Voice Generators and Voice Recognition Systems

Voice recognition and speech generation are other assistive technologies useful for people with disabilities who cannot type instructions designed for computers with keyboards or touch screens. Some specialized voice transcription software is used to transmit data or instructions to a computer, allowing people with different abilities to use their computer or mobile device effectively, just by talking to them.

Devices equipped with this speech recognition technology can also be used to create text documents.

Speech generating devices allow them to communicate aloud with an electronic device that can create speech from text, icons or images.

These technologies depend on the clarity of the pronunciation of words or speech, so they may not be useful for people who cannot pronounce speech correctly.

Recently, Chinese scientists developed a device that is a wearable “artificial throat” attached to the neck like a temporary tattoo and capable of transforming throat movements into sounds. Scientists used a laser to apply graphene to a thin sheet of polyvinyl alcohol film*. The flexible device is a sticker measuring 1.5 cm by 3 cm, or about twice the size of a thumbnail. The film is attached to the skin of the throat with plain water and connected with electrodes to a small bracelet on the arm, which contains a circuit board, microcomputer, power amplifier and decoder.