International Journal of Speech Technology

, Volume 8, Issue 3, pp 247–257 | Cite as

Bitter Pills to Swallow. ASR and TTS have Drug Problems

  • Caroline Henton


In an emerging application of speech technology, physicians speak prescription orders into wireless handheld devices that record the order using automatic speech recognition (ASR). Orders are recognized using ASR, then displayed on the screen for verification and, after checking, are relayed to the pharmacy for filling. Given the frequent opportunities for mistakes, this scenario provokes chills in many of us. Many physicians do not speak English as a native language, or they have a strongly accented variety of English.

Some drugs are familiar enough that they should not present recognition/pronunciation difficulties (e.g. aspirin, codeine). Hundreds of drug names are easily confusable; other names range from opaque to ambiguous to ‘no idea’ with regard to pronunciation.

The problems with the ‘unknowable’ drug names (the majority) are sometimes alleviated by drug manufacturers providing a ‘pronunciation hint’, in a dictionary-style phonetic transcription. This is not necessarily helpful to native or non-native speakers of English, or those unfamiliar with such renditions. More often, we are left to our own (wobbly) intuitions about stress placement, vowel length or ‘hard’ or ‘soft’ letter ‘c’, etc. Speaking the potentially infinite class of drug names correctly is an extra challenge for any TTS system.

This paper presents data for drug names in the confusable, transparent, opaque, and unknowable categories. The clear and present dangers for patients receiving the wrong drugs and for everyone using such speech-automated systems are examined.


speech technology in healthcare linguistic diversity pronunciation problems 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Andolsen, A.A. (2004). Can you understand me now? The Information Management Journal, 38(1):52–56.Google Scholar
  2. Associated Press (March 13, 2004) Company invents talking chips for prescription bottles.
  3. Clayton, B.D. and Stock, Y.N. (2004). Basic Pharmacology for Nurses. 13th Edn. Mosby.Google Scholar
  4. Grasso, M.A. (2003). The long-term adoption of speech recognition in medical applications. In Proceedings of the 16th IEEE Symposium on Computer-Based Medical Systems (CBMS 2003), 257–262.Google Scholar
  5. Henton, C. (2002). You say ‘zee’, and I say ‘zed’. Issues in localizing voice-driven applications. Speech Technology, May/June:28–31.Google Scholar
  6. Henton, C. (2003). The name game: pronunciation puzzles for TTS. Speech Technology, September/October, 32–35.Google Scholar
  7. HLT News. (April 1, 2004). Speaking bottles,
  8. Hodgson, B.B. and Kizior, R.J. (2003). Saunders Nursing Drug Reference 2004. W.B. Saunders.Google Scholar
  9. MBF News (March 30, 2004) Similar sounding drug names raise medication error risk.
  10. Nursing 2004 Drug Handbook. 24th edn., Lippincott, Springhouse Publishing Company.Google Scholar
  11. Rolandi, W. (2003). When you don’t know when you don’t know. Speech Technology, July/August: 28.Google Scholar
  12. Springhouse Nurse’s Drug Guide 2004. Lipincott.Google Scholar
  13. Skidmore-Roth, L. (2003). Mosby’s Nursing Drug Reference. MosbyGoogle Scholar
  14. Truss, L. (2003). Eats Shoots & Leaves. The Zero Tolerance Guide to Punctuation. London: Profile Books.Google Scholar
  15. Voice of the Injured (2004). Prescription errors due to similar drug names.
  16. United States Pharmacopeial Convention, Inc.(1999). Use Caution, Avoid Confusion. U.S. Pharmacopeia Quality Review no. 76 (2001).
  17. U.S. Pharmacopeia Quality Review No. 73 (March, 2000).Google Scholar
  18. U.S Pharmacopeia (2001). USP identifies more than 750 unique drug names reported to cause confusion. Entity = PRAsset&EntityID=3139&XSL=PressRelease.

Copyright information

© Springer Science + Business Media, LLC 2006

Authors and Affiliations

  1. 1.CTO, TalknowledgySanta Cruz

Personalised recommendations