Search results

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.

Speech recognition machines currently on the market are all built upon the same research foundation. The most important milestones on the road to present‐day systems are reviewed in this article based largely on an interview with Dr Roger Moore of the Royal Signals and Radar Establishment.

The purpose of this study was to investigate the effects of word-related factors (i.e. frequency, range, dispersion and cognateness) on first-language English (L1E) readers' (n = 20) and second-language English (L2E) readers' (n = 20) incidental acquisition of vocabulary through the reading of an authentic novel.

Participants read A Clockwork Orange by Anthony Burgess, a 58,686 token (word) English language novel containing Slovos, that is, words from Nadsat, a futuristic, foreignized teen talk invented by Burgess. Upon finishing the novel, the participants took two unexpected vocabulary tests, one for meaning recognition and the other for meaning recall.

The results of this study indicate that word-related factors significantly correlate with the word meaning recall test scores of both groups. However, the regression models of meaning recall for the two groups showed that dispersion was the most robust predictor, which implies that the participants recalled more word meanings when the novel had a more even distribution of the unknown target words. The meaning recognition test scores showed cognates were a significant predictor for the L1E readers but not for L2E readers.

This study marks the first attempt in the field to investigate the relative contribution of frequency, range and dispersion – a closely bound set of word-related factors – to both L1E and L2E readers' incidental acquisition of vocabulary through reading an authentic novel. Considering the important role of dispersion, the current study suggests that developers of graded readers and children's literature should more evenly distribute unknown target words in their books. Doing so will better facilitate both L1E and L2E readers' acquisition of those words. The study also addresses a fallacy of methodology regarding incidental vocabulary acquisition by examining the effect of the cognateness of the foreignized words embedded in A Clockwork Orange. The L1E readers' sensitivity to cognates implies that cognate-word awareness-raising activities are necessary to learning a foreign language, especially if that language has many cognates in common with English, such as Spanish.

The purpose of this paper is to present a system for recognition of location names in ancient books written in languages, such as Chinese, in which proper names are not signaled by an initial capital letter.

Rule-based and statistical methods were combined to develop a set of rules for identification of product-related location names in the local chronicles of Guangdong. A name recognition system, with functions of document management, information extraction and storage, rule management, location name recognition, and inquiry and statistics, was developed using Microsoft's .NET framework, SQL Server 2005, ADO.NET and XML. The system was evaluated with precision ratio, recall ratio and the comprehensive index, F.

The system was quite successful at recognizing product-related location names (F was 71.8 percent), demonstrating the potential for application of automatic named entity recognition techniques in digital collation of ancient books such as local chronicles.

Results suffered from limitations in initial digitization of the text. Statistical methods, such as the hidden Markov model, should be combined with an extended set of recognition rules to improve recognition scores and system efficiency.

Electronic access to local chronicles by location name saves time for chorographers and provides researchers with new opportunities.

Named entity recognition brings previously isolated ancient documents together in a knowledge base of scholarly and cultural value.

Automatic name recognition can be implemented in information extraction from ancient books in languages other than English. The system described here can also be adapted to modern texts and other named entities.

Not only does the problem of correcting spelling errors by computer have a long history, it is evidently of considerable current interest as papers and letters on the topic continue to appear rapidly. This is not surprising, since techniques useful in detecting and correcting mis‐spellings normally have other important applications. Moreover, both the power of small computers and the routine production of machine‐readable text have increased enormously over the last decade to the point where automatic spelling error detection/correction has become not only feasible but highly desirable.

This study aims to investigate the effects of word internal morphological form variation on adult first language (L1) (n = 20) incidental vocabulary acquisition through reading.

Participants were given a 37,611-token English novel containing pseudo words, placed throughout the text by the novelist. Two unexpected vocabulary assessments were administered at the completion of the reading task.

Results showed statistically significant effects for morphological form variation, with the readers having incidentally acquired more words whose tokens did not vary in form (i.e. no exposure to inflectional or derivational variants). However, a large effect size was present only for low-frequency words (two-four exposures).

Discussion of the results is given regarding the feasibility of enhancing adult L1 college readers’ morphological awareness through extensive reading and attention-drawing tasks.

The purpose of this paper is to classify Chinese word semantic relations, which are synonyms, antonyms, hyponyms and meronymys.

