Speech Processing

There are three main areas in speech processing. They are speech synthesis, speech recognition, and speech coding. In speech synthesis, a machine is developed, which can accept as input a piece of English text and convert it to natural sounding speech. Applications of this method includes speech output from computers, interrogating database from an ordinary telephone, permitting a doctor in a remote location to access medical records stored in a central computer and reading machine from the blind.

In speech recognition a system is produced which can introduce or recognise from any speaker of a given language. the main application areas of a speech recognition system is telephone bankin, direct control of machines by human voice, quality control and so on.

Speech Coding refers to the development of techniques which exploit the redundancy in the speech signal, in order to reduce the number of bits reqired to present the system.