{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:30:17Z","timestamp":1776889817352,"version":"3.51.2"},"reference-count":30,"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\/icassp49357.2023.10096255","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":6,"title":["Investigating Content-Aware Neural Text-to-Speech MOS Prediction Using Prosodic and Linguistic Features"],"prefix":"10.1109","author":[{"given":"Alexandra","family":"Vioni","sequence":"first","affiliation":[{"name":"Samsung Electronics,Innoetics,Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Georgia","family":"Maniati","sequence":"additional","affiliation":[{"name":"Samsung Electronics,Innoetics,Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nikolaos","family":"Ellinas","sequence":"additional","affiliation":[{"name":"Samsung Electronics,Innoetics,Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"June","family":"Sig Sung","sequence":"additional","affiliation":[{"name":"Samsung Electronics,Mobile eXperience Business,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Inchul","family":"Hwang","sequence":"additional","affiliation":[{"name":"Samsung Electronics,Mobile eXperience Business,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aimilios","family":"Chalamandaris","sequence":"additional","affiliation":[{"name":"Samsung Electronics,Innoetics,Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pirros","family":"Tsiakoulis","sequence":"additional","affiliation":[{"name":"Samsung Electronics,Innoetics,Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746395"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2013"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-439"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-970"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2464"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2382"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747222"},{"key":"ref2","article-title":"Improving Instrumental Quality Prediction Performance for the Blizzard Challenge","author":"falk","year":"2008","journal-title":"Proc Blizzard Challenge Workshop"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.883177"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10022"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10262"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10922"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2021-32"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-linguistics-011718-012503"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413604"},{"key":"ref26","article-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","author":"devlin","year":"2019","journal-title":"Proc NAACL-HLT"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2530"},{"key":"ref20","article-title":"The LJ Speech Dataset","author":"ito","year":"2017"},{"key":"ref22","article-title":"Accurate Short-term Analysis of the Fundamental Frequency and the Harmonics-to-noise Ratio of a Sampled Sound","volume":"17","author":"boersma","year":"1993","journal-title":"Proc Institute of Phonetic Sciences"},{"key":"ref21","article-title":"Expressive Speech Synthesis for Storytelling: the INNOETICS’ entry to the Blizzard Challenge 2016","author":"raptis","year":"2016","journal-title":"Proc Blizzard Challenge Workshop"},{"key":"ref28","article-title":"MPNet: Masked and Permuted Pre-training for Language Understanding","volume":"33","author":"song","year":"2020"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref29","article-title":"Non-Attentive Tacotron: Robust and Controllable Neural TTS Synthesis Including Unsupervised Duration Modeling","author":"shen","year":"2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2003"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-28"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413877"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-847"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2005-72"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1802"},{"key":"ref5","article-title":"AutoMOS: Learning a non-intrusive assessor of naturalness-of-speech","author":"patton","year":"2016","journal-title":"Proc NIPS"}],"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\/10096255.pdf?arnumber=10096255","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:09:11Z","timestamp":1700507351000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096255\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096255","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}