1. Introduction: A signal is the most amazing phenomenon created by this nature which helps each and every not only humans but also every living thing on this earth to covey some information by means of gesture, action or sound. Considering the perspective of engineering, the signal can be either analog or a digital signal. And the processing can be done on these signals which are known as analog signal processing and digital signal processing. “An analog or analogue signal is any continuous signal for which the time varying feature (variable) of the signal is a representation of some other time varying quantity, i.e., analogous to another time varying signal.”[1] The speech signal is the best example of an analog signal as the signal varies …show more content…
Theory:
3.1 Classification of a speaker recognition system: Speaker recognition system can be classified into two types. This classification is made on the basis of the number of speakers whose voices has to be recognized. 1. Open set system: In the open set speaker recognition system, the number of speakers are more and will always be greater than 1.It can be noted that, speakers whose voices are going to be recognized are not registered at the system. 2. Closed Set system: A closed set of speaker recognition system will consists of only the specified or fixed number of speakers. And all these speakers has to be registered with the system. 3.1 Description: All general speaker recognition systems consist of two phases. “The first one is known as the training phase while the second one is called as testing phase.” [3] In the training phase, each registered speaker has to provide samples of their speech so that the system can build a database of samples for that speaker. It consists of two main parts. In the first part each person’s input voice sample is processed to sum up the characteristics of their vocal tracts. The second part involves collecting each person's data together into a single, easily manipulated matrix. The testing system has the exact system architecture as the training system. “First the input signal is analyzed also processed and then it is compared to the data stored in the codebook.”[3] The automatic speaker recognition …show more content…
Speaker identification is the process of determining which registered speaker provides a given utterance. Each block of the speaker recognition system can be described as below;
• Input Speech: Input speech is the signal given by the speaker to the above system. Normally the human speech is the pure analogue signal, thus in order to process the signal further the analogue signal has to be converted to the digital signals. This conversion can be done by using the techniques such as sampling and quantization which is known as digital signal processing. But for the above system, the input speech signal is already given in the digital form which can be done by recording the voices of the speaker.
• Feature Extraction: Feature extraction refers to the analyzing of the speech signal which is provided as an input to the above system. The purpose of this feature extraction is the conversion of speech waveform to some type of parametric representation. Feature extraction coverts the incoming speech signal into a represented form such that it is possible to reconstruct the original signal from it. There are various techniques to extract features like MFCC, PLP, RAST, LPCC which can be briefly stated as