An Efficient Network for Farsi Text to Speech Conversion Using Vowel State

Author

Rasekh, Ehsan ; Eshghi, Mohammad

Author_Institution

Electr. & Comput. Eng. Fac., Shahid Beheshti Univ., Tehran

fYear

2006

fDate

14-17 Nov. 2006

Firstpage

1

Lastpage

4

Abstract

The main problem in Farsi text to speech synthesizers is unwritten short vowels in Farsi orthography. In this paper an ANN is used to determine the phonemes in a Farsi text. The output of this ANN is a new variable called vowel state, instead of a phoneme. Five vowel states are enough to extract pronunciations in a Farsi text, where the number of phonemes is about 30. This reduction of the output causes the reduction of interconnections of the network, considerably. The proposed vowel states approach and the ANN is tested over 2024 words with different percentage of the database as the training set. The 80.31% to 97.34% correct results are achieved using this system

Keywords

learning (artificial intelligence); natural languages; neural nets; speech processing; speech synthesis; ANN; Farsi orthography; artificial neural network; phoneme; pronunciation extraction; text to speech synthesis; training set; vowel state approach; Artificial neural networks; Computer networks; Dictionaries; Helium; Natural languages; Optical computing; Silicon compounds; Speech synthesis; Synthesizers; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

TENCON 2006. 2006 IEEE Region 10 Conference

Conference_Location

Hong Kong

Print_ISBN

1-4244-0548-3

Electronic_ISBN

1-4244-0549-1

Type

conf

DOI

10.1109/TENCON.2006.343934

Filename

4142166