Abstract:
Noise removal is a necessary preprocessing step for speech acquisition in computer telephony and other applications, such as speech-assisted human-machine interfaces.
In telephony system, the received signal by the microphone, is reverberated through the environment and picked up by the microphone again .That is in the form of time delayed and attenuated image of original speech signal, and causes a reduction in the quality of the communication.
Voice and sound detection is an important are in industrial sector as well as in the security agencies’ work. Keeping the importance of such areas the project work will be sound detection, data acquisition, improving signal to noise ratio via filter and data processing techniques. Signal acquired through a parabolic microphone is far better in terms of acoustic gain compared to the signal acquired through a normal microphone without a parabolic reflector. Once the speech signal has been acquired, noise removal is required to improve the signal to noise ratio. Reverberation cancellation can be done by using squelch circuitry.
A parabolic microphone will be used to gather the input speech signal. The noise removal part comprises of low pass filters. Reverb cancellation is achieved using squelch circuit.
