A Voice-Input Voice-Output Communication Aid for People With Severe Speech Impairment

Abstract

A new form of augmentative and alternative communication (AAC) device for people with severe speech impairment-the voice-input voice-output communication aid (VIVOCA)-is described. The VIVOCA recognizes the disordered speech of the user and builds messages, which are converted into synthetic speech. System development was carried out employing user-centered design and development methods, which identified and refined key requirements for the device. A novel methodology for building small vocabulary, speaker-dependent automatic speech recognizers with reduced amounts of training data, was applied. Experiments showed that this method is successful in generating good recognition performance (mean accuracy 96%) on highly disordered speech, even when recognition perplexity is increased. The selected message-building technique traded off various factors including speed of message construction and range of available message outputs. The VIVOCA was evaluated in a field trial by individuals with moderate to severe dysarthria and confirmed that they can make use of the device to produce intelligible speech output from disordered speech input. The trial highlighted some issues which limit the performance and usability of the device when applied in real usage situations, with mean recognition accuracy of 67% in these circumstances. These limitations will be addressed in future work.

Model adaptation and adaptive training for the recognition of dysarthric speech

“…The benefits of such a setup has proved effective for dysarthric people using speech as an interface for natural communication [9] or enabling them to control physical devices through speech commands [7].…”

Reducing Speech Noise for Patients with Dysarthria in Noisy Environments

“…That is, 2 where s(n; m) and α i (m) are the n-th sample of clean voiced speech and the i-th LP coefficient at the m-th frame, respectively. Then, by searching the local maxima of FOD, we determine whether one of them is greater than a pre-defined threshold, which is set to 0.5 in this paper.…”

“…In fact, the performance of modern ASR systems is quite satisfactory, and thus a considerable number of applications have been actively deployed in real-world environments. Furthermore, several attempts have been made in recent years to bring the convenience of ASR to disabled people who have severe constraints to their body movement, allowing only a narrow scope of physical activity [2]. In particular, some of these attempts have been focused on people with dysarthria who have paralysis of the articulator as well as most other parts of the body due to damage to their central nervous system.…”

A cross-lingual adaptation approach for rapid development of speech recognizers for learning disabled users

“…As discussed in [6], traditional automatic speech recognition techniques are unsuitable for impaired speech for several reasons: the amount of training material is limited, the training samples are highly variable, and they are very different from voices corresponding to non-disabled users.…”

“…For example, VIVOCA [6] is a voice-input voice-output augmentative communication aid for people with severe impairment. Joode et al present a detailed study on assistive technologies for people with cognitive deficits including different uses of speech technology [7], and Lancioni et al provide a review of speech generating devices for augmented communication [8].…”