Monica Mundada

Performance Evaluation of Speech Synthesis Techniques for English Language

The conversion of text to synthetic production of speech is known as text-to-speech synthesis (TTS). This can be achieved by the method of concatenative speech synthesis (CSS) and hidden Markov model techniques. Quality is the important paradigm for the artificial speech produced. The study involves the comparative analysis for quality of speech synthesis using hidden Markov model and unit selection approach. The quality of synthesized speech is evaluated with the two methods, i.e., subjective measurement using mean opinion score and objective measurement based on mean square score and peak signal-to-noise ratio (PSNR). Mel-frequency cepstral coefficient features are also extracted for synthesized speech. The experimental analysis shows that unit selection method results in better synthesized voice than hidden Markov model.

Cluster Head Location based Base Station Mobility in Wireless Sensor Network

Wireless sensor networks (WSN) are sophisticated systems that are used to gather data from an unreachable and remote environment. WSN consists of base station and hundred to thousands of sensor nodes. The main design issues in WSN include efficient energy management and network lifetime. Most of the approaches assume the nodes to be homogenous, however they can be heterogeneous. In this paper we take a realistic approach by considering heterogeneous networks. The clustering mechanism, location of base station and the routing process are crucial to elongate the lifetime of the sensor nodes. The clusters will be formed in different topologies depending on the sensor node deployment. The mobile base station, concept of budget to the sensor nodes and multi hop routing in a sensor network with heterogeneous nodes is used to make the network energy efficient and maximize the network lifetime. General Terms Wireless Sensor Networks, Heterogeneous Sensor Nodes, Mobile Base Stations.