Investigating Speech Recognition for Improving Predictive AAC
Making good letter or word predictions can help accelerate the communication of users of high-tech AAC devices. This is particularly important for real-time person-to-person conversations. We investigate whether per forming speech recognition on the speaking-side of a conversation can improve language model based predictions. We compare the accuracy of three plausible microphone deployment options and the accuracy of two commercial speech recognition engines (Google and IBM Watson). We found that despite recognition word error rates of 7-16%, our ensemble of N-gram and recurrent neural network language models made predictions nearly as good as when they used the reference transcripts.
Data supporting this paper can be accessed at https://digitalcommons.mtu.edu/data-files/1/
SLPAT '19: Proceedings of the Eighth Workshop on Speech and Language Processing for Assistive Technologies
Stanage, A. M.,
Investigating Speech Recognition for Improving Predictive AAC.
SLPAT '19: Proceedings of the Eighth Workshop on Speech and Language Processing for Assistive Technologies, 37-43.
Retrieved from: https://digitalcommons.mtu.edu/cs_fp/16