Home   >   CSC-OpenAccess Library   >    Manuscript Information
Full Text Available

This is an Open Access publication published under CSC-OpenAccess Policy.


Top researchers from over 74 countries worldwide have trusted us because of quality publications.

United States of America
United Kingdom
Saudi Arabia
Segmentation of Malay Syllables in Connected Digit Speech Using Statistical Approach
M-S Salam, Dzulkifli Mohamad, S-H Salleh
Pages - 23 - 33     |    Revised - 15-02-2008     |    Published - 30-02-2008
Volume - 2   Issue - 1    |    Publication Date - February 2008  Table of Contents
Speech Segmentation, Divergence Algorithm, Brandts Algorithm
This study present segmentation of syllables in Malay connected digit speech. Segmentation was done in time domain signal using statistical approaches namely the Brandt’s Generalized Likelihood Ratio (GLR) algorithm and Divergence algorithm. These approaches basically detect abrupt changes of energy signal in order to determine the segmentation points. Patterns used in this experiment are connected digits of 11 speakers spoken in read mode in lab environment and spontaneous mode in classroom environment. The aim of this experiment is to get close match between reference points and automatic segmentation points. Experiments were conducted to see the effect of number of the auto regressive model order p and sliding window length L in Brandt’s algorithm and Divergence algorithm in giving better match of the segmentation points. This paper reports the finding of segmentation experiment using four criterions ie. the insertion, omissions, accuracy and segmentation match between the algorithms. The result shows that divergence algorithm performed only slightly better and has opposite effect of the testing parameter p and L compared to Brandt’s GLR. Read mode in comparison to spontaneous mode has better match and less omission but less accuracy and more insertion.
CITED BY (13)  
1 Ramli, I. (2015). Regular paper Sentence boundary detection without speech recognition: A case of an under-resourced language. J. Electrical Systems, 11(3), 308-318.
2 Akila, A., & Chandra, E. (2015). Word based tamil speech recognition using temporal feature based segmentation. ictact Journal on Image & Video Processing, 5(4).
3 Jin-peng, Q., Jie, Q., Fang, P., & Tao, G. (2015, July). Multi-channel detection for abrupt change based on the Ternary Search Tree and Kolmogorov statistic method. In Control Conference (CCC), 2015 34th Chinese (pp. 4968-4973). IEEE.
4 Jin-peng, Q., Qing, Z., Fang, P., & Jie, Q. (2014, July). A fast method for change point detection from large-scale time series based on Haar Wavelet and Binary Search Tree (HWBST). In Control Conference (CCC), 2014 33rd Chinese (pp. 506-511). IEEE.
5 Qi, J. P., Zhang, Q., Qi, J., & Zhu, Y. (2014). A Fast Method for Abrupt Change Detection from Large-Scale Electrocardiogram (ECG) Time Series. In Service Science and Knowledge Innovation (pp. 420-429). Springer Berlin Heidelberg.
6 Jamil, N., Ramli, M. I., Abu Bakar, Z., & Seman, N. (2014, January). Prosody-based sentence boundary detection of spontaneous speech. In Intelligent Systems, Modelling and Simulation (ISMS), 2014 5th International Conference on (pp. 311-317). IEEE.
7 Qi, J. P., Zhang, Q., Zhu, Y., & Qi, J. (2014). A Novel Method for Fast Change-Point Detection on Simulated Time Series and Electrocardiogram Data. PloS one, 9(4), e93365.
8 Salam, M. S. B. H., Mohamad, D., & Salleh, S. H. S. Connected digit speech segmentation: a malay speech case using statistical approach with insertion reduction using neural network.
9 Fook, C. Y., Hariharan, M., Yaacob, S., & Ah, A. (2012, March). Malay speech recognition in normal and noise condition. In Signal Processing and its Applications (CSPA), 2012 IEEE 8th International Colloquium on (pp. 409-412). IEEE.
