Speech Recognition and Speech Synthesis

1478 Words3 Pages

Speech Recognition and Speech Synthesis

Speech Recognition.

Speech Recognition is the process by which a computer maps an acoustic speech signal to text. It is different that speech understanding which is the process by which a computer maps an acoustic speech signal to some form of abstract meaning of the speech.

This process depends on the speaker, and how he speaks the language. There are three different systems for the speaker.

* Speaker dependent system.

* Speaker independent system.

* Speaker adaptive system.

Speaker Dependent System.

A speaker dependent system is developed to operate for a single speaker. These systems are usually easier to develop, cheaper to buy and more accurate, but not as flexible as speaker adaptive or speaker independent systems.

Speaker Independent System.

A speaker independent system is developed to operate for any speaker of a particular type like American English, or any other kind of English Language. These systems are the most difficult to develop, most expensive and accuracy is lower than speaker dependent systems. However, they are more flexible.

Speaker Adaptive System.

A speaker adaptive system is developed to adapt its operation to the characteristics of new speakers. It's difficulty lies somewhere between speaker independent and speaker dependent systems.

There are many things that effects the speaker systems. For example The size of vocabulary of a speech recognition system affects the complexity, processing requirements and the accuracy of the system. Some applications only require a few words like numbers, others require very large dictionaries (e.g. dictation machines). There are no established definitions for the size of vocabulary. To make it easy to understand we can say that :-

small vocabulary - tens of words

medium vocabulary - hundreds of words

large vocabulary - thousands of words

very-large vocabulary - tens of thousands of words.

As well as the size of vocabulary effects the speaker system, the way on speaking this words effects too. There are two different ways of speech. continuous speech or isolated-word speech.

Isolated-word Speech:-

An isolated-word system operates on single words at a time - requiring a pause between saying each word. This is the simplest form of recognition to perform because the end points are easier to find and the pronunciation of a word tends not affect others. Thus, because the occurrences of words are more consistent they are easier to recognize.

Continuous Speech:-

A continuous speech system operates on speech in which words are connected together, i.e. not separated by pauses.

Open Document