"ref13","article-title":"Is intelligibility still the main problem? a review of perceptual quality dimensions of synthetic speech","author":"hinterleitner","year":"0","journal-title":"ISCA Workshop on Speech Synthesis 2013"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2014.06.003"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/S0042-6989(00)00235-2"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2005.01.050"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.neubiorev.2009.07.008"},{"key":"ref18","first-page":"17","article-title":"Hybrid Optical-Electrical Brain Computer Interfaces, Practices and Possibilities","author":"tomas","year":"2012","journal-title":"Towards Practical Brain-Computer Interfaces"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2008.08.036"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/S0304-3940(03)00027-2"},{"journal-title":"International Telecommunication Union CH-Genf 1994","article-title":"ITU-T recommendation P. 85. A Method for Subjective Performance Assessment of the Quality of Speech Voice Output Devices","year":"0","key":"ref4"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/S0304-3940(01)01970-X"},{"journal-title":"WaveNet A Generative Model for Raw Audio","year":"2016","author":"van den oord","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.2359987"},{"key":"ref5","article-title":"Expectations for assessment techniques applied to speech synthesis","volume":"13","author":"morton","year":"1991","journal-title":"Proceedings of the Institute of Acoustics"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1002\/bltj.20228"},{"journal-title":"Tech Rep ITU-T","article-title":"ITU-T recommendation P. 563: Single-ended method for objective speech quality assessment in narrow-band telephony applications","year":"2004","key":"ref7"},{"journal-title":"Char2Wav End-to-end speech synthesis","year":"2017","author":"sotelo","key":"ref2"},{"key":"ref9","article-title":"Comparison of approaches for instrumentally predicting the quality of text-to-speech systems","author":"sebastian","year":"0","journal-title":"INTERSPEECH 2010"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/S0016-0032(39)90816-1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2392932"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1080\/026870399401957"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"467","DOI":"10.1016\/j.csda.2003.11.020","article-title":"A systematic comparison of methods for combining p- values from independent tests","volume":"47","author":"thomas","year":"2004","journal-title":"Computational Statistics & Data Analysis"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1093\/cercor\/bhn245"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1016\/S1364-6613(00)01816-7","article-title":"Structure and function of auditory cortex: music and speech","volume":"6","author":"robert","year":"2002","journal-title":"Trends in Cognitive Sciences"},{"key":"ref26","first-page":"63","volume":"53","author":"klimesch","year":"2007","journal-title":"EEG alpha oscillations the inhibition-timing hypothesis"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2003.09.049"}],"event":{"name":"2018 Tenth International Conference on Quality of Multimedia Experience (QoMEX)","start":{"date-parts":[[2018,5,29]]},"location":"Cagliari","end":{"date-parts":[[2018,6,1]]}},"container-title":["2018 Tenth International Conference on Quality of Multimedia Experience (QoMEX)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8452069\/8463292\/08463392.pdf?arnumber=8463392","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T08:40:28Z","timestamp":1643186428000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8463392\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,5]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/qomex.2018.8463392","relation":{},"subject":[],"published":{"date-parts":[[2018,5]]}}}