10 H. Farsi, Improvement of Minimum Tracking in Minimum Statistics Noise Estimation Method, Signal Processing: An International Journal (SPIJ), 4(1), pp. 17 22, 2010.
11 R. Sabah and R.N. Ainon, Isolated Digit Speech Recognition in Malay Language Using Neuro-Fuzzy Approach, in Modelling & Simulation, AMS '09. Third Asia International Conference , Bali, 25-29 May 2009, pp.no. 336 340.
12 A. V. Aquino and Y. J. A. Barria, Change Detection in Time Series Using the Maximal Overlap Discrete Wavelet Transform. Lat. Am. appl. res. 39(2), pp. 145-152., 2009.
13 M. S Salam, D. Mohamad and S. H Salleh, Insertion Reduction in Speech Segmentation Using Neural Network, in Information Technology, 2008. ITSim International Symposium, Kuala Lumpur, 26-28 Aug. 2008, pp.no. 1-7.
1 Google Scholar 
2 Academic Journals Database 
3 ScientificCommons 
4 Academic Index 
5 CiteSeerX 
6 refSeek 
7 iSEEK 
8 Socol@r  
9 Libsearch 
10 Bielefeld Academic Search Engine (BASE) 
11 Scribd 
12 WorldCat 
13 SlideShare 
15 PdfSR 
16 Chinese Directory Of Open Access 
1 Abas Lutfi. Linguistik Deskriptif Nahu. Dewan Bahasa dan Pustaka, Kuala Lumpur: pp. 10 - 20 (1971)
2 H.N Ting, Y. Jasmy and S.H Salleh. Malay Syllable Recognition Using Neural Network. In Proceeding of the International Student Conference on Research and Development, SCOReD, Kuala Lumpur, 2006.
3 Md Sah Hj Salam and Mohamad Nasir Said Ibrahin. An Initial Experiment on Syllable Based Approach For Malay Digit Recognition. In Proceeding of Advance Technology Congress. ATC2003, Putrajaya, Malaysia 2003.
4 J.L Rouas, J. Farinas, F. Pellegrino and R.A Obrecht, Rhythmic Unit Extraction and Modeling for Automatic Language Identification. Speech Communication 47: 436-456. 2005.
5 S. Jarifi, D. Pastor and O. Rosec,. Brandts GLR Method & Refined HMM Segmentation for TTS Synthesis Application. In Proceeding of European Signal Processing Conference, EUSIPCO2005. Antalya,Turkey. 2005
6 B. Michele and V.N. Igor, Detection of Abrupt Changes: Theory and Application, Prentice Hall, INC. USA 1993
7 R.A. Obrecht, Automatic Segmentation of Continuous Speech Signal, IEEE Trans. Acoustic, Speech and Signal Processing, vol ASSP-36(1). pp 29-40, 1988
8 T. Jehan T. Musical Signal Parameter Estimation. Master Thesis, University of Rennes, France. 1997
9 O. Engstrand, Sytematicity of phonetic variation in natural discourse. Speech Communication 11, pp. 337-346. 1992
10 K. Kohler Segmental reduction in connected speech in German: Phonological facts and phonetics explaination. Speech Production and Speech Modelling, Kluwer, Dordrecht. pp.69-92. 1990
11 P. Cosi, J.P. Hosom, and F. Tesser. High performance Italian continuous digit recognition, In Proceedings of International Conference on Spoken Language Processing, Beijing, China, ICSLP 2000.
12 Language Production and Perception, online : http://www.ling.upenn.edu/courses/Fall_1998/ling001/production_perception.html. pp. 1 11.
13 T. Nuttakorn and K. Boonserm. A syllable - based connected Thai digit speech recognition using neural network and duration modeling. In Proceeding of The 1999 IEEE International Symposium on Intelligent Signal Processing and Communication. Pp 785-788. 1999.
14 W. Wei .and and S.V. Vuuren. Improved neural Network Training of Inter-Word Context Units for Connected Digit recognition, In Proceeding of IEEE International Conf. on Acoustics, Speech & Signal Processing, Seattle, ICASSP 1998
15 Md Sah Hj Salam , Dzulkifli Mohamad dan S-H Salleh. Speech Anticipation via Genetic Optimization: An Experiment on Simulated Data, In Proceeding of International .Conference on Artificial Intelligence in Engineering and Technology, ICAIET 06, Kota Kinabalu, Sabah, Malaysia.2006.
16 L.R Rabiner and M.R Sambur. Some Preliminary Experiments in the Recognition of Connected Digits. IEEE Trans. Acoustic, Speech and Signal Processing, vol ASSP-24. pp 170-182 April 1976.
Mr. M-S Salam
- Malaysia
Mr. Dzulkifli Mohamad
- Malaysia
Mr. S-H Salleh
- Malaysia