Abstract - In this research paper we emphasized on development of double ended voice enabled system in order to receive the voice query and convey voiced output message related to travel and tourism domain in Indian language. The voice enable system was developed using multiple components such as automatic speech recognizer (ASR) engine, query classifier and speech synthesis engine. The speech recognition engine plays very crucial role in speech based system which we have evaluated using multiple pattern recognition algorithms namely Hidden Markov Model (HMM), Support Vector Machine (SVM), ontology based feed forward back propagation neural network (OFFBPNN), dynamic time warping (DTW). The performance of SVM AND HMM were seen superior with respect to OFFBPNN, DTW which were measured in terms of word accuracy and word error rate . The output of ASR is fed to k-nearest neighbour (KNN) query classifier and the end result of classifier is finally passed to Odia speech synthesizer to deliver the response in voice mode. We have employed voice transformation technique in speech synthesis system to produce the spoken output in male, female, child and robotic voice. The developed double ended voice enabled system is operational over Odia spoken query and delivered the response in synthesized Odia voice. Keywords – SVM, ANN, DTW, ASR, speech synthesis I. INTRODUCTION The double ended voice enable system plays key role in man-machine communication in natural language. The system facilitates numerous benefits from the angles of usability, operation ability and delivery of end result. The system demands that, it can be used by normal human being as well as physically challenged persons. The system is independent of text based query that means it accepts the query in natural language of the user so that system is well operational by both literate and illiterate groups. Finally, the system end result in voice mode which is well comprehensible for literate, illiterate, normal and physically challenged persons. In this research work we focus on development of double ended voice enabled service that can be employed in travel and tourism (TT) sector of India. The tourism impact over a country is multifaceted because it provides international amity, cross culture understanding, on economic growth of county, employment and income generation vis-a-vis growth of foreign currency. The travel and tourism demand for the development of economy of a county is on a rising trend from the last decade. The total contribution of TT is comprised of 9% of global GDP and generated over 260 million jobs – 1 in 11 of the world’s total jobs. The travel and tourism industry acts as a new generation source for economic development of the country, employment generation and maintaining international peace. The impulse resulting from travel and tourism is clearly positive for a country like India [1]. But it is given less priority in comparison to other industrial activities. Tourism in India has occupied a back seat relative to other countries in spite of the presence of picturesque tourist places, beautiful temples, bountiful artistic sculpture, rich folks and fauna across the country. In spite of good efforts by the government the number of tourists visiting India is not satisfactory. The most important reason for low foot steps to Indian tourism is lack of information for tourists especially for physically challenged persons. Now we are doing research by utilizing extensively both information technology and knowledge engineering techniques to avail the Indian travel and tourism information in hands free mode. Our work not only acts as an aid to travel and tourism industry of a country but also uses natural mode of speech between man and machine, so that, the very objective of communication is well achieved without much difficulty [2]. Further, the developed system also emphasizes speech based input which is more comprehensible with respect to other primitive interfaces such as keyboards and pointing devices. Our objective is to retrieve the Indian travel and tourism information accurately by developing double ended speech enabled system (DESES) that will be more flexible for illiterate as well as physically challenged tourists. Finally, DESES will act as an expert system where computers can be a substitute for a human expert. In this work we emphasize on natural language like Odia for Human-Computer interaction (HCI) by using Odia automatic speech recognizer (OASR) that uses mel cepstral coefficients as feature vector and the OASR is developed using HMM, SVM, OFFBPNN and DTW as a classifier to aid information exchange. The output of OASR is fed to KNN classifier to get the text based solution of query stated by the user to OASR .The output generated by KNN passed to Odia speech synthesizer in order to produce the solution in voice mode. Our developed Odia speech synthesizer can produce the result in male, female, child and robotic voice. The speech corpus is collected from 30 speakers, some of them are native to Odisha and few are non-native but can speak Odia. The ongoing research work used two groups of Double Ended Speech Enabled System in Indian Travel & Tourism Industry Sanghamitra Mohanty 1 , Basanta Kumar Swain 2 1 Department of Computer Sc. & Application, Utkal University, Bhubaneswar, India 2 Department of Computer Sc. & Engineering, Government College of Engineering, Kalahandi, Bhawanipatna, India 1 sangham1@rediffmail.com, 2 technobks@yahoo.com 978-1-4799-1597-2/13/$31.00 ©2013 IEEE