How to Design Dialogue Scenarios and Estimate Main Dialogue Parameters for a Voice-Controlled Man-Machine Interface

In this paper we classify and analyze dialogue scenarios in automated human-machine systems with speech recognition. We take into account how to identify and correct recognition errors. Also, we evaluate and compare the scenarios according to how long the dialogue lasts, provided that the dialogue completes successfully with at least some given probability. Based on the results of our work, we formulated recommendations for developers of speech dialogue systems to choose a dialogue scenario; the actual scenario depends on how reliable the used speech blocks are. © 2019 IEEE.

Authors
Farkhadov M.1, 2 , Petukhova N.1 , Eliseev A.1 , Farkhadova M. 3
Conference proceedings
13th IEEE International Conference on Application of Information and Communication Technologies, AICT 2019 - Proceedings
Publisher
Institute of Electrical and Electronics Engineers Inc.
Language
English
Status
Published
DOI
10.1109/AICT47866.2019.8981770
Number
8981770
Year
2019
Organizations
  • 1 Automated Queuing Systems and Signal Processing, V.A. Trapeznikov Institute of Control Sciences, RAS, Moscow, Russian Federation
  • 2 Wireless Technologies Lab, MIPT, Dolgoprudny, Russian Federation
  • 3 Faculty of Russian Language and General Educational Disciplines, RUDN University, Moscow, Russian Federation
Keywords
duration of the dialogue; probabilistic methods; probability of successful completion of the dialogue; scenarios and algorithms for managing speech dialogue; speech interface
Cite
ГОСТ MLA RIS BibTex
Share

Other records

ENHANCED RADIO ACCESS PROCEDURE IN SLICED 5G NETWORKS

Article
Vikhrova O., Suraci C., Tropeano A., Pizzi S., Samouylov K., Araniti G.
11th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops, ICUMT 2019, Dublin, Ireland, October 28-30, 2019. IEEE. Vol. 2019-October. 2019.