Speech! An effective way of communication between human is now becoming an alternative way to communicate between human and machine. This alternative way is now-a-days used in many real time systems for faster, easier and comfortable response and communication. Speech segmentation and labelling are the process that lay as a key to decide the accuracy of several speech related research. A tool "AAYUDHA" is proposed that enables automatic segmentation and labelling of continuous speech in Tamil. Two different segmentation algorithms, one based on Fast Fourier Transform (FFT) feature set and 2D filtering and other based on Discrete Wavelet Transform (DWT) feature set and its energy variation in different sub-bands are implemented. The segmentation accuracy of those algorithms is analyzed. Further the segmented speech is labelled using a baseline Hidden Markov Model (HMM) based acoustic model. A speech corpus named "KAZHANGIYAM" is created which includes the recorded Tamil speech of various speakers. The database also includes the information of manually segmented data of those speech data. This speech corpus is used to analyze the accuracy of the algorithms used in the proposed tool. This tool concentrates on the phonetic level segmentation of Tamil speech. The tool shows an acceptable segmentation and labelling accuracy.

No abstract

Congestion due to traffic, results in wasted fuel, increase in pollution level, increase in travel time and vehicular queuing. Smart city initiatives are aimed to improve the quality of urban life. Intelligent Transportation System (ITS) provides solution for many smart city projects, as they capture real time data without any fixed infrastructure. The real-time prediction of traffic flow aids in alleviating congestion. Accurate and timely prediction on the future traffic flow helps individual travellers, public transport, and transport planning. Existing systems are designed to predict specific traffic parameters like weekday, weekend, and holidays. This research presents a machine learning based traffic flow forecasting for the city of Bloomington, US not with any precise parameter. The day-wise dataset for the 5 areas is taken from Jan 1, 2017 to Dec 31, 2019. The algorithm used for implementation is Support Vector Regression (SVR) and Long Short-Term Memory (LSTM). LSTM algorithm provides better traffic prediction with least root means square error value.