Smartphone speech-to-text applications for communication with profoundly deaf patients

OBJECTIVE: Visual communication aids, such as handwriting or typing, are often used to communicate with deaf patients in the clinic. This study aimed to establish the feasibility of communicating through smartphone speech recognition software compared with writing or typing.

METHOD: Thirty doctors and medical students were timed writing, typing and dictating a standard set of six sentences appropriate for a post-operative consultation, and the results were assessed for accuracy and legibility.

RESULTS: The mean time for smartphone dictation (17.8 seconds, 95 per cent confidence interval = 17.0-18.7) was significantly faster than writing (59.2 seconds, 95 per cent confidence interval = 56.6-61.7) or typing (44 seconds, 95 per cent confidence interval = 41.0-47.1) (p < 0.001). Speech recognition was slightly less accurate, but accuracy increased with time spent dictating.

CONCLUSION: Smartphone dictation is a feasible alternative to typing and handwriting. Slow speech may improve accuracy. Early clinical experience has been promising.