Abstract
Turkish Recognition ENgine (TREN) is a modular, Hidden Markov Model based (HMM-based), speaker independent and Distributed Component Object Model based (DCOM-based) speech recognition system. TREN contains specialized modules that allow a fully interoperable platform including a Turkish speech recognizer, a feature extractor, an end-point detector and a performance monitoring module. TREN deals with the interaction between two layers constituting the distributed architecture of TREN. The first layer is the central server, which applies some speech signal preprocessing and distributes the recognition calls to the appropriate remote servers according to their current CPU load of the recognition process. The second layer is composed of the remote servers performing the critical recognition task. In order to increase the recognition performance, a Turkish telephony speech database with a very large word corpus is collected and statistically the widest span of triphones representing Turkish is examined. TREN has been used to assist speech technologies which require a modular and multithreaded recognizer with dynamic load sharing facilities.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Goddeau, D.: Deploying Speech Application over the Web. In: Proceedings of Eurospeech, Rhodes, Greece, pp. 685–688 (September 1997)
Sokolov, M.: Speaker Verification over the World Wide Web. In: Proceedings of Eurospeech, Rhodes, Greece, pp. 847–850 (September 1997)
Microsoft Corp., DCOM technical Overview (1996)
The Aurora Project, announced at Telecom 1995, Geneva (October 1995), http://gold.ity.int/TELECOM/wt95
Stallard, D.: The BBN SPIN System. In: Voice on the Net Conference, Boston MA (September 1997)
Barry, T., Solz, T., Reising, J., Williamson, D.: The Simultanous Use of Three Machine Speech Recognition Systems to Increase Recognition Accuracy. In: Proceedings of IEEE National Aerospace and Electronics Conf (NAECON), May 23-27, vol. 2, pp. 667–671 (1994)
Digalakis, V., Neumeyer, L., Perakakis, M.: Quantization of Cepstral Parameters for Speech Recognition over the World Wide Web. IEEE Journal on Selected Areas in Communcations 17(1), 82–90 (1999)
Stadermann, J., Righoll, G.: Flexible Feature Extraction and HMM Design for a Hybrid Speech Recognition System in Noisy Environments. In: International Conference on Acoustics, Speech, Signal Processing, April 6-10, vol. 3, pp. 332–335 (2003)
Kun, A.L., Miller III, W.T., Lenharth, W.H.: Modular System Architecture for Electronic Device Integration in Police Cruisers. In: Proceedings of the 2002 IEEE Intelligent Vehicle Symposium, Versailles, France, June 18-20 (2002)
Yapanel, Ü., Dog̃an, M.U., Arslan, L.M.: Türkçe Anahtar Sözcük Yakalama Sistemi için farklı Atık Modellerinin Karşılaştırılması (Comparison of Garbage Modeling Techniques for a Turkish Keyword Spotting System). In: SIU proc, Gazimagusa, pp. 122–127 (April 2001)
Rabiner, L.R., Juang, B.: Fundamentals of Speech Recognition. P. Hall Signal Processing Series, N.Jersey (1993)
Rabiner, L.R., Sambur, M.R.: An algorithm for determining the endpoints of isolated utterances. Bell Syst. Tech. J. 54, 297–315 (1975)
Karatza, H.D.: A Comparison of Load Sharing and Job Scheduling in a Network Of Workstations. International Journal of Simulation: Systems, Science, Technology 4(3-4), 4–11 (2003)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Palaz, H., Kanak, A., Bicil, Y., Dog̃an, M.U. (2005). A DCOM-Based Turkish Speech Recognition System: TREN – Turkish Recognition ENgine. In: Yolum, p., Güngör, T., Gürgen, F., Özturan, C. (eds) Computer and Information Sciences - ISCIS 2005. ISCIS 2005. Lecture Notes in Computer Science, vol 3733. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11569596_68
Download citation
DOI: https://doi.org/10.1007/11569596_68
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-29414-6
Online ISBN: 978-3-540-32085-2
eBook Packages: Computer ScienceComputer Science (R0)