Browsing by Author "Priyadarshani, P. G. N."

Now showing 1 - 3 of 3

Dynamic Time Warping Based Speech Recognition for Isolated Sinhala Words
(Research Symposium 2010 - Faculty of Graduate Studies, University of Kelaniya, 2010) Priyadarshani, P. G. N.; Dias, N.G.J.
Communication between computer and the human is basically done through keyboard and screen-oriented systems. In the current Sri Lankan context, this restricts the usage of computers to a small fraction of the population, who are both computer literate and conversant with English. Accordingly, the major barrier between the computer and people in Sri Lanka is the language since English is not the mother tongue of most of the people and there is a large proportion of under educated people in rural areas of Sri Lanka. In order to enable a wider proportion of population to benefit from Information Technology, there is a dire need for an interface other than keyboard and screen interface that is widely used at present. The best solution is an efficient speech recognizer so that a natural human-machine interface could be developed to replace the traditional interfaces, such as keyboard and mouse of the computer. Further speech technologies guarantee to be the next generation user interface. For many languages speech recognition applications as well as text to speech synthesis applications have been developed and they have achieved a considerably high precision and applied them in real world applications successfully in developed countries. Even though currently there is no proper speech recognition approach for Sinhala language and the researches in this field in Sri Lanka is still in an infant stage. Here we investigated the fitness of the dynamic programming technique called Dynamic Time Warping (DTW) algorithm in conjunction with the Mel Frequency Cepstral Coefficients (MFCC) to identify separately pronounced Sinhala words. One of the major difficulties in speech recognition is that although different recordings of the same words includes more or less the same sounds in the same order, the durations of each sub word within the word do not match. Consequently, when recognizing words by matching them with reference templates it gives inaccurate results if there is no temporal alignment. DTW solves this problem by accommodating differences in timing between test words and reference templates. Converting the sound waves into a parametric representation is a major part of any speech recognition approach and here we have used MFCCs along with their first and second derivatives in time as the feature vector because they have been shown good performance in both speech recognition a well as in speaker recognition than other conventional speech features, In addition the derivatives reflect better dynamic changes of human voice over time. For extracting the features we divide speech signal into equally spaced frames and compute one set of features per frame as the speech signals are not stationary. We developed the referencetemplates for each word from one example of that particular word per speaker and matched the test speech against to those reference patterns using DTW approach rather than other methods such as Vector Quantization and Euclidean distance because DTW can successfully deal with test signal and reference templates of the same word having different durations. The local distance measure is the distance between features at a pair of frames while the global distance from beginning of utterance until last pair of frames reflects the similarity between two vectors. Based on that, we could recognize the words that we input from our selected vocabulary. In most of the systems developed based on DTW for other languages have been used very limited vocabulary for instance ten words but in this work we have used a considerably large vocabulary of 600 words. We obtained the recordings and separated each utterance and made an audio file for each using the software Praat. We developed the program in MATLAB 7.0. For our experiment we used two informants whose native language is Sinhala since we followed speaker dependent approach and tested each speaker separately, it displayed 80.33% overall accuracy.
Speaker dependent speech recognition on a selected set of Sinhala words
(2013) Priyadarshani, P. G. N.
A study on Linux Live CD re-mastering
(Research Symposium 2009 - Faculty of Graduate Studies, University of Kelaniya, 2009) Priyadarshani, P. G. N.; Dias, N.G.J.
Linux is a Unix-like operating system initially created by Linus Torvalds in 1991. This Operating System basically consisted of the kernel and some GNU tools. Thereafter Linux was developed progressively with the help of the people around the world. The most interesting thing is Linux provides 100% freedom to run, copy, distribute, study, change and improve because it is free and open source. As a consequence, some individuals and companies began distributing Linux with their own choice of packages bound around Linus' kernel aiming some user communities. Redhat Enterprise Linux, Debian, Suse, Ubuntu, Fedora, CentOS and Knoppix are some major distributions. In the users domain, Live CDs are very important because it is capable of trying out a distribution without installing and allows running the distribution on any computer without making any harm to the existing system. Along with the portability, it has a great demand over installation CDs. Moreover, Live CDs can be used to determine whether an operating system or version is compatible with specific hardware settings and certain peripherals, to know which computer or peripheral will function properly before purchasing it. People can also use a Live CD to troubleshoot hardware while many Live CDs can save user created files in a Windows partition, a USB drive, a network drive, or other accessible media. Even the Live CD s are already packed up with some software and capable of fulfilling the user requirements to some extent, the problem is, a preferred Live CD may not provide an environment that is perfectly suited for a specific user since Live CDs are dedicated to specific applications according to the requirements of thematic user communities. Therefore, it comes with the software that valuable to a specific user as well as some software that do not need at all. Further, some software that is essential for a specific user may not be included. On the other hand, although some Live CDs provide the facility of installing the operating system in to the computer, still it is impossible to install software that are not included with the Live CD without an Internet connection, because it needs to download the relevant dependencies which supports the software. The solution to the above mentioned problems of Live CDs is to create customized Live CDs according to the user requirements in order to acquire higher utility. Moreover, it is possible to upgrade a Live CD by including security patches and software updates etc. The main purpose of this study is to explain how to customize a Live CD by adding necessary software packages, plug-ins, removing some unwanted packages and changing the appearance while upgrading. First, we have obtained an image of the original Live CD. Then, we re-mastered the core of the Live CD by using built-in UNIX commands and some standard Linux tools. After recreating the ISO image, it was burned to a CD/DVD. Finally, the customized Live CD was successfully compatible with particular users‟ requirements. To demonstrate the procedure we have selected Ubuntu one of the famous Linux distributions in the world.