Abstract
In this chapter, a technique is proposed to remove the CVC-type word limitation observed in case of spoken word recognition model described in Chap. 7. This technique is based on a phoneme count determination block based on K-means clustering (KMC) of speech data. Sections 8.2 and 8.3 of this chapter provides detail description of a K-mean algorithm-based technique to provide prior knowledge about the possible number of phonemes in a word. Experimental work, related to the proposed technique, is discussed in Sect. 8.4. Section 8.5 concludes the description.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Tapas Kanungo T, Mount DM, Netanyahu NS, Piatko CD, Silverman R, Wu AY (2002) An efficient k-means clustering algorithm: analysis and implementation. IEEE Trans Pattern Anal Mach Intell 24(7):881–892
Wagstaff K, Cardie C, Rogers S, Schroedl S (2001) Constrained K-means clustering with background knowledge. In: Proceedings of the 18th international conference on machine learning, pp 577–584
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2014 Springer India
About this chapter
Cite this chapter
Sarma, M., Sarma, K.K. (2014). Application of Clustering Techniques to Generate a Priori Knowledge for Spoken Word Recognition. In: Phoneme-Based Speech Segmentation using Hybrid Soft Computing Framework. Studies in Computational Intelligence, vol 550. Springer, New Delhi. https://doi.org/10.1007/978-81-322-1862-3_8
Download citation
DOI: https://doi.org/10.1007/978-81-322-1862-3_8
Published:
Publisher Name: Springer, New Delhi
Print ISBN: 978-81-322-1861-6
Online ISBN: 978-81-322-1862-3
eBook Packages: EngineeringEngineering (R0)