1 |
Wavebender GAN: An architecture for phonetically meaningful speech manipulation ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
The speech synthesis phoneticians need is both realistic and controllable ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
The speech synthesis phoneticians need is both realistic and controllable ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
PROMIS: a statistical-parametric speech synthesis system with prominence control via a prominence network
|
|
Malisz, Zofia; Berthelsen, Harald; Beskow, Jonas; Gustafson, Joakim. - : KTH, Tal, musik och hörsel, TMH, 2019. : KTH, Tal-kommunikation, 2019. : STTS – Södermalms talteknologiservice AB, 2019. : Vienna, 2019
|
|
Abstract:
We implement an architecture with explicit prominence learning via a prominence network in Merlin, a statistical-parametric DNN-based text-to-speech system. We build on our previous results that successfully evaluated the inclusion of an automatically extracted, speech-based prominence feature into the training and its control at synthesis time. In this work, we expand the PROMIS system by implementing the prominence network that predicts prominence values from text. We test the network predictions as well as the effects of a prominence control module based on SSML-like tags. Listening tests for the complete PROMIS system, combining a prominence feature, a prominence network and prominence control, show that it effectively controls prominence in a diagnostic set of target words. The tests also show a minor negative impact on perceived naturalness, relative to baseline, exerted by the two prominence tagging methods implemented in the control module. ; QC 20201020
|
|
Keyword:
Computer Systems; Datorsystem
|
|
URL: http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-283137
|
|
BASE
|
|
Hide details
|
|
5 |
Modern speech synthesis for phonetic sciences : A discussion and an evaluation
|
|
|
|
BASE
|
|
Show details
|
|
6 |
The speech synthesis phoneticians need is both realistic and controllable
|
|
Malisz, Zofia; Henter, Gustav Eje; Valentini-Botinhao, Cassia. - : KTH, Tal, musik och hörsel, TMH, 2019. : KTH, Tal-kommunikation, 2019. : The Centre for Speech Technology, The University of Edinburgh, UK, 2019. : Stockholm, 2019
|
|
BASE
|
|
Show details
|
|
10 |
The ALICO corpus : analysing the active listener
|
|
Wagner, Petra; Kopp, Stefan; Włodarczak, Marcin. - : KTH, Tal-kommunikation, 2016. : Saarland University, Germany, 2016. : Stockholms Universitet, 2016. : Bielefeld University, 2016. : Universidade Nova de Lisboa, 2016
|
|
BASE
|
|
Show details
|
|
12 |
Voicing in Polish: interactions with lexical stress and focus
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Speech rhythm variability in Polish and English: a study of interaction between rhythmic levels
|
|
Malisz, Zofia. - : Faculty of English, Adam Mickiewicz University, 2013
|
|
BASE
|
|
Show details
|
|
18 |
Prosodic Characteristics of Feedback Expressions in Distracted and Non-distracted Listeners ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Prosodic Characteristics of Feedback Expressions in Distracted and Non-distracted Listeners ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|