Shaping user input in speech graffiti: a first pass

ABSTRACT

Speech Graffiti is a standardized interaction protocol for spoken dialog systems designed to address some com-mon difficulties with ASR. We have proposed a strategy of shaping to help users adapt their interaction to match what the system understands best, thereby re-ducing the chance for misunderstandings and improving interaction efficiency. In this paper we report on an evaluation of our initial implementation of shaping in Speech Graffiti, noting that our baseline strategy was not as powerful as expected, and discussing proposed changes to improve its effectiveness.

REFERENCES

• 1: Brennan, S.E. Lexical entrainment in spontaneous dialog. In Proc. ISSD 1996, 41--44.
• 2: Domjan, M. The Essentials of Conditioning and Learning. Thomson Wadsworth, Belmont CA, USA 2005.
• 3: Harris, T.K. and Rosenfeld, R. A Universal Speech Interface for Appliances. In Proc. ICSLP 2004.
• 4: Hone, K. and Graham, R. Subjective Assessment of Speech-System Interface Usability. In Proc. Eurospeech 2001.
• 5: Mark D. Jackson, Constrained languages need not constrain person/computer interaction, ACM SIGCHI Bulletin, v.15 n.2-3, p.18-22, October 1983 [doi>10.1145/1044782.1044784]
• 6: Matarazzo, J.D., Weitman, M., Saslow, G. and Weins, A.N. Interviewer influence on duration of interviewee speech. Journal of Verbal Learning and Verbal Behavior 1 (1963), 451--458.
• 7: Ben Shneiderman, Natural vs. precise concise languages for human operation of computers: research issues and experimental approaches, Proceedings of the 18th annual meeting on Association for Computational Linguistics, June 19-22, 1980, Philadelphia, Pennsylvania [doi>10.3115/981436.981478]
• 8: Sidner, C. and Forlines, C. Subset Languages for Conversing with Collaborative Interface Agents. In Proc. ICSLP 2002, 281--284.
• 9: Tomko, S. Speech Graffiti: Assessing the User Experience. CMU LTI Tech Report CMU-LTI-04-185 (2004). www.cs.cmu.edu/~stef/papers/mthesis.ps
• 10: Stefanie Tomko , Thomas K. Harris , Arthur Toth , James Sanders , Alexander Rudnicky , Roni Rosenfeld, Towards efficient human machine speech communication: The speech graffiti project, ACM Transactions on Speech and Language Processing (TSLP), v.2 n.1, p.2-es, February 2005 [doi>10.1145/1075389.1075391]
• 11: Toth, A., Harris, T., Sanders, J., Shriver, S., and Rosenfeld, R. Towards Every-Citizen's Speech Interface: An Application Generator for Speech Inter-faces to Databases. In Proc. ICSLP 2002, 1497--1500.
• 12: Elizabeth Zoltan-Ford, How to get people to say and type what computers can understand, International Journal of Man-Machine Studies, v.34 n.4, p.527-547, April 1991 [doi>10.1016/0020-7373(91)90034-5]

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.5 INFORMATION INTERFACES AND PRESENTATION (I.7)
      H.5.2 User Interfaces (D.2.2, H.1.2, I.3.6)
          Subjects: Voice I/O

Keywords:
speech recognition, spoken dialog systems, user interfaces