In speaker verification (SV), claimed identity of a speaker from the enrolled database is verified. The SV system is categorized in two ways. One of them is text dependent case and other is the test dependent one. This paper mainly focuses on the text dependent case. Text dependent speaker verification system is one, where a speaker utters the same phrase for the training and the testing phase. Here, the speaker has the prior knowledge as what phrase has to be spoken. It is basically used in systems that requires secure access and is operated with user’s cooperation and knowledge. This paper summarizes the various methodologies adopted in text dependent speaker verification, in order to give the researchers an overview of this system. Here, different features and classifiers employed in text dependent speaker verification system have been discussed. And also, a comparison of the performance obtained by the existing methodologies, are enumerated.

From last two decades use of computer as well as internet has increased drastically. And the demand for faster, accurate and meaningful response i.e. answers has increased in recent years. Hence a question answer has raised a lot of interest in research society due to wide applications. Basically open and closed domain is there depending on the application found in Question Answering (QA). This paper presents work of development of database and collection in Marathi language for the school based examination system. This is a first developed sentence database in Marathi language for the examination system.

Robotics is an emerging field in mechatronics stream. Automation in industrial environment is a prioritised area of interest for many researchers. In large scale industries, transportation of goods from one place to another is often required. The automatic guided vehicles (AGV) are mainly used in such cases. The smart and cost effective solution for moving small and delicate goods in commercial applications is the focus for present study. In order to make the robot smart, robust and compact, the selection of sensory mechanism with respect to reliability and cost is preferred. The combination of ultrasonic sensors, magnetometer with multiple numbers of master and slave controllers is unique approach in pursuit of finding the desired outcome. The source and destination of robot is predetermined and the obstacles in the path are randomly arranged. The ultrasonic sensors detect the obstacle and send the data to master control. The magnetometer keeps the track of direction in which destination is present. This helps the robot to track down the expected path. The demonstration of experiment is observed and the obtained results are being studied.

Human can produce different sounds such vowels, semi-vowels, nasals, fricatives, stops, murmurs etc. Some sounds are produced by vocal fold vibration and others by making constriction in the vocal cord. Stop consonants fall under the second category. They are associated with low energy, high variability and highly random in nature. The extraction of useful features from speech signal is a very challenging task. They can be extracted from certain locations, where there are sudden and significant articulatory changes known as landmarks. Landmarks associated with stops are Voicing Onset Time and burst release. Analysis of Burst and Voicing Onset Time can give the place of articulation during the production of sounds. Therefore, detection of these landmarks is studied by a number of researchers. Landmark based processing is required for analysis of events associated with stops. In this paper, we reviewed some of the existing methodologies for landmark detection of stop consonants.