User Linguistic Model Adaptivity for Prediction in AAC Message Composition

Efficient linguistic prediction for AAC aids is a fundamental issue to increase and improve the communication capabilities of verbal disable people. However, although a number of works describing requirements for prediction engines in AAC languages exists, their adaptability to the specific needs of the user is lacking in literature. In this paper, we describe preliminary techniques for the adaptation of the AAC language model to the peculiar characteristics of the user. More precisely, we describe an automatic procedure able to produce a semantic/statistic linguistic model of the user language behavior given the overall AAC language model, the user dictionary, and a corpus of sentences produced by the user.

[1]  Zoubin Ghahramani,et al.  An Introduction to Hidden Markov Models and Bayesian Networks , 2001, Int. J. Pattern Recognit. Artif. Intell..

[2]  Matteo Matteucci,et al.  CABA2L A Bliss Predictive Composition Assistant for AAC Communication Software , 2004, ICEIS.

[3]  H. Chertkow,et al.  Semantic memory , 2002, Current neurology and neuroscience reports.

[4]  Jeff A. Bilmes,et al.  A gentle tutorial of the em algorithm and its application to parameter estimation for Gaussian mixture and hidden Markov models , 1998 .

[5]  Alan F. Newell,et al.  Adaptive and predictive techniques in a communication prosthesis , 1987 .

[6]  Klaus-Robert Müller,et al.  Asymptotic statistical theory of overtraining and cross-validation , 1997, IEEE Trans. Neural Networks.

[7]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[8]  Rich Caruana,et al.  Overfitting in Neural Nets: Backpropagation, Conjugate Gradient, and Early Stopping , 2000, NIPS.

[9]  Gregory W. Lesher,et al.  Techniques for augmenting scanning communication , 1998 .

[10]  Biing-Hwang Juang,et al.  The segmental K-means algorithm for estimating parameters of hidden Markov models , 1990, IEEE Trans. Acoust. Speech Signal Process..

[11]  Cristina Conati,et al.  What role can adaptive support play in an adaptable system? , 2004, IUI '04.

[12]  H H Koester,et al.  Learning and performance of able-bodied individuals using scanning systems with and without word prediction. , 1994, Assistive technology : the official journal of RESNA.