Search

Individuals with severe motor impairments commonly enter text using a single binary switch and symbol scanning methods. We present a new scanning method – Huffman scanning – which uses Huffman coding to select the symbols to highlight during scanning, thus minimizing the expected bits per symbol. With our method, the user can select the intended symbol even after switch activation errors. We describe two varieties of Huffman scanning – synchronous and asynchronous – and present experimental results, demonstrating speedups over row/column and linear scanning.

We are delighted to bring you this special issue on speech and language processing for assistive technology. It addresses an important research area that is gaining increased recognition from researchers in speech and language processing as a rich and fulfilling area on which to focus their work, and by researchers in assistive technology as the means to dramatically improve communication technologies for individuals with disabilities. This special issue brings a wide swath of approaches and applications highlighting the variety this area offers.

Significant progress has been made in the application of natural language processing (NLP) to augmentative and alternative communication (AAC), particularly in the areas of interface design and word prediction. This article will survey the current state-of-the-science of NLP in AAC and discuss its future applications for the development of next generation of AAC technology.

This paper describes discriminative language modeling for a large vocabulary speech recognition task. We contrast two parameter estimation methods: the perceptron algorithm, and a method based on maximizing the regularized conditional log-likelihood. The models are encoded as deterministic weighted finite state automata, and are applied by intersecting the automata with word-lattices that are the output from a baseline recognizer. The perceptron algorithm has the benefit of automatically selecting a relatively small feature set in just a couple of passes over the training data. We describe a method based on regularized likelihood that makes use of the feature set given by the perceptron algorithm, and initialization with the perceptron's weights; this method gives an additional 0.5% reduction in word error rate (WER) over training with the perceptron alone. The final system achieves a 1.8% absolute reduction in WER for a baseline first-pass recognition system (from 39.2% to 37.4%), and a 0.9% absolute reduction in WER for a multi-pass recognition system (from 28.9% to 28.0%).

This paper investigates discriminative language modeling in a scenario with two kinds of observed errors: errors in ASR transcription and errors in utterance classification. We train joint language and class models either independently or simultaneously, under various parameter update conditions. On a large vocabulary customer service call-classification application, we show that simultaneous optimization of class, n-gram, and class/n-gram feature weights results in a significant WER reduction over a model using just n-gram features, while additionally significantly outperforming a deployed baseline in classification error rate. A range of parameter estimation approaches, based on either the perceptron algorithm or conditional log-linear models, for various feature sets are presented and evaluated. The resulting models are encoded as weighted finite-state automata, and are used by intersecting the model with word lattices.

This paper investigates supervised and unsupervised adaptation of stochastic grammars, including n-gram language models and probabilistic context-free grammars (PCFGs), to a new domain. It is shown that the commonly used approaches of count merging and model interpolation are special cases of a more general maximum a posteriori (MAP) framework, which additionally allows for alternate adaptation approaches. This paper investigates the effectiveness of different adaptation strategies, and, in particular, focuses on the need for supervision in the adaptation process. We show that n-gram models as well as PCFGs benefit from either supervised or unsupervised MAP adaptation in various tasks. For n-gram models, we compare the benefit from supervised adaptation with that of unsupervised adaptation on a speech recognition task with an adaptation sample of limited size (about 17h), and show that unsupervised adaptation can obtain 51% of the 7.7% adaptation gain obtained by supervised adaptation. We also investigate the benefit of using multiple word hypotheses (in the form of a word lattice) for unsupervised adaptation on a speech recognition task for which there was a much larger adaptation sample available. The use of word lattices for adaptation required the derivation of a generalization of the well-known Good-Turing estimate. Using this generalization, we derive a method that uses Monte Carlo sampling for building Katz backoff models. The adaptation results show that, for adaptation samples of limited size (several tens of hours), unsupervised adaptation on lattices gives a performance gain over using transcripts. The experimental results also show that with a very large adaptation sample (1050h), the benefit from transcript-based adaptation matches that of lattice-based adaptation. Finally, we show that PCFG domain adaptation using the MAP framework provides similar gains in F-measure accuracy on a parsing task as was seen in ASR accuracy improvements with n-gram adaptation. Experimental results show that unsupervised adaptation provides 37% of the 10.35% gain obtained by supervised adaptation.

We present the software design principles, algorithms, and utilities of a general weighted grammar library, the GRM Library, that can be used in a variety of applications in text, speech, and biosequence processing. Several of the algorithms and utilities of this library are described, including in some cases their pseudocodes and pointers to their use in applications. The algorithms and the utilities were designed to support a wide variety of semirings and the representation and use of large grammars and automata of several hundred million rules or transitions.

This paper presents modifications to a standard probabilistic context-free grammar that enable a predictive parser to avoid garden pathing without resorting to any ad-hoc heuristic repair. The resulting parser is shown to apply efficiently to both newspaper text and telephone conversations with complete coverage and excellent accuracy. The distribution over trees is peaked enough to allow the parser to find parses efficiently, even with the much larger search space resulting from overgeneration. Empirical results are provided for both Wall St. Journal and Switchboard test corpora.

Objective. We aim to increase the symbol rate of electroencephalography (EEG) based brain–computer interface (BCI) typing systems by utilizing context information. Approach. Event related potentials (ERP) corresponding to a stimulus in EEG can be used to detect the intended target of a person for BCI. This paradigm is widely utilized to build letter-by-letter BCI typing systems. Nevertheless currently available BCI typing systems still require improvement due to low typing speeds. This is mainly due to the reliance on multiple repetitions before making a decision to achieve higher typing accuracy. Another possible approach to increase the speed of typing while not significantly reducing the accuracy of typing is to use additional context information. In this paper, we study the effect of using a language model (LM) as additional evidence for intent detection. Bayesian fusion of an n-gram symbol model with EEG features is proposed, and a specifically regularized discriminant analysis ERP discriminant is used to obtain EEG-based features. The target detection accuracies are rigorously evaluated for varying LM orders, as well as the number of ERP-inducing repetitions. Main results. The results demonstrate that the LMs contribute significantly to letter classification accuracy. For instance, we find that a single-trial ERP detection supported by a 4-gram LM may achieve the same performance as using 3-trial ERP classification for the non-initial letters of words. Significance. Overall, the fusion of evidence from EEG and LMs yields a significant opportunity to increase the symbol rate of a BCI typing system.