Speech Output Devices Research Articles

Believe in Me: Insights of a Nonspeaking College-Bound Autistic

Believe in Me: Insights of a Nonspeaking College-Bound Autistic

GeoTalk: a GPS-Enabled Portable Speech Output Device for People with Intellectual Disability

A high percentage of people with intellectual disability experience communication impairments that limit their use of spoken language and make the use of alternative and augmentative communication (AAC) devices potentially beneficial. However, AAC devices often present barriers for people with intellectual disability due to the complexity of switching between levels and overlays and by hardware configurations that limit the number of words or phrases that can be programmed into a device. This study reports on an evaluation of GeoTalk, a handheld device application that incorporates universal design in the user interface and integrates global positioning system (GPS), electronic schedule timers, and other sensor technology to automatically switch between vocabulary sets when the user enters a designated geographic zone, such as a school, bank, and grocery store. The system also triggers automated switches in vocabulary sets based upon time of day or remote sensors in situations that require a unique vocabulary set. Findings from the pilot test showed that people with intellectual disability were able to operate the GPS-enabled GeoTalk device with fewer errors, requiring fewer prompts, and with greater speed than two commercially available comparison AAC devices.

An Improved Spectral Subtraction Algorithm Study Based on Voice Human-Computer Interaction in Cockpit

The voice interaction in cockpit mainly includes speech recognition, enhancement and synthesis. This interaction transfers the speech information to the corresponding orders to make machines in cockpit work unmistaken, also feedback the execution results to users by speech output devices or some other ways. The speech enhancement technology is studied in this paper, aiming at the Voice Interactive. We propose an improved spectral subtraction (SS) algorithm based on auditory masking effect, by using two steps SS. The simulated results based on the segment SNR compared to the traditional SS show the effectiveness and superiority of the improved algorithm.

An overview of technological resources used in rehabilitation research with people with severe/profound and multiple disabilities

Purpose: This paper provides an outline of technological resources used in rehabilitation research with persons with severe/profound and multiple disabilities, and discusses the practicality of such resources. Method: Research articles published during the last 8 years (1993-2000) are considered. With regard to each of the technological resources used in the articles (i.e. microswitches, speech output devices, computer-aided instruction systems, audio recording systems, orientation systems, mobile robot, and SIBIS), accessibility, cost and implementation issues are examined. Results and Conclusions: Some technological resources are easily accessible and affordable (i.e. microswitches, speech output devices, audio-recording systems and SIBIS). Other resources are still at the prototype level (i.e. computer-aided instruction systems, orientation systems and robot) and are much more complex and costly. In spite of this, the latter resources might still have an important role in daily contexts.

An evaluation of the diagnostic rhyme test

The intelligibility of a speech output device is an important predictor of user acceptability. The Diagnostic Rhyme Test (DRT) is an ANSI standard for measuring speech intelligibility (ANSI S3.2-1989). In the DRT, respondents hear a word and choose its equivalent from two visually presented words. The two words differ only in their initial (e.g., veal-feel), and the two consonants differ only in a single distinctive acousticphonetic feature (e.g., voicing). To define “distinctive feature”, the DRT uses a minimal distinctive feature system, loosely based on the work of Jakobson et al. (1963) and Miller and Nicely (1955). These studies carefully analyzed natural speech errors in various noise environments. Whether or not these studies can be freely applied to alternative forced-choice tests of coded or synthesized speech is an empirical issue. In the present study, the results of a Consonant Identification (CI) task were compared to a previously conducted DRT using the same coding algorithms. The CI data indicated that the low-bit-rate coded speech yielded significantly more multifeature confusions then the uncoded speech. Moreover, the multifeature confusions could not be easily predicted from the single-feature confusions. A fundamental assumption of the DRT is that speech errors are adequately diagnosed by testing single-feature confusions. The results of the present study contradict that assumption. In conclusion, we argue that the application of the DRT (and more generally, any closed-response choice procedure) to coded or synthesized speech is questionable.

Outcome of recommendations for augmentative communication in children.

Some children with severe motor disorders have unintelligible speech, and may be recommended augmentative communication systems, such as a symbol chart or a voice output aid. The paper reports the outcome after 15-18 months for 35 children of recommendations for augmentative communication. Using structured questionnaires, parents were asked whether equipment was provided as recommended. Their perception of success in children's use of augmentative aids was recorded and related to potentially influential factors. Twenty-five symbol systems, 10 speech output devices and 11 switches were received; 18 symbol systems were used for communication and 10 were used frequently. Seven speech output devices were used for communication but only two were reported to be used frequently. Factors leading to more successful outcomes include early receipt of the aid, perceived adequate local training in the use of the aid, and children aged 6 years or more at initial assessment. The findings also suggest that referring professionals will need to be better informed about the nature and limitations of augmentative communication aids, and that improved local professional input and careful interagency planning and co-ordination are required to achieve optimal outcome.

Symbol vocabulary and the focus of conversations: augmenting language development for youth with mental retardation.

Communication devices designed to augment the language development of individuals with severe cognitive disabilities and little or no functional speech typically contain primarily nouns because they seem easiest to acquire and evaluate. In this study, the effect of a more diverse vocabulary was assessed. Systematic observations of the use of computerized speech-output devices by 12 youth with moderate or severe mental retardation and severe spoken language disability and by their partners were made over a 2-year period. Social-regulative symbols (e.g., "please," "I'm finished") were used as soon as they were introduced, and their availability expanded the focus of conversations both at home and at school. Implications for conceptualizing variation in early language use and for the design of language intervention programs are discussed.

