There are various signals we can get in the real world such as sound, light, radio signals, biomedical signals from human body, etc. All these signals are in the form of a continuous stream of information, called analog signals. Human voice is a kind of signal we get from the real world and use as biometric input.
A signal is a measurable physical quantity containing some information, which can be conveyed, displayed, recorded, or modified.
There are various reasons for processing signals. The biometric systems, require voice processing for various reasons −
The analog signal processing module converts real world information such as sound wave in the form of 0s and 1s to make it understandable and usable by the contemporary digital systems such as biometric systems. The keystrokes, hand geometry, signature, and speech fall into the domains of signal processing and pattern recognition.
There are two types of signals − analog and digital. The analog signals are uninterrupted, continuous stream of information whereas digital signal is a stream of 0s and 1s.
DSP systems are one of the important components of biometric systems, which convert analog signals into a stream of discrete digital values by sampling and digitizing using an Analog-to-Digital Converter (ADC).
DSPs are single-chip digital microcomputers, which process electrical signals generated by electronic sensors from cameras, fingerprint sensors, microphones, etc.
A DSP allows the biometric system to be small and easily portable, to perform efficiently and to be overall less costly.
The DSP architecture is built to support complex mathematical algorithms that involve a significant amount of multiplication and addition. The DSP can execute multiply/add in a single cycle with the help of the multiply/accumulate (MAC) hardware inside its Arithmetic Logic Unit (ALU).
It can also enhance the resolution of the captured image with the use of two-dimensional Fast Fourier Transforms (FFT) and finite IR filters.