CS users have nearly-perfect reception of everyday connected speech materials. Audio-visual integration models suggest that CS users may be able to receive up to 80% of consonant-vowel syllables with automatic cues from current speech recognition computer programs.
Uchanski, R.M., Delhorne, L.A., Dix, A.K., Reed, C.M., Braida, L.D., and Durlach, N.I. (1994) "Automatic Speech Recognition to Aid the Hearing Impaired: Current Prospects for the Automatic Generation of Cued Speech." Journal of Rehabilitation Research and Development, Vol. 31, pp. 20-41.
CS is clearly and accurately readable, without sound, by deaf students with several years of CS experience.
Nicholls, G. (1979) "Cued Speech and the Reception of Spoken Language."
Master's thesis, McGill University, Montreal. (Available from NCSA/Cued Speech Discovery bookstore.)
Nicholls, G. & Ling, D. (1982) "Cued Speech and the Reception of Spoken Language."
Journal of Speech and Hearing Research, 25, 262-269.