Automatic speech recognition for disabled people
โ Scribed by J.M. Noyes; R. Haigh; A.F. Starr
- Publisher
- Elsevier Science
- Year
- 1989
- Tongue
- English
- Weight
- 729 KB
- Volume
- 20
- Category
- Article
- ISSN
- 0003-6870
No coin nor oath required. For personal study only.
โฆ Synopsis
It has been suggested that one of the most promising areas for the application of speech recognition is in helping handicapped people (Leggett and Williams, 1984). Within the last decade, many improvements have been made in the performance of automatic speech recognisers and current technology is discussed in relation to the needs of the disabled population. Recent research developments'in the field of automatic speech recognition are reviewed, with particular reference to voice control of robotic arms and environmental control units. This includes a description of a Voice Activated Domestic Appliance System (VADAS), whose evaluation has just been completed. The general conclusion reached is that although speech recognition applications for disabled people are well within the capacity of available technology, it is primarily a lack of human factors work which is impeding developments.in this field. Several human factors issues are identified; the most important of these being the need to increase the reliability of present speech recognisers, before they can confidently be incorporated into the lives of the disabled population.
๐ SIMILAR VOLUMES
This paper concerns the use of formant frequency information in automatic speech recognition. The discussion is addressed to the physical significance of the formant and to how this relates t o the phonetic concepts of segment and equivalence that are needed for the recognition of phonetic types. Sp
In this paper we address application of minimum Bayes-risk classifiers to tasks in automatic speech recognition (ASR). Minimum-risk classifiers are useful because they produce hypotheses in an attempt to be optimal under a specified task-dependent performance criterion. While the form of the optimal
This paper presents a new approach to multi-band automatic speech recognition which has the advantage to overcome many limitations of classical muti-band systems. The principle of this new approach is to build a speech model in the time-frequency domain using the formalism of dynamic Bayesian networ