Assessing the Viability of a Vocal Cord Vibration Switch for Four Children with Multiple Disabilities~!2009-10-06~!2010-02-19~!2010-04-02~!

Abstract

This prospective case series evaluated the viability of a recently-developed vocal cord vibration switch with four participants between the ages of 5.8-14.5 years old who had severe motor disabilities and complex communication needs. At the time of study enrolment, participants did not have an established single switch access pathway but were all capable of some form of vocalization, albeit frequently unintelligible. Participants were each provided with a vocal cord vibration switch for unrestricted home use. Participants were subsequently followed for a one-month period and switch viability was evaluated on three separate occasions. Viability of the switch was assessed in terms of quantitative measures such as switch sensitivity, specificity, and user-perceived exertion, along with qualitative characterizations such as ease of use and user satisfaction reported by the participants, their caregivers, and their clinicians. Data from the three consecutive assessments indicated low levels of exertion, device sensitivity between 73.3% and 93.2%, and specificity between 98.1% and 100%. All four participants reported that they liked the device and expressed desire to continue using it. In addition, clinicians and caregivers unanimously agreed that the device was the most viable access solution for their clients.

Age-Based Automatic Voice Conversion Using Blood Relation for Voice Impaired

“…Off late, algorithms have been developed to facilitate straightforward communication through synthesized speech for those with total or partial loss of speech. They include electrolarynx [6], sign to speech converter [7], text to speech synthesis [8], silent sound technology [9], vocal cord vibration switches [10], articulatory speech synthesizers [11], brain implants [12], breath to speech [13], and, tongue articulatory systems [14]. They are based on inputs captured through hand gestures, text data, lip movements, vocalizations, visual features, brain signals, exhales, and tongue movements respectively.…”

“…They are based on inputs captured through hand gestures, text data, lip movements, vocalizations, visual features, brain signals, exhales, and tongue movements respectively. Such models can be useful to interpret speech for tracheostomized patients who have undergone larynx surgery, those who are speechdisabled due to accidents or voice disorders, medical rehabilitation, and robotics [6][7][8][9][10][11][12][13][14]. However, such techniques are used to synthesize the speech, whose voice is chosen either of google voice or robotic voice or a universal or generated voice database, where the speaker does not sound natural.…”

A Simple Speech Production System Based on Formant Estimation of a Tongue Articulatory System Using Human Tongue Orientation

“…An articulatory speech synthesizer as a generic acoustic model [8], was used to determine the acoustic performance of articulatory mapping by describing the articulatory trajectories of the jaw, lips, tongue body, and tongue tip. Vocal cord vibration switches [9] were positioned on the throat and capture sensor signals, which are sent to an iPod through a Bluetooth transmitter to detect the periodic vibrations associated with vocalizations. Also, in silent sound technology, an electromagnetic sensor is attached to the face and records pulses, which were converted to speech [10].…”