Abstract
In 1983 the Dutch PTT and Philips set up a joint working party under the name of ‘Speech Processing’, ‘to allow reliable statements to be made on the usability of speech processing in subscriber telecommunication services’. To this end, the working party investigated the feasibility of an information service for the general public with voice commands and voice output, to be accessible via the regular telephone network.
In order to be able to use speaker-independent speech recognition, samples of all words needed in the service were collected from about 180 male and female speakers and used to make recognition templates. To accommodate the needs of new as well as experienced users, several dialogue structures were conceived and tested in a Wizard-of-Oz experiment with simulated voice recognition. These dialogues were then used in a field experiment with 122 subjects. The results of this experiment showed that a simple public network information service with speaker-independent speech recognition is feasible, both technically and in terms of user performance, although not without problems for quite a few users. Error correction proved awkward; in speech-recognition systems where this is the case the overall recognition score should be higher than 80%, in order to ensure that users are only confronted with the difficult correction procedures in exceptional cases.
This is a preview of subscription content, log in via an institution to check access.
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
Frankhuizen, J.L. and Vrins, T. G. M. (1980): ‘Human factors studies with Viewdata’. Proc. of the 9th Int. Symp. on Human Factors in Telecommunication, 1980, Red Bank, New Jersey.
Lee, E. S.; Whalen, T.E.; McEwen, S. and Latrémouille, S. (1982): ‘Human Factors in Videotex Information Retrieval’. Proc. of the 1982 Int. Zürich Seminar on Digital Communications–Man-Machine Interaction, p. 225–232.
Leiser, R. G.; De Alberdi, M.; Carr, D. and Jones, J. (1987): ‘Human factors in dialogue development for voice control of PABX features’. Proc. of the 2nd Symp. on Occupational Ergonomics, Zadar, Yugoslavia, April 1987.
Leopold, F. F. and Van Nes, F.L. (1987): ‘Control of data processing systems by voice commands’. Behaviour and Information Technology, 6, no. 3, p. 323–326.
Van Nes. F. L. and Tromp, J.H. (1979): ‘Is viewdata easy to use?’ IPO Annual Progress Report 14, p. 120–123.
Van Nes, F. L. (1982): ‘Perceptive, cognitive and communicative aspects of data processing equipment’. Proc. of the 1982 Int. Zürich Seminaron Digital Communications–Man-Machine Interaction, p. 259–262.
Van Noorden, L. P. A. S. (1989): ‘AUDITEL: details of the experiments and results’. Proc. of the 12th Int. Symp. on Human Factors in Telecom-munication, HFT ‘88, The Hague, May 1988.
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1990 Springer-Verlag Berlin, Heidelberg
About this paper
Cite this paper
van Nes, F.L. (1990). A Field Trial with Speech Recognition for Telecommunication. In: Ohnsorge, H. (eds) Benutzerfreundliche Kommunikation / User-Friendly Communication. Telecommunications, vol 15. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-51146-2_15
Download citation
DOI: https://doi.org/10.1007/978-3-642-51146-2_15
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-52536-3
Online ISBN: 978-3-642-51146-2
eBook Packages: Springer Book Archive