Abstract
In this chapter, we describe our novel work in phonetic-based indexing and search, which is designed for extremely fast searching through vast amounts of media. This method makes it possible to search for words, phrases, jargon, slang, and other terminology that are not readily found in a speech-to-text dictionary. The most advanced phonetic-based speech analytics solutions, such as ours, are those that are robust to noisy channel conditions and dialectal variations; those that can extract information beyond words and phrases; and those that do not require the creation or maintenance of lexicons or language models. Such well-performing speech analytic programs offer unprecedented levels of accuracy, scale, ease of deployment, and an overall effectiveness in the mining of live and recorded calls. Given that speech analytics has become sine qua non to understanding how to achieve a high rate of customer satisfaction and cost containment, we demonstrate in this chapter how our data mining technology is used to produce sophisticated analyses and reports (including visualizations of call category trends and correlations or statistical metrics), while preserving the ability at any time to drill down to individual calls and listen to the specific evidence that supports the particular categorization or data point in question, all of which allows for a deep and fact-based understanding of contact center dynamics.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
In 2008, the Federal Trade Commission received 78,838 FDCPA complaints, representing more than $78 million in potential fines for improper collection activities (2009 FTC Annual Report on FDPCA Activity).
References
Ch. Alberti, M. Bacchiani, A. Bezman, C. Chelba, A. Drofa, H. Liao, P. Moreno, T. Power, A. Sahuguet, M. Shugrina, O. Siohan, “An audio indexing system for election video material,”, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4873–4876, 2009.
M. Bacchiani, “Trends Toward Natural Speech,” Presentation at SpeechTEK, New York City, August 24–26, 2009.
P. Cardillo, M. Clements, M. Miller, “Phonetic searching vs. large vocabulary continuous speech recognition,” International Journal of Speech Technology, January, pp. 9–22, 2002.
M. Clements, P. Cardillo, M. Miller, “Phonetic Searching vs. LVCSR: How to Find What You Really Want in Audio Archives,” AVIOS, San Jose, CA, April 2001.
M. Clements, M. Gavalda, “Voice/audio information retrieval: minimizing the need for human ears,” in Proceedings of the IEEE Workshop on Automatic Speech Recognition and Understanding, Kyoto, Japan, December 2007.
J. Garofolo, C. Auzanne, E. Voorhees, “The TREC spoken document retrieval track: a success story,” Proceedings of TREC-8, Gaithersburg, MD, pp. 107–116, November 1999.
M. Gavalda, “Speech analytics: understanding and acting on customer intent and behaviour”, in presentation at the Business Systems Conference on Improving Performance in the Contact Centre, London, November 2009.
D. Graff, Z. Wu, R. McIntyre, M. Liberman, “The 1996 Broadcast News Speech and Language-Model Corpus,” in Proceedings of the 1997 DARPA Speech Recognition Workshop, Chantilly, VA, 1997.
D.A. James, S.J. Young, “A fast lattice-based approach to vocabulary independent wordspotting,” in Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing, Adelais, SA, Australia, Vol. 1, pp. 377–380, 1994.
S.E. Johnson, P.C. Woodland, P. Jourlin, K. Spärk Jones, “Spoken document retrieval for TREC-8 at Cambridge University,” in Proceedings of TREC-8, Gaithersburg, MD, pp. 197–206, November 1999.
D. Jurafsky, J. Martin, Speech and Language Processing, Prentice-Hall, Upper Saddle River, NJ, 2000.
K. Ng, V. Zue, “Phonetic recognition for spoken document retrieval,” in Proceedings of ICASSP 98, Seattle, WA, 1998.
B. Ramabhadran, A. Sethy, J. Mamou, J.B. Kingsbury, U. Chaudhari. “Fast decoding for open vocabulary spoken term detection.” in Proceedings of Human Language Technologies: the 2009 Annual Conference of the North American Chapter of the Association For Computational Linguistics, Companion Volume: Short Papers (Boulder, Colorado, May 31–June 5, 2009). Human Language Technology Conference. Association for Computational Linguistics, Morristown, NJ, pp. 277–280, 2009.
R.R. Sarukkai, D.H. Ballard, “Phonetic set indexing for fast lexical access,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 20, no. 1, pp. 78–82, January 1998.
J. Wilpon, L. Rabiner, L. Lee, E. Goldman, “Automatic recognition of keywords in unconstrained speech using hidden Markov models,” IEEE Transactions on Acoustics, Speech, and Signal Processing, Vol. 38, no. 11, pp. 1870–1878, November 1990.
R. Wohlford, A. Smith, M. Sambur, “The enhancement of wordspotting techniques,” in Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing, Denver, CO, Vol. 1, pp. 209–212, 1980.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer Science+Business Media, LLC
About this chapter
Cite this chapter
Gavalda, M., Schlueter, J. (2010). “The Truth is Out There”: Using Advanced Speech Analytics to Learn Why Customers Call Help-line Desks and How Effectively They Are Being Served by the Call Center Agent. In: Neustein, A. (eds) Advances in Speech Recognition. Springer, Boston, MA. https://doi.org/10.1007/978-1-4419-5951-5_10
Download citation
DOI: https://doi.org/10.1007/978-1-4419-5951-5_10
Published:
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4419-5950-8
Online ISBN: 978-1-4419-5951-5
eBook Packages: EngineeringEngineering (R0)