Neural networks in text-to-speech systems for the Greek language
Neural networks in text-to-speech systems for the Greek language
复制标题
希腊语文本转语音系统中的神经网络
DOI：
10.1109/melcon.2000.879998
复制
发表时间：
2000
期刊：
影响因子：
--
通讯作者：
A. Stafylopatis
中科院分区：
文献类型：
--
作者：
T. Falas;A. Stafylopatis
本文介绍了使用神经网络的文本到语音系统的希腊语的实验研究的结果。特别是，神经网络被用于文本到音素的转换，在那里它们表现出优异的性能。它表明，即使是一个小的网络可以捕捉到显着部分的希腊发音，以及吸收许多的不规则性。研究结果表明，在一个完整的文本到语音系统的希腊语的文本到音素阶段，可以实现在真实的时间与简单的神经网络架构。性能方面，正确识别电子形式的希腊文本中的音素，是非常好的。
This paper presents the results of an experimental study for the use of neural networks in text-to-speech systems for the Greek language. In particular, neural networks are employed in text-to-phonemes conversion, where they demonstrate excellent performance. It is shown that even a small network can capture a significant portion of the regularities in the Greek pronunciation as well as absorb many of the irregularities. The results of the study show that the text-to-phonemes phase in a complete text-to-speech system for the Greek language can be implemented in real time with simple neural network architectures. The performance, with regards to the correct recognition of phonemes taken from Greek text in electronic form, is very good to excellent.