Synthesized or digitized? A guide to the use of computer speech

In addition to technical and cost determinants, a range of human factors issues governs the appropriateness of synthesized or digitized speech for a particular system. For example, since synthesized messages are created textually, they may reflect the rules and habits of written language, rather than spoken language. This may cause listeners some difficulty interpreting the intended meaning of the message. Moreover, the different speech media place constraints upon techniques of message creation editing, transmission and reception. Synthesized speech is easy to edit in terms of lexical content, but the production of sophisticated prosodic features can be problematic. In contrast, unedited digitized speech will normally have appropriate prosodic cues and because of this will be difficult to edit. The influence of these factors is examined and illustrations of both good and poor practice are given. The paper concludes with a decision criteria checklist for speech output devices.

A Human Factors Guide to Computer Speech

Recently, computer speech technology has advanced to the point where practical, commercially available speech output devices can be utilized for a variety of applications which take advantage of the unique attributes of language as a communication mode. Such devices, although not approaching the sophistication and flexibility of their human counterparts, allow production and manipulation of intelligible synthesized speech and the storage and display of high-quality digitized utterances. As the technology becomes more widely known and the costs decrease, much wider usage can be anticipated.

Voice-input aids for the physically disabled

Speech technology, an amalgam of speech sciences and microelectronics technology, offers new potential to aid the disabled. Low-cost very-large-scale integration (VLSI) speech synthesizers have been on the market for some time and, consequently, the use of synthetic speech output devices in aids has received a great deal of attention. Only recently, however, have VLSI chip-sets for speech recognition started to appear. This article reviews the possibilities for exploiting low-cost speech recognizers in aids for the severely physically disabled. Five areas of application are highlighted: wheelchair control, control of the domestic environment, text composition and editing, and control of manipulators are four of these. The ubiquitous nature of microprocessors and microcomputers, however, makes it difficult nowadays to distinguish sensibly between a general-purpose computer and a computer-based aid. A further important application, therefore, is likely to be provision of a voice interface between a disabled user and a “personal” (or remote) computer, irrespective of the function or functions implemented on that machine. As a consequence, some or all of the above applications could be combined within the same device. It seems sensible, however, at this stage to concentrate on a single application. It is argued that control of the domestic environment by voice is likely to be the most fruitful area for the initial application of automatic speech recognition technology to aid the disabled. The development of a speech interface to an environmental control (ECU) is described, and the principles on which the system design (hardware, software and man-machine dialogue) is based are explained and justified. Evaluation of the system has demonstrated the feasibility of employing speech recognition in environmental control. This is a continuing development, and many possibilities for future improvement are apparent.

Flexible, high‐performance speech synthesizer using custom NMOS circuitry

A programmable digital signal processor (PDSP) intended primarily for speech synthesis applications has been developed using custom NMOS LSI circuitry. Key features include high speech quality, great flexibility, simple interfacing to standard microcomputers, low cost, low power, small size, and the stability of a digital processor. Because of extensive programmability, substantial computational power, and a selection of hardware configurations, the PDSP components can implement a wide range of vocal tract model structures at costs roughly proportional to performance. For example, the user can create a cascade formant synthesizer, a parallel formant synthesizer, a hybrid cascade/parallel formant synthesizer, or a lattice filter structure. Typical applications encompass fixed‐vocabulary speech output devices, systems for translating unrestricted text into speech, and low‐bitrate/secure voice communications. The custom devices are currently being designed into a high‐performance speech output reading system for the blind.

Problems in realizing a digital vocoder and novel solutions

Some details are given of a channel vocoder intended for use as a speech output device for data-processing systems, but also suitable for voice transmission with 2400 bit/s, e.g., in narrow-band digital radio systems or in digital encryption systems. Characteristic features are, in the analyzer, the use of switched op-amp integrators instead of conventional low-pass filters plus rectifiers, and digital amplitude compression; in the synthesizer, pulse excitation which, in the case of unvoiced sounds, is achieved by means of a pseudorandom pulse derived from a digital shift-register circuit. This pseudorandom pulse exhibits very good stability and reproducibility.

Flexible analog time compression of short utterances

A technique for decreasing (or increasing) the duration of spoken words or short phrases is of practical interest in relation to vocabulary preparation for computer speech output devices. A natural-sounding compressed output is the result of: 1) proper manipulation of the analog signal; 2) providing the user with convenient operating controls and immediate aural feedback; and 3) providing flexible selective compression characteristics. The implementation of this technique involves an audio magnetic tape loop with adjustable multiple playback heads and associated recording, playback, and control circuitry. The major design aspects of this device, its application to vocabulary preparation for a computer audio response unit, and its usefulness for the study of speech perception will be presented.

EXPERIMENTAL INVESTIGATION OF SPEECH RATE AND MESSAGE VERIFICATION PROCEDURES

Abstract Speech output devices are currently in development stages in the computer industry. These devices will permit an operator to perform an enquiry to a computer and receive a spoken response message. This study investigated speech rates and verification procedures with a simulated speech output device. Operators were required to write an alphanumeric response message during message transmission. Three speech rates were investigated : 45, 60 and 75 characters per minute (e.p.m.). The results showed the 60 c.p.m. to be the most favourable in terms of operator accuracy and preference. Three procedures of verifying response messages were investigated : Required Verification, Optional Verification, and No Verification. The results showed the Optional Verification method to be the most efficient.