Influence of language parameters selection on the coarticulation of the phonemes for prosody training in TTS by neural networks

被引：0

作者：

Tucková, J ^{[1
]}

Sebesta, V ^{[1
]}

机构：

[1] Czech Tech Univ, Fac Elect Engn, CR-16635 Prague, Czech Republic

来源：

ARTIFICIAL NEURAL NETS AND GENETIC ALGORITHMS, PROCEEDINGS | 2003年

关键词：

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This contribution describes the influence of the Czech language parameters selection on the coarticulation of the phonemes for the modelling of prosody features by the artificial neural network (ANN) in a text-to-speech (TTS) synthesis. The GUHA method and neural network pruning can be used for this reason. In our work we analyzed the errors between the target and calculated values of F-0 and D from the point of view of the different context of speech units. The context of three phonemes combinations CCC, VVC, VCV, CVV, VCC, CCV, and CVC (C = consonant, V = vowel) were analyzed for the determination of a next improvement of prosody. The qualitative criteria have been found in this contribution.

引用

页码：85 / 90

页数：6

共 50 条

[21] An Electronic Nose Using Neural Networks with Effective Training Data Selection
Charumporn, Bancha
Yoshioka, Michifumi
Fujinaka, Toru
Omatu, Sigeru
Journal of Robotics and Mechatronics, 2003, 15 (04) : 369 - 376
[22] Categorization of large text collections: Feature selection for training neural networks
Manomaisupat, Pensiri
Vrusias, Bogdan
Ahmad, Khurshid
INTELLIGENT DATA ENGINEERING AND AUTOMATED LEARNING - IDEAL 2006, PROCEEDINGS, 2006, 4224 : 1003 - 1013
[23] The influence of relative sample size in training artificial neural networks
Blamire, PA
INTERNATIONAL JOURNAL OF REMOTE SENSING, 1996, 17 (01) : 223 - 230
[24] Selection of relevant engineering seismological parameters with the aid of artificial neural networks
Goldschmidt, Konstantin
Miavaghi, Mani Mohtasham
Sadegh-Azar, Hamid
VDI Berichte, 2022, 2022 (2379): : 451 - 462
[25] Best Parameters Selection of Arrhythmia Classification Using Convolutional Neural Networks
Prawira, Rizqi Hadi
Wibowo, Adi
Yusuf, Ajif Yunizar Pratama
2019 3RD INTERNATIONAL CONFERENCE ON INFORMATICS AND COMPUTATIONAL SCIENCES (ICICOS 2019), 2019,
[26] Automated selection of computed tomography display parameters using neural networks
Zhang, D
Neu, SC
Valentino, DJ
MEDICAL IMAGING: 2001: IMAGE PROCESSING, PTS 1-3, 2001, 4322 : 1912 - 1917
[27] Dynamic selection of model parameters in principal components analysis neural networks
López-Rubio, E
Ortiz-de-Lazcano-Lobato, JM
Vargas-González, MDC
López-Rubio, JM
ECAI 2004: 16TH EUROPEAN CONFERENCE ON ARTIFICIAL INTELLIGENCE, PROCEEDINGS, 2004, 110 : 618 - 622
[28] Learning fused lasso parameters in portfolio selection via neural networks
Stefania Corsaro
Valentina De Simone
Zelda Marino
Salvatore Scognamiglio
Quality & Quantity, 2024, 58 (5) : 4281 - 4299
[29] Subset Selection for Tuning of Hyper-parameters in Artificial Neural Networks
Aki, K. K. Emre
Erkoc, Tugba
Eskil, M. Taner
2017 24TH IEEE INTERNATIONAL CONFERENCE ON ELECTRONICS, CIRCUITS AND SYSTEMS (ICECS), 2017, : 144 - 147
[30] STP-CNN: Selection of transfer parameters in convolutional neural networks
Mallouk, Otmane
Joudar, Nour-Eddine
Ettaouil, Mohamed
EXPERT SYSTEMS, 2024,

← 1 2 3 4 5 →