ICSH 2015: Smart Health pp 333-339 | Cite as

A Speech-Based Mobile App for Restaurant Order Recognition and Low-Burden Diet Tracking

Conference paper
First Online:
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9545)

Abstract

Obesity is a public health problem in the US. Diet tracking helps control obesity but manual entry is tedious. Proposed solutions such as food recognition from photographs and scanning barcodes have limitations. We investigate the use of speech recognition for diet recording. We improved the accuracy of food order recognition at restaurants by (1) limiting words in the speech recognizer’s corpus to only items on the menus of nearby restaurants (2) implementing an acoustic model to recognize the speaking style of the smartphone owner. Building on these mechanisms, we propose DietRecord, a smartphone application that automatically recognizes and records restaurant orders. Results of our user studies to evaluate DietRecord were encouraging.

Keywords

Speech Recognition Acoustic Model Nutrition Information Speech Recognition System Menu Item 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
This is a preview of subscription content, log in to check access.

References

  1. 1.
    National Center for Health Statistics. http://www.cdc.gov/nchs/
  2. 2.
    Kong, F., Tan, J.: DietCam: regular shape food recognition with a camera phone. In: Proceedings of the BSN. IEEE (2011)Google Scholar
  3. 3.
    Food Research and Action Center (FRAC), Overweight and Obesity in the US. http://frac.org/initiatives/hunger-and-obesity/obesity-in-the-us/
  4. 4.
    Rozzi, W.A., Stern, R.M.: Speaker adaptation in cont. speech recognition via estimation of correlated mean vectors. In: IEEE Proceedings of the ICASSP 1991 (1991)Google Scholar
  5. 5.
    Jyothi, P., et al.: Distributed discriminative language models for Google voice-search. In: Proceedings of the ICASSP. IEEE (2012)Google Scholar
  6. 6.
    Huggins-Daines, D., et al.: Pocketsphinx: a free, real- time cont. speech recognition system for hand-held devices. In: Proceedings of the IEEE ICASSP (2006)Google Scholar
  7. 7.
    Vertanen, K., Kristenssen, P.: Parakeet: a cont. speech recognition system for mobile touch-screen devices. In: Proceedings of the ACM IUI 2009 (2009)Google Scholar
  8. 8.
    Andrew, A.H., Boriello, G., Fogarty, J.: Simplifying mobile phone food diaries. In: Proceedings of the Pervasive Health 2013 (2013)Google Scholar
  9. 9.
    Hsu, H.H., Min-Ho, C., Neil, Y.Y.: A health man- agement application with QR-code input and rule inference. In: Proceedings of the ISIC. IEEE (2012)Google Scholar
  10. 10.
    Ohbuchi, E., Hiroshi, H., Lim, A.H.: Barcode readers using the camera device in mobile phones. In: Proceedings of the International Conference Cyberwords (2004)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  1. 1.Computer Science DepartmentWorcester Polytechnic InstituteWorcesterUSA

Personalised recommendations