Detection of word boundary in continuous speech is an important issue in speech recognition. This paper presents different methods for detecting word boundary in Assamese language and also discusses the possible future development to improve the accuracy. These methods are based on the behavior of pitch frequency across the sentences. Here we use Scilab, Praat and Wavesurfer software.

Word boundary detection(WBD),Hidden markov model( HMM), LPC, SOM, MLP

[1] Srichand "Word Boundary Detection in Indian Languages and Application to Keyword Spotting," Department of Computer Science and Engineering Indian Institute of Technology, Madras- 600 03G, India, August 1996.
[2] Ramana Rao G.V. and Srichand J. ,"Word Boundary Detection Using Pitch Variation," Department of Computer Science and Engineering, Indian Institute of Technology, May 1996.
[3] Anurag Jain, S.S. Agrawal, Nupur Prakash ,"Performance evaluation of word boundary detection for Hindi speech database," GGSIP University, Delhi India ,2CDAC Noida India.
[4] G.V.Ramana Rao "Detection of word boundaries in continuous hindi speech using pitch and duration,",Department of computer science and engineering,Indian Institute of Technology,Madras 600036,India.
[5] Colin Keng-Yan TAN, Kim-Teng LUA,"Learning of Word Boundaries In Continuous Speech Using Time Delay Neural Networks," Laboratory for Computational Linguistics, Department of Computer Science, School of Computing, National University of Singapore.
[6] Andreas Tsiartas, Prasanta Kumar Ghosh, Panayiotis Georgiou and Shrikanth Narayanan ,"Robust Word Boundary Detection in Spontaneous Speech using Acoustic and Lexical Cues,"Speech Analysis and Interpretation Laboratory,Department of Electrical Engineering, University of Southern California, Los Angeles,CA90089.
[7] Syed Abbas Ali,Najmi Ghani Haider and Mahmood Khan Pathan, "A LPC-PEV Based VAD for Word Boundary Detection,", Faculty of Computer &Information Systems Engineering, N.E.D University of Engg.&Tech.,Karachi.
[8] Jan Bartoˇsek and V´aclav Hanˇzl ,"Foot Detection in Czech Using Pitch Information and HMM,",Department of Circuit Theory, FEE CTU in Prague, Technick´a 2, 166 27 Praha 6 - Dejvice, Czech Republic.
[9] Manash Pratim Sarma and Kandarpa Kumar Sarma, "Speech Recognition of Assamese Numerals Using Combinations of LPC - Features and Heterogenous ANNs", Department of Electronics And Communication Technology,Gauhati University, Assam, India, Springer-Verlag Berlin Heidelberg 2010, pp. 8–12.
[10] Robert Togneri department of Electrical and Electronics Engineering , M.D. Alder , "Speech processing using artificial neural network", Department of mathematics Yianni Attikiouzel Department of electrical and electronics engineering, the university of western Australia.
[11] Archana Agarwal, Anurag Jain, Nupur Prakash and S.S.Agrawal," Word Boundary Detection in Continuous Speech based on Suprasegmental Features for Hindi Language,"University School of Information Technology, G.G.S Indraprastha University, Delhi, India, 2010 2nd International Conference on Signal Processing Systems (ICSPS).
[12] Francesco Beritelli, "Robust Word Boundary Detection Using Fuzzy Logic,"(Istituto di Informatica e Telecomunicazioni -University of Catania, V.le A. Doria 6, 95125 Catania, Italy).
[13] Khurram Waheed, Kim Weaver and Fathi M. Salam, "A Robust Algorithm for Detecting Speech Segments using an Entropic Contrast," Circuits, Systems and Artificial Neural Networks Laboratory ,Michigan State University, East Lansing, MI 48824-1226.
[14] Joe Tebelskis, "Speech Recognition using Neural Networks",School of Computer Science,Carnegie Mellon University,Pittsburgh, Pennsylvania 15213-3890,May 1995.