Search results

There are severe limitations to the speech recognition systems currently on the market and the articles in this special report make quite clear what the systems will not do and why.

This paper describes the development process of a mobile Voice User Interface (VUI) for Korean users with dysarthria with currently available speech recognition technology by conducting systematic user needs analysis and applying usability testing feedback to prototype system designs.

Four usability surveys are conducted for the development of the prototype system. According to the two surveys on user needs and user experiences with existing VUI systems at the stage of the prototype design, the target platforms, and target applications are determined. Furthermore, a set of basic words is selected by the prospective users, which enables the system to be not only custom designed for dysarthric speakers but also individualized for each user. Reflecting the requests relating to general usage of the VUI and the UI design preference of users through evaluation of the initial prototype, we develop the final prototype, which is an individualized voice keyboard for mobile devices based on an isolated word recognition engine with word prediction.

The results of this paper show that target user participation in system development is effective for improving usability and satisfaction of the system, as the system is developed considering various ideas and feedback obtained in each development stage from different prospective users.

We have developed an automatic speech recognition-based mobile VUI system not only custom designed for dysarthric speakers but also individualized for each user, focussing on the usability aspect through four usability surveys. This voice keyboard system has the potential to be an assistive and alternative input method for people with speech impairment, including mild to moderate dysarthria, and people with physical disabilities.

Mobile handheld devices, such as cellular phones and personal digital assistants, are inherently small and lack an intuitive and natural user interface. Speech recognition and synthesis technology can be used in mobile handheld devices to improve the user experience. The purpose of this paper is to describe a prototype system that supports multiple speech‐enabled applications in a mobile handheld device.

The main component of the system, the Program Manager, coordinates and controls the speech‐enabled applications. Human speech requests to, and responses from, these applications are processed in the mobile handheld device, to achieve the goal of human‐like interactions between the human and the device. In addition to speech, the system also supports graphics and text, i.e., multimodal input and output, for greater usability, flexibility, adaptivity, accuracy, and robustness. The paper presents a qualitative and quantitative evaluation of the prototype system. The Program Manager is currently designed to handle the specific speech‐enabled applications that we developed.

The paper determines that many human interactions involve not single applications but multiple applications working together in possibly unanticipated ways.

Future work includes generalization of the Program Manager so that it supports arbitrary applications and the addition of new applications dynamically. Future work also includes deployment of the Program Manager and the applications on cellular phones running the Android Platform or the Openmoko Framework.

This paper presents a first step towards a future human interface for mobile handheld devices and for speech‐enabled applications operating on those devices.

The purpose of this paper is to present evidence of the need to have a carefully designed lexical model for speech recognition for dyslexic children reading in Bahasa Melayu (BM).

Data collection is performed to obtain the most frequent reading error patterns and the reading recordings. Design and development of the lexical model considers the errors for better recognition accuracy.

It is found that the recognition accuracy is increased to 75 percent when using context‐dependent (CD) phoneme model and phoneme refinement rule. Comparison between context‐independent phoneme models and CD phoneme model is also presented.

The most frequent errors recognized and obtained from data collection and analysis illustrate and support that phonological deficit is the major factor for reading disabilities in dyslexics.

This paper provides the first step towards materializing an automated speech recognition (ASR)‐based application to support reading for BM, which is the first language in Malaysia.

The paper contributes to the knowledge of the most frequent error patterns for dyslexic children's reading in BM and to the knowledge that a CD phoneme model together with the phoneme refinement rule can built up a more fine‐tuned lexical model for an ASR specifically for dyslexic children's reading isolated words in BM.

We have followed recent developments in computer hardware library and information uses in these pages. Readers have likely noticed that the emphasis has been on equipment for micro/ personal computers. That will continue to be the focus here.

Algorithms developed at the Royal Signals and Radar Establishment and the Joint Speech Research Unit open the way to greater precision in distinguising similar words and to recognition of continuously spoken connected speech.

Reports in the popular press suggest much consumer frustration with interactive voice response (IVR) self‐service. The present study aims to conceptualize why frustration might occur and measures attitudes toward IVR.

Questionnaire responses were obtained from a quota sample approximately equally divided among men and women and three age groups (18‐28, 29‐48, 49 and older).

Compared to a human operator, consumers perceive that transactions conducted through IVR take longer and are less customizable. Respondents strongly prefer a human operator, believe that IVR was implemented to benefit the company more than customers, and are bothered by not having an initial choice of a human operator versus IVR. Despite these negative views, satisfaction with IVR was primarily driven by transaction speed rather than concerns with these other issues. Compared to younger consumers, older respondents held a more cynical view of IVR and the companies that employ the technology.

Only inbound (and not outbound) IVR calls were studied and only customers (and not employees) were surveyed.

Frustration with IVR resulted in a “spillover” effect, lowering overall regard for the firm. Five managerial recommendations are suggested that may help recapture lost goodwill.

This is believed to be the first study to offer a theoretic explanation for consumer frustration with IVR. Also, the comparison of age groups on attitudes toward IVR in the present study may be novel.

The Lucas Factory in Wolverhampton is the Actuation Division of Lucas Aerospace which manufactures a large range of products covering powered flying control systems and actuators, engine pneumatic actuation systems, general airframe hydraulic systems and components, and fuel management equipment.

A recent supplement to the journal of the Czechoslovak Association for Cybernetics, Kybernetika, Vol. 24, 1988, pp. 3–24, which was published under the auspices of the Czechoslovak Academy of Sciences, was concerned with the use of the multidimensional z‐transform in the solution of partial difference equations. Written by Dr Jiri Gregor it gives a survey of (generalised) multidimensional z‐transform (n‐D‐z transform) method and its use in the solution of linear partial difference equations with constant coefficients, as well as systems of such equations, whose solutions the author calls sequences. He says that this theory is aimed at forming a basis of multidimensional digital system theory which attracted wide and increasing attention in the last decade.

Some facilities managers will be in the position of adapting existing space to cope with changing needs, while others will be concerned with drawing up specifications for new spaces. Both need practical advice from the acoustician about how to deal with existing problems of speech and noise in rooms. Many offices facing crises in space planning and in staff management are also faced with difficulties concerning speech acoustics, particularly in the areas of speech intelligibility, speech privacy and noise. Research into these aspects of room acoustics by the present author has resulted in an improved approach to measuring the information characteristics of both speech and noise in rooms. A design index is described for predicting the intelligibility of speech and is illustrated by a typical example of conditions in the open plan office. Advice is also needed on the implications of new speech technologies (speech synthesis and speech recognition) on office layout. These new products have already been in everyday use for over 10 years in some office environments and are becoming more commonplace. It is shown that as the new, speech‐driven equipment is taken up, the problems of containing noise in open‐plan spaces will increase, unless speech acoustics in the office is given a new priority.