Implementation of Text-To-Speech for Real Time Embedded System Using Raspberry Processor
The real time hardware implementation of Text-To-Speech system has been drawing attention of the research community due to its various real time applications. These include reading aids for the blind, talking aid for the vocally handicapped and training aids and other commercial applications. All these applications demand the real time embedded platform to meet the real time specifications such as speed, power, space requirements etc. In this context the embedded processor ARM has been chosen as hardware platform to implement Text-To-Speech conversion. This conversion needs algorithms to perform various operations like parts of speech tagging, phrase marking, word to phoneme conversion and clustergen synthesis. We are using Raspberry Pi, a credit card–sized single-board Processor developed in the UK by the Raspberry Pi Foundation for the implementation.
An embedded system is a dedicated computer system designed for one or two specific functions. This system is embedded as a part of a complete device system that includes hardware, such as electrical and mechanical components. The embedded system is unlike the general-purpose computer, which is engineered to manage a wide range of processing tasks. Because an embedded system is engineered to perform certain tasks only, design engineers may optimize size, cost, power consumption, reliability and performance. Embedded systems are typically produced on broad scales and share functionalities across a variety of environments and applications. Text-to-speech (TTS) is the problem of Automatic conversion of text into speech that Resembles, as closely as possible, a native speaker of the language reading that text . In TTS Systems an arbitrary text is converted into speech which can be heard out loud.
The proposed method is used to overcome the drawback present in existing method. The design of this project involves text to speech. Here whatever we are giving input from any keyboard corresponding output will get in the form of voice means speech. The development board with ARM architecture is selected as the hardware platform. Start-up codes, OS kernel and user’s application programs are together stored in a NAND FLASH. Application programs run in 64MB SDRAM, which can also be used as the room of various data and the stack. The processor at the heart of the Raspberry Pi system is a Broadcom BCM2836 system-on-chip (SoC) multimedia processor. This means that the vast majority of the system’s components, including its central and graphics processing units along with the audio and communications hardware, are built onto that single component hidden beneath the 256 MB memory chip at the centre of the board. It’s not just this SoC design that makes the BCM2836 different to the processor found in your desktop or laptop, however. It also uses a different instruction set architecture (ISA), known as ARM.
The paper described a way of implementing the text to speech system on ARM microcontroller. Among different speech synthesizing algorithms CLUSTERGEN synthesis is chosen for implementing a real time text to speech system. The results of the implementation are presented. These results shows that the x86 based implementation and ARM based implementation are very close. From the results it can be concluded that a complete low cost real time embedded system can be built with the implementation presented in the paper. This embedded system can be used in many applications like reading aid for the visually disabled persons, talking aid for vocally handicapped.
 Shin, C. and Sproat, R. “Issues in text-to-speech conversion for Mandarin”, Computational Linguistics and Chinese Language Processing, pp. 35-82, August 1996.  The FLITE website. [Online]. Available :http://www.speech.cs.cmu.edu/flite/  Taylor, P. and Black, A. “ Assigning Phrase Breaks from part-ofspeech Sequences” Computer Speech and Language 12, 99-117,1998