• Corpus ID: 17779711

WINDMILL-THE USE OF A PARSING ALGORITHM TO PRODUCE PREDICTIONS FOR DISABLED PERSONS

@inproceedings{Wood1996WINDMILLTHEUO,
  title={WINDMILL-THE USE OF A PARSING ALGORITHM TO PRODUCE PREDICTIONS FOR DISABLED PERSONS},
  author={Matthew Edward John Wood and Eric Lewis},
  year={1996}
}
Augmentative and Alternative Communication (AAC) systems are designed to enable people to communicate with those around them when they are unable to do so themselves. Such people include those su ering from congenital diseases, such as cerebral palsy; progressive diseases, such as motor-neuron disease and multiple sclerosis; or those who have been the victim of a trauma, such as a head injury. The devices employed to aid such subjects can be categorised into four groups: 

Figures from this paper

Computer-assisted transcription of speech based on confusion network reordering

This work proposes a method for computer-assisted transcription of speech, based on automatic reordering confusion networks, that allows to significantly reduce the number of actions needed to correct ASR outputs.

Towards lifelong human assisted speaker diarization

Computer-assisted Speaker Diarization: How to Evaluate Human Corrections

A framework to evaluate the human corrections of a speaker diarization using French broadcast news drawn from the REPERE corpus is presented and an automaton to simulate the correction sequence is proposed.

An Adaptive Keyboard with Personalized Language-Based Features

A personalized and adaptive on-screen keyboard for both single-handed and zero-handed users that combines tapping-based and motion-based text input with language-based acceleration techniques, including adaptive and adaptive task-based dictionary, frequent character prompting, word completion, and grammar checker with suffix completion is developed.

Semantic knowledge in word completion

We propose an integrated approach to interactive word-completion for users with linguistic disabilities in which semantic knowledge combines with $n$-gram probabilities to predict semantically

An Active Learning Method for Speaker Identity Annotation in Audio Recordings

A method which decreases the intervention number of a human is proposed, which corrects a diarization by taking into account the human interventions, and it is evaluated in terms of KSR (Keystroke Saving Rate), and it reduces the number of actions needed to correct a speaker darization output by 6.8% in absolute value.

MODELLING SEMANTIC KNOWLEDGE FOR A WORD COMPLETION TASK

This work proposes an integrated semantics-based word completion model that combines the semantic knowledge in the SKB with n-gram probabilities and proposes the strategy of using salient terms and the ad hoc algorithm for the OOV recognition.

EUMSSI: Multilayered Analysis of Multimedia Content Using UIMA, MongoDB and Solr

The EUMSSI platform provides support for both synchronous and asynchronous analysis processes and thus allows for on-demand services as well as long running batch processes, and builds on established open source projects such as UIMA, MongoDB and Solr.

Réordonnancement automatique d'hypothèses pour l'assistancè a la transcription de la parole

Les technologies de reconnaissance vocale automatique (ASR) a grand vocabulaire fonctionnent bien dans des contextes connus et controles. Cependant, certaines erreurs doivent encore etre corrigees.

Evaluating human corrections in a computer-assisted speaker diarization system

A framework to evaluate the human corrections of a speaker diarization system using French broadcast news drawn from the following campaigns: REPERE, ESTER and ETAPE is presented.

References

SHOWING 1-10 OF 13 REFERENCES

Adaptive and predictive techniques in a communication prosthesis

A reduction in the number of character inputs necessary to enter any given text of over 50% is possible when using PAL, giving the user a considerable saving in time and effort.

Grammatical Recognition in Computer Aided Conversation

A method of improving rates of prosthetic conversations through the use of word prediction in conjunction with grammatical recognition and how speech recognition can be used to improve the prediction facility by analysing the other half of the conversation to provide semantic information.

PACE-Grammatical Recognition in Computer Aided Conversation

A method of improving rates of prosthetic conversations through the use of word prediction in conjunction with grammatical recognition, and how speech recognition can be used to improve the prediction facility by analysing the other side of the conversation to provide semantic information.

Prediction and conversational momentum in an augmentative communication system

C u r r e n t computer technol-q teners outside the person's close ogy offers severely physi-circle, however, it is extremely diffi-I ~ l b ~'~ cally impaired nonspeak-~ cult to accomplish such vital

Introduction to expert systems

From the Publisher: The third edition of Peter Jackson's book, Introduction to Expert Systems, updates the technological base of expert systems research and embeds those results in the context of a

Up from trigrams! - the struggle for improved language models

Generative Grammars

  • Longman Linuistics Library. Longman,
  • 1987

Syntactic Strutures

  • 1957

Syntax pal - a system to improve the syntax of those with language dysfunction

  • In The Proceedings of RESNA
  • 1991

Generative Grammars. Longman Linuistics Library

  • Generative Grammars. Longman Linuistics Library
  • 1987