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

[1] Selecting prosody parameters for unit selection based Chinese TTS
Dong, MH
Lua, KT
Xu, J
NATURAL LANGUAGE PROCESSING - IJCNLP 2004, 2005, 3248 : 272 - 279
[2] Using neural networks to model prosody in Czech TTS system Epos
Horák, P
Adámek, J
Sobe, D
TEXT, SPEECH AND DIALOGUE, PROCEEDINGS, 2004, 3206 : 339 - 345
[3] THE INFLUENCE OF A MUSICAL TRAINING ON THE PERCEPTION OF PROSODY OF A FOREIGN LANGUAGE: AN EXPLORATORY STUDY
Degrave, Pauline
Rasier, Laurent
Hiligsmann, Philippe
NEDERLANDS IN HET PERSPECTIEF VAN UITSPRAAKVERWERVING EN CONTRASTIEVE TAALKUNDE, 2011, 2 : 83 - 99
[4] The Use of Neural Networks to Improve the Recognition Accuracy of Explosive and Unvoiced Phonemes in Uzbek Language
Musaev, Muhammadjon
Khujayorov, Ilyos
Ochilov, Marmon
2020 INFORMATION COMMUNICATION TECHNOLOGIES CONFERENCE (ICTC), 2020, : 231 - 234
[5] Efficient training of large neural networks for language modeling
Schwenk, H
2004 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-4, PROCEEDINGS, 2004, : 3059 - 3064
[6] A training data selection in on-line training for multilayer neural networks
Hara, K
Nakayama, K
Kharaf, AAM
IEEE WORLD CONGRESS ON COMPUTATIONAL INTELLIGENCE, 1998, : 2247 - 2252
[7] Selection of training data for neural networks by a genetic algorithm
Reeves, CR
Taylor, SJ
PARALLEL PROBLEM SOLVING FROM NATURE - PPSN V, 1998, 1498 : 633 - 642
[8] Submodular Batch Selection for Training Deep Neural Networks
Joseph, K. J.
Teja, Vamshi R.
Singh, Krishnakant
Balasubramanian, Vineeth N.
PROCEEDINGS OF THE TWENTY-EIGHTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2019, : 2677 - 2683
[9] On data selection for training wind forecasting neural networks
Homsi Goulart, Antonio Jose
de Camargo, Ricardo
COMPUTERS & GEOSCIENCES, 2021, 155
[10] The　Influence　of　Training　Quality　on　the　Performance　of　Neural　Networks
Jiang Lin Qu Liangsheng Chen Tao Institute of Diagnostics & Cybernetics Xi′an Jiaotong University
International Journal of Plant Engineering and Management, 1996, (01) : 29 - 37

← 1 2 3 4 5 →