Sei sulla pagina 1di 23

A persons style of speaking.

The speech signal is an acoustic sound pressure wave that originates by exiting of air from vocal tract and voluntary movement of anatomical structure.

Speech processing done by


Feature extraction,& Feature matching

It can be considered as an acoustic filtering operation. It has two phases

Training phase Testing phase

Done by manipulating the input audio signal.

What we see is that voice analysis is done after the voice input is taken through a microphone from user. The algorithms are designed such that it involves the manipulation of the signal and at different levels.

It consists of two distinguished phases


First is training session. Second is operation session or testing phase.

Types are
LPC (Linear Predictive Coding), MFCC

(Mel Frequency Coefficient),& DTW(Dynamic Time Warping).

Cepstrum

Of all the algorithms that have been mentioned above. We see that the last algorithm that is the MFCC (Mel Frequency Cepstrum Coefficient) Algorithm is the best suited algorithm due to its functionality and its ability to function in this context.
MFCC are commonly used as feature in speech recognition systems, such as the systems which can automatically recognize numbers on a phone.

They are also common in speaker recognition ,which is the task of recognizing people from their voices. MFCCs are also increasingly finding uses in music information retrieval applications such as genre classification, audio similarity measures, etc. Thus we see that this algorithm finds its use in various applications due to its less error rate and more efficiency and more reliability.

Detecting the word Forward

Detecting the word Left

Detecting the word Turn

It will be very useful for those who are physically handicapped they can give voice commands to the robot and it will serve their purposes like bring and place small objects. This robot is useful in places where humans cant reach but human voice reaches. Like in a small pipeline, in a firefighting situations, and in highly toxic areas.

It

will be also helpful in minimizing terrorist and antisocial activities like diffusing bombs or carrying it away from populated areas.

Future aspects means what lies ahead of us in this project and we see that here we have a very bright future as it is going to embellish the very own movements robots locomotion and other features as we see today them as a robotic arm or say a lever that works on its own.

Imagine a world when the motion is controlled just by our voice than we can say that how easy it will be for us to use it to fulfill our needs.

This Project Report has discussed the idea that how the speech is being generated as it is an acoustic sound pressure wave that originates by exiting of air from vocal tract and voluntary movement of anatomical structure.

We have also shown the output of the sound waves that are generated as a result of the sound produced by us. At last we have shown the comparison of the waves.

Potrebbero piacerti anche