Huffman and Linear Scanning Methods with Statistical Language Models

Brain–Computer Interfaces for Augmentative and Alternative Communication: A Tutorial

“…(Beukelman & Mirenda, 2013;Foulds, 1980), and slower speeds (two to five words per minute; Patel, 2011) are observed for letter spelling due to the need for multiple selections for spelling words (Hill & Romich, 2002). Word prediction and language modeling can increase both speed and typing efficiency (Koester & Levine, 1996;Roark et al, 2015;Trnka et al, 2008), but the benefits may be limited due to additional cognitive demands (Koester & Levine, 1996). Scan rate in auto-advancing row-column scanning access methods also affects communication rate, and though faster scan rates should lead to faster communication rates, slower scan rates can reduce selection errors (Roark et al, 2015).…”

“…Word prediction and language modeling can increase both speed and typing efficiency (Koester & Levine, 1996;Roark et al, 2015;Trnka et al, 2008), but the benefits may be limited due to additional cognitive demands (Koester & Levine, 1996). Scan rate in auto-advancing row-column scanning access methods also affects communication rate, and though faster scan rates should lead to faster communication rates, slower scan rates can reduce selection errors (Roark et al, 2015). BCIs are similarly affected by scan rate (Sellers & Donchin, 2006); for example, a P300 speller can only operate as fast as each item is flashed.…”

Recursive coding for AAC systems

“…Further, multiple works compare different row-item style keyboard arrangements [64,65,66]. In the works most similar to our own, Baljko and Roark design decision trees based on Huffman codes to offer a minimum number of trials per decision [62,67,68]; the major distinction is that our formulation considers that some trials take more time than others (selection of the first query set takes less time that selection of the second query set).…”

Configurações para métodos de acesso por escaneamento

“…Em uma série de trabalhos, Roark et al (2010Roark et al ( , 2013Roark et al ( , 2015 apresentaram um padrão de varredura não linear como método de acesso por escaneamento [76] [16] [77].…”

“…A transcrição de sentenças é uma atividade que se aproxima de um contexto real de comunicação executada por um usuário de CAA. Por essa razão, escolhe-se esse método como ferramenta de pesquisa nessa área para a avaliação de diferentes configurações em sistemas de escaneamento, tais como: taxa de varredura [104] [80], arranjo de teclas [72] [24], previsão de palavras [97] e paradigmas de escaneamento [77].…”