Affiliations: [a] Department of Electronics and Communication Engineering, Sri Krishna College of Technology, Coimbatore, Tamil Nadu, India
| [b] Department of Electronics and Communication Engineering, K. Ramakrishnan College of Engineering, Trichy, Tamil Nadu, India
| [c] Department of Computer Science and Engineering, R.M.K. College of Engineering and Technology, Thiruvallur, Tamil Nadu, India
| [d] Department of Electronics and Communication Engineering, Chennai Institute of Technology, Chennai, Tamil Nadu, India
| [e] Department of Electronics and Communication Engineering, Kongunadu College of Engineering and Technology, Trichy, Tamil Nadu, India
| [f] Department of Electronics and Communication Engineering, K. Ramakrishnan College of Technology, Trichy, Tamil Nadu, India
Correspondence:
[*]
Corresponding author. Kirthika Natarajan, Department of Electronics and Communication Engineering, Sri Krishna College of Technology, Coimbatore – 641042, Tamil Nadu, India. E-mail: [email protected].
Abstract: This is contrary for Voice impaired people since their speech is tough for others to recognize even by their parents and teachers. Provided if their parents are illiterate. So our TTS system can be used for converting their written text to speech for their illiterate parents and friends around them. Though many methods have been adopted for the concatenation of the basic sound units, the HMM-based approach in modeling the sound is utilized by many researchers in many languages. In this paper, we have tried to implement, text to speech systems of synthesis for a Tamil text uses a phonemic concatenation approach in MATLAB. Instead of utilizing Tamil letters as it is, due to its difficulty in production, Tamil text is transliterated into English then it is converted into intelligible speech. The performance of the output is verified for various examples by changing its parameters, in which the quality of the sound is comparable to that of English text. So the proposed system is utilized for all languages other than Tamil also if it is properly transliterated for limited vocabulary.
Keywords: Phoneme, text normalization, voice impaired, subharmonic ratio, pitch, transliteration
