Evaluating the WER for different Extraction Methods

    Industry 4.0, Vol. 6 (2021), Issue 3, pg(s) 100-101

    In this paper we will discuss an important topic such as the WER (word error rate). Imagine if we use an ASR system in a real event for approximately one hour or more. We would have a lot of issues like: the quality of the transcription of words, the time of the processing of the words spoken. And so a lot of WER will be produced by this event. The high rate of ASR errors have demanded the necessity to find better techniques in order to correct such errors. The improvement of the system it is a necessity not only to have a better stability of the system but also to prevent the high costs in order to use our resources in the best way as possible.


    Logistic equation for the study of COVID – 19 in Albania

    Mathematical Modeling, Vol. 5 (2021), Issue 2, pg(s) 78-82

    The rapid spread of COVID-19 disease worldwide has caused a frightening crisis in the health care system in many states. To prevent it, many states have taken various measures, including total blockades. In this paper we have used the logistic growth model to show the increase in the population of the number infected with the Covid-19 virus in Albania. The generalized logistic equation is used to interpret the COVID-19 epidemic data in Albania. The growth rate was calculated using two random data and the expected number of infected people. The predictions of the logistic model are as correct as the data are accurate, and that correct that they can imitate the dynamics of the epidemic. The model clearly shows that there is a correlation between real and projected data. When daily predictions of epidemic size begin to converge, we can say that the epidemic is under control. If we deviate from the forecast curve it may indicate that the  epidemic may get out of control. With a fully valid model, this type of information can be used as an example by policy makers to assess how to take appropriate action.


    An approach of Feature Techniques using Warped frequencies

    Mathematical Modeling, Vol. 5 (2021), Issue 2, pg(s) 52-54

    In this paper we will use different feature extraction approach in order to compare the stability of the Automatic Speech Recognition (ASR) on different SNR noise, in different situations. By using the classic feature extraction like: Mel filter Bank, Fast Fourier Transformation (FFT), Discrete Fourier Transformation (DFT). After we implement this methods for the different situations then we will warp the frequency of this methods directly on the spectrum in order to see if we get better results. The results will be compared with one another using the Word Error Rate algorithm (WER).


    Application of Dijkstra algorithm to a tramway system of the ongoing expansion city of Tirana

    Trans Motauto World, Vol. 6 (2021), Issue 4, pg(s) 146-150

    The population of the city of Tirana is getting bigger. Transportation in this city has become extremely heavy. Many of its citizens choose to move using their vehicles thus causing an overcrowded traffic. It has happened to all of us to get stuck in the traffic of Tirana, to be late for our destinations and to be stressed by that chaos.
    The use of public transport would be a successful way of reducing the traffic. In this paper we have treated Dijkstra Algorithm and its application in railway system of transport for the proposed Tram system for the city of Tirana. Considering the expansion(map) and relief of this city, we think that it is very favorable to build a tram system in this city. The results of this paper help to have a clear idea of the construction of the tram and a prediction of how it will work and how much it can facilitate the traffic in Tirana.


    Comparing the Effectiveness/Robustness of Gammatone and LP Methods with the direct use of FFT

    Industry 4.0, Vol. 6 (2021), Issue 2, pg(s) 60-62

    In this paper we evaluate the growth of Automatic Speech Recognition systems in respect to the various forms of spectral analysis ways used. A straightforward analysis of platter and Gammatone filter banks used for spectral analysis compared with the direct use of FFT spectral values is taken into account. This analysis was supported understanding the effectiveness of existing Automatic Speech Recognition systems that are specifically targeted on platter and Gammatone filter banks compared with FFT spectral values. We discover that warping the FFT spectrum directly, instead of using filter bank averaging, provides an additional precise approximation to the sensory activity scales. Direct use of FFT spectral values are even as effective as using either Gammatone or Linear Prediction filter banks, as long as the feature extracted from the FFT spectral values takes into consideration a Gammatone or platter like frequency scale. Computing speech signals using FFT or filter bank spectral features and utilizing a method supported by a sliding block of spectral features, is shown to be simpler in terms of ASR accuracy.