Basically, four simple methods are applied, ontology-based, dictionary-based, pattern-based and morpho-syntactic method. The authors make good use of search engine to build lexical and semantic resources for dictionary-based and pattern-based methods. To improve classification performance with more external resources, they also classify the given word pairs in Chinese and in English at the same time by using machine translation.

Experimental results show that the approach achieved an average F1 score of 50.87 per cent, an average accuracy of 70.36 per cent and an average recall of 40.05 per cent over all classification tasks. Synonym and antonym classification achieved high accuracy, i.e. above 90 per cent. Moreover, dictionary-based and pattern-based approaches work effectively on final data set.

For many natural language processing (NLP) tasks, the step of distinguishing word semantic relation can help to improve system performance, such as information extraction and knowledge graph generation. Currently, common methods for this task rely on large corpora for training or dictionaries and thesauri for inference, where limitation lies in freely data access and keeping built lexical resources up-date. This paper builds a primary system for classifying Chinese word semantic relations by seeking new ways to obtain the external resources efficiently.

There are believed to be something in the region of 250 different speech recognition systems available worldwide. This brief review, together with the articles on two British connected speech systems and the report on the Japanese scene, can do no more than give a taste of what is currently available in Britain.

This paper aims to propose a gesture recognition method at an early stage. An accelerometer is installed in most current mobile phones, such as iPhones, Android-powered devices and video game controllers for the Wii or PS3, which enables easy and intuitive operations. Therefore, many gesture-based user interfaces that use accelerometers are expected to appear in the future. Gesture recognition systems with an accelerometer generally have to construct models with user’s gesture data before use and recognize unknown gestures by comparing them with the models. Because the recognition process generally starts after the gesture has finished, the output of the recognition result and feedback delay, which may cause users to retry gestures, degrades the interface usability.

The simplest way to achieve early recognition is to start it at a fixed time after a gesture starts. However, the degree of accuracy would decrease if a gesture in an early stage was similar to the others. Moreover, the timing of a recognition has to be capped by the length of the shortest gesture, which may be too early for longer gestures. On the other hand, retreated recognition timing will exceed the length of the shorter gestures. In addition, a proper length of training data has to be found, as the full length of training data does not fit the input data until halfway. To recognize gestures in an early stage, proper recognition timing and a proper length of training data have to be decided. This paper proposes a gesture recognition method used in the early stages that sequentially calculates the distance between the input and training data. The proposed method outputs the recognition result when one candidate has a stronger likelihood of recognition than the other candidates so that similar incorrect gestures are not output.

The proposed method was experimentally evaluated on 27 kinds of gestures and it was confirmed that the recognition process finished 1,000 msec before the end of the gestures on average without deteriorating the level of accuracy. Gestures were recognized in an early stage of motion, which would lead to an improvement in the interface usability and a reduction in the number of incorrect operations such as retried gestures. Moreover, a gesture-based photo viewer was implemented as a useful application of our proposed method, the proposed early gesture recognition system was used in a live unscripted performance and its effectiveness is ensured.

Gesture recognition methods with accelerometers generally learn a given user’s gesture data before using the system, then recognizes any unknown gestures by comparing them with the training data. The recognition process starts after a gesture has finished, and therefore, any interaction or feedback depending on the recognition result is delayed. For example, an image on a smartphone screen rotates a few seconds after the device has been tilted, which may cause the user to retry tilting the smartphone even if the first one was correctly recognized. Although many studies on gesture recognition using accelerometers have been done, to the best of the authors’ knowledge, none of these studies has taken the potential delays in output into consideration.

There is a huge amount of information and data stored in publicly available online databases that consist of large text files accessed by Boolean search techniques. It is widely held that less use is made of these databases than could or should be the case, and that one reason for this is that potential users find it difficult to identify which databases to search, to use the various command languages of the hosts and to construct the Boolean search statements required. This reasoning has stimulated a considerable amount of exploration and development work on the construction of search interfaces, to aid the inexperienced user to gain effective access to these databases. The aim of our paper is to review aspects of the design of such interfaces: to indicate the requirements that must be met if maximum aid is to be offered to the inexperienced searcher; to spell out the knowledge that must be incorporated in an interface if such aid is to be given; to describe some of the solutions that have been implemented in experimental and operational interfaces; and to discuss some of the problems encountered. The paper closes with an extensive bibliography of references relevant to online search aids, going well beyond the items explicitly mentioned in the text. An index to software appears after the bibliography at the end of the paper.