Speech Synthesis for Punjabi Language Using Festival

Journal Title: IOSR Journals (IOSR Journal of Computer Engineering) - Year 2017, Vol 19, Issue 5

Abstract

Processing of digital speech plays an important role in modern speech communication research and applications. The main propose of digital speech is communication which means transmission of messages between human and computer systems. The process of converting the written text into speech is called Text-toSpeech (TTS) and the generation of “synthetic” speech is known as Speech Synthesis. This paper discusses the development of Text-to-Speech system using festival framework for Punjabi language which is in Gurumukhi script. Since festival uses concatenation approach, diphone has been chosen as the basic unit of concatenation for speech synthesis. We defined the phone set and possible number of diphones for Punjabi language. Apart from that configuration of Festival framework on Ubuntu 14.04 Linux is discussed. Recording of nonsense word has been done from which the diphones are extracted for concatenation to produce speech. The aim of this paper is to give the details regarding the manipulations of some files required to add some new language in festival.

Authors and Affiliations

Pansy Nandwani, Dr. Dharam Veer Sharma

Keywords

Related Articles

 CEET: A Compressed Encrypted & Embedded Technique for Digital Image Steganography

 Abstract: In this information era, digital information sharing and transfer plays a vital role and their use has increased exponentially with the development of technology. Thus providing security of data is a topi...

 Design and Simulation of Dct Chip In Vhdl and Application in Watermark Extraction

 Abstract: The paper presented the design, modeling and chip implementation of 2D Discrete Cosine Transform (DCT) domain for copyright protection of images, as digital watermarking chip. Recent improvement in comput...

 A Novel identity based secure distributed data storage scheme

 Abstract: Secure distributed data storage can shift the burden of maintaining a large number of files from the owner to proxy servers. Proxy servers can convert encrypted files for the owner to encrypted files for...

 Optical Character Recognition using Dynamic Memory Image Algorithm

 Abstract : Embedded products have different types of display screens like LCD, Touch screen, CRT etc. For automating the development testing of such devices, we need to recognize the text displayed on it using a ca...

Automatic Detection of Non-Proliferative Diabetic Retinopathy Using Fundus Images

 Abstract: To diagnosis of Diabetic Retinopathy (DR) it is the prime cause of blindness in the working age population of the world. Detection method is proposed to detect dark or red lesions such as microaneurysms a...

Download PDF file
  • EP ID EP385838
  • DOI 10.9790/0661-1905011421.
  • Views 137
  • Downloads 0

How To Cite

Pansy Nandwani, Dr. Dharam Veer Sharma (2017). Speech Synthesis for Punjabi Language Using Festival. IOSR Journals (IOSR Journal of Computer Engineering), 19(5), 14-21. https://europub.co.uk./articles/-A-385838