Disambiguating speech commands using physical context

ABSTRACT

Speech has great potential as an input mechanism for ubiquitous computing. However, the current requirements necessary for accurate speech recognition, such as a quiet environment and a well-positioned and high-quality microphone, are unreasonable to expect in a realistic setting. In a physical environment, there is often contextual information which can be sensed and used to augment the speech signal. We investigated improving speech recognition rates for an electronic personal trainer using knowledge about what equipment was in use as context. We performed an experiment with participants speaking in an instrumented apartment environment and compared the recognition rates of a larger grammar with those of a smaller grammar that is determined by the context.

REFERENCES

• 1: G. S.Aist and J. Mostow. 1997. Adapting Human Tutorial Interventions for a Reading Tutor that Listens: Using Continous Speech Recognition in Interactive Educational Multimedia. In CALL '97 Conference on Multimedia, England.
• 2: Answers Anywhere www.iAnywhere.com
• 3: Chang, K. Chen, M., Canny, J., Towards Balanced Exercise Programs: Tracking Free-weight Exercises, Ubicomp 2007.
• 4: Coen, M.; Weisman, L; Thomas, K; Groh, M. A Context Sensitive Natural Language Modality for the Intelligent Room. In Proc. MANSE'99. Dublin, Ireland. 1999.
• 5: Consolvo, S., Paulos, E., Smith, I. Mobile Persuasion for Everyday Behavior Change. Mobile Persuasion. Stanford Captology Media. 2007
• 6: Richard C. Davis , T. Scott Saponas , Michael Shilman , James A. Landay, SketchWizard: Wizard of Oz prototyping of pen-based user interfaces, Proceedings of the 20th annual ACM symposium on User interface software and technology, October 07-10, 2007, Newport, Rhode Island, USA [doi>10.1145/1294211.1294233]
• 7: Anind K. Dey, Understanding and Using Context, Personal and Ubiquitous Computing, v.5 n.1, p.4-7, February 2001 [doi>10.1007/s007790170019]
• 8: J. R. Glass , T. J. Hazen , I. L. Hetherington, Real-time telephone-based speech recognition in the Jupiter domain, Proceedings of the Acoustics, Speech, and Signal Processing, 1999. on 1999 IEEE International Conference, p.61-64, March 15-19, 1999 [doi>10.1109/ICASSP.1999.758062]
• 9: Lee Hoi Leong , Shinsuke Kobayashi , Noboru Koshizuka , Ken Sakamura, CASIS: a context-aware speech interface system, Proceedings of the 10th international conference on Intelligent user interfaces, January 10-13, 2005, San Diego, California, USA [doi>10.1145/1040830.1040880]
• 10: Microsoft Speech Server http://microsoft.com/speech
• 11: MySportTraining 3.97 by VidaOne, Inc http://www.pocketgear.com/software_detail.asp?id=630
• 12: Tim Paek , David Maxwell Chickering, Improving command and control speech recognition on mobile devices: using predictive user models for language modeling, User Modeling and User-Adapted Interaction, v.17 n.1-2, p.93-117, March 2007 [doi>10.1007/s11257-006-9021-6]
• 13: Matthai Philipose , Joshua R. Smith , Bing Jiang , Alexander Mamishev , Sumit Roy , Kishore Sundara-Rajan, Battery-free Wireless Identification and Sensing, IEEE Pervasive Computing, v.4 n.1, p.37-45, January 2005 [doi>10.1109/MPRV.2005.7]
• 14: R. Porzel and I. Gurevych, Contextual Coherence in Natural Language Processing, CONTEXT 2003, LNAI 2680, Springer-Verlag, pp 272--285, 2003.
• 15: Lawrence Rabiner , Biing-Hwang Juang, Fundamentals of speech recognition, Prentice-Hall, Inc., Upper Saddle River, NJ, 1993
• 16: Joshua R. Smith, Alanson Sample, Pauline Powledge, Alexander Mamishev, Sumit Roy. A wirelessly powered platform for sensing and computation. In Proc. Ubicomp 2006
• 17: C. Wai, R. Pieraccini, and H. M. Meng, A Dynamic Semantic Model for Re-scoring Recognition Hypotheses, In Proceedings of ICASSP2001, pp 589--592, 2001.
• 18: Mark Weiser , John Seely Brown, The coming age of calm technolgy, Beyond calculation: the next fifty years, Copernicus, New York, NY, 1997
• 19: Mark Weiser, "The Computer for the Twenty-First Century," Scientific American, pp. 94--10, September 1991

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

General Terms:
Design, Experimentation, Human Factors, Measurement

Keywords:
context, exercise, fitness, speech recognition