= ee In this step the continuous speech signal is blocked into frames of N samples, with adjacent frames being separated by M (M<N). The first frame consists of the first N samples. The second frame begins M samples after the first frame, and overlaps it by N - M samples and sc on. This process continues until all the speech is accounted for within one or more frames Typical values for N and M are N = 256 (which is equivalent to 30 msec windowing anc Facilitate the fast radix-2 FFT) and M = 100. The code for frame blocking is given in the project file by the name “blockFrames”. on. This process continues until all the speech is accounted for within one or more frames. filtering is given in the file known as “melfb”. As it is known that the frequency contents of sounds for speech signals does not follow a linear scale. Thus for each tone with an actual frequency, f, a subjective pitch is measured on a scale called the ‘mel’ scale. The Mel-Frequency scale is a linear frequency spacing below 1000 Hz and a logarithmic spacing above 1000 Hz. The code for illustrating Mel frequency filtering is given in the file known as “melfb”. One approach to simulating the subjective spectrum is to use a filter bank, spaced uniformly on the mel-scale (in Figure 5). That filter bank has a triangular band pass frequency response and the spacing as well as the bandwidth is determined by a constant Mel frequency interval The number of Mel spectrum coefficients, K, is typically chosen as 20. Note that this filte bank is applied in the frequency domain, thus it simply amounts to applying the triangle-shape windows as in the Figure 5 to the spectrum. A useful way of thinking about this mel-wrapping filter bank is to view each filter as a histogram bin (where bins have overlap) in the frequency domain. Figure 6: Conceptual diagram illustrating vector quantization codebook formation. Clustering the Training Vectors After the enrolment session, the acoustic vectors extracted from input speech of each speaker provide a set of training vectors for that speaker. The next important step is to build a speaker- specific VQ codebook for each speaker using those training vectors. The MATLAB code for clustering vectors is given in a file named “vqlbg”. There is a well-known algorithm, namely LBG algorithm for clustering a set of L training vectors into a set of M codebook vectors. The algorithm is formally implemented by the following recursive procedure: Figure 7: Flow diagram of the LBG algorithm (Adapted from Rabiner and Juang, 1993) Figure 7 shows, in a flow diagram, the detailed steps of the LBG algorithm. “Cluster vectors” is the nearest-neighbour search procedure which assigns each training vector to a cluster associated with the closest codeword. “Find centroids” is the centroid update procedure. “Compute D (distortion)” sums the distances of all training vectors in the nearest-neighbour search so as to determine whether the procedure has converged. Now in this window we have two options, either we can modify an existing GUI or we can just make a new one. In our case we click on the “Blank GUI (Default)” and start to design our GUI by selecting the items on the side bar as shown in the image below. Now for the above piece of code to work we require the file “project image 3.jpg” in the current working directory of Matlab. The image file is shown below: After adding the above code in our GUI’s main working program we got the output shown below: Figure 12: Matlab Application Compiler After typing the above command in the command window we selected the “Application Compiler” option to open the window shown below: Figure 13: Welcome screen for the Application The code files are included along with the Project repot in .zip file. Figure 16: Pressed the add new sound. Program starts recording voice after getting the sampling rate, nbits and the record time form user Figure17: Plotting the recorded audio sample from user 1 Figure 28: pressed the speaker recognition button, after recording the voice the above window pops oper Figure 19:the program has successfully Identified the user Figure 20: Here sound database is the main indexing file. u1 is the user 1 sample in the database and v is the speaker recognized file
