Back to Current Issues

Spoken Keyword Spotting System Design Using Various Wavelet Transformation Techniques with BPNN Classifier

Senthil Devi K. A., Dr. B. Srinivasan ,

Assistant Professor, Gobi Arts & Science College, Tamil Nadu, India. 2 Associate Professor, Gobi Arts & Science College, Tamil Nadu, India.
:10.22362/ijcert/2017/v4/i3/xxxx [UNDER PROCESS]

SpokenKeyword spotting is a speech data mining task which is used to search audio signals for finding occurrences of a specified spoken word in the given speech file.It is essential to identify the occurrences of specified keywords expertly from lots of hours of speech contents such as meetings, lectures, etc. In this paper, keyword spotting system designed with various wavelet transformation techniques and BackpropagationNeural Network (BPNN). Back Propagation Neural Network (BPNN) is trained with two predefined spoken keywords based on known features, and finally, input speech features are compared with keyword features in the trained BPNN for spotting the occurrences of the specified keyword.The method of this paper tested with ten speech content often different speakers. Various statistical features extraction techniques with wavelet transformation are used. Performance comparison is done among these methods with Haar, Daubechies2 and Simlet 4 wavelets.

Senthil Devi K. A, “Spoken Keyword Spotting System Design Using Various Wavelet Transformation Techniques with BPNN Classifier”, International Journal Of Computer Engineering In Research Trends, 4(3):111-118, March-2017.

Keywords : Spoken keyword spotting, Speech data mining, MFCC, Wavelet Packet Decomposition, Discrete Wavelet Transformation, BPN neural network, wavelet families.

1. Bahi, H., and Benati, N., [2009], “A new keyword
spotting approach”, IEEE International
Conference on Multimedia Computing and
Systems, pp. 77-80.
2. Chui CK, [1992], “An introduction to wavelets”.
Academic, New York.
3. P. Flandrin. Representation temps-fréquence.
Hermes, 1993
4. Fourier J, [1822], “The analytical theory of heat.
(trans: Freeman A)”, Cambridge University Press,
London, pp. 1878
5. Heerman P.D. and N.Khazenie, “Classification of
multispedtral remote sensing data using a bach
propagation neural network,” IEEE Trans, Geosci.
Remote Sensing, vol.GE_30,no.1,1992, pp.81-88.
6. Jo Yew Tham, Lixin Shen, Seng Luan Lee and
Hwee Huat Tan (2000) “A General Approach for
analysis and application of Discrete Multiwavelet
Transforms”, IEEE Transaction on Signal
Processing ,48(2), 457- 464.
7. Jothilakshmi, S., Spoken keyword detection using
autoassociative neural networks, International
Journal Speech Technology, Springer, 2013, pp.
8. Khan, W. and Holton, R., Word spotting in
continuous speech using wavelet transform, IEEE
International Conference on Electro/Information
Technology, 2014, pp.275-279
9. Mallat S., [1999], “A wavelet Tour of Signal
Processing”, Academic Press, New York, 1999.
10. Qian S, [2002], “Time-frequency and wavelet
transforms”, Prentice Hall PTR, Upper Saddle,
River, NJ.
11. Rama Kishore, Taranjit Kaur, “Backpropagation
Algorithm: An Artificial Neural Network
Approach for Pattern Recognition”, International
Journal of Scientific & Engineering Research,
Volume 3, Issue 6, June-2012 1 ISSN 2229-5518.
12. Sangeetha, J. and Jothilakshmi, S., “A novel
spoken keyword spotting system using support
vector machine”, Engineering Applications of
Artificial Intelligence, Springer, 2014, pp. 287–
13. Senthil devi K.A., Dr.Srinivasan B., “A novel
Keyword Spotting Algorithm in speech mining
using wavelet”, International Journal of Current
Research Vol. 8, Issue, 08, pp.36943-36946,
August, 2016.
14. Senthil devi K A., Dr.Srinivasan B., “Wavelet –
Neural Network Approach for keyword spotting in
Speech Mining”, International Journal of Trends
and Technologies”, Vol 43, Issue 3, pp 160-165,
15. Tao Li, Sheng Ma, Mitsunori Ogihara, ” Wavelet
methods in data mining”, Chapter 27 Data Mining
and Knowledge Discovery Handbook ,Springer,
2005, pp 603-626.

DOI Link : Not yet assigned

Download :

Refbacks : There are currently no refbacks

Quick Links


Science Central

Score: 13.30

Submit your paper to