Grapheme to Phoneme Conversion using Deep Neural Networks

Please enable javascript in your browser.

Safari, Arash | 2017

642 Viewed

Type of Document: M.Sc. Thesis
Language: Farsi
Document No: 50332 (19)
University: Sharif University of Technology
Department: Computer Engineering
Advisor(s): Sameti, Hossein
Abstract:
The goal of this research is to convert letter to phoneme using deep neural networks. As the deep neural networks are among the best methods for speech and text processing (The highest accuracy in converting text to letter in English language is obtained by using deep neural networks too.), multilayer deep neural networks are used in this research to increase the accuracy. It should be noted that deep neural networks have not been used for converting text to phoneme in Persian language before. In this research a rule based alignment method based on our preposed rule is presented and achieved an accuracy more than 98%. Several approaches for converting word to grapheme with emphasis on the out of the vocabulary words, were at employed and according to PER criteria on the Farsi Text Corpuse, an accuracy was obtained around 89.13 % which is 4% higher than the best previous methods. Also Deep Neural Network were employed for recognizing kasre_e_ezafe which result in 94% accuracy. A collection of all preposed methods were used to convrt Persian text into phonemes
Keywords:
Texts ; Deep Neural Networks ; Out of Vocabulary Words ; Phonological Sequence ; Large Scale Image Search ; Kasre-e-Ezafe

No TOC