Future of Speech Recognition

The speech recognition prospects are better displayed in sci-fi films like Star Trek, than in the existing reality. In fact, the developments in the field are said to have been slowed down.  So far no instant translator, or like sci-fi writers like to call it – lingvo-decoder – or something of the kind have been created to wipe out interpreters as a profession and bring lots of happiness to many people who are too lazy to learn a foreign language.
Today all the developments in the field are focusing on eliminating the shortcomings of the existing technology – which is a necessity to pronounce words clearly and loudly. It’s no good delivering some secret info such as your pin number to the ears of the surrounding people somewhere at the airport or at the railway station.  In the same way some military command when distinctly pronounced in action can give away the battle group prior to the necessary moment. Most children, elderly people  and people who suffer from speech disorders find it difficult to pronounce the words clearly for the device to understand them. The new technology is going to address those problems.
The latest initiative, called silent speech interface (or SSI in short) is a device that allows speech communication without using the sound. So people do not have to vocalize what they want to say. It’s enough just to murmur the words or mimic their articulation. The system process what has been said using ultrasound and optical camera input of tongue and lip movements. So far the whole technology is quite clumsy and bulky but the refinements are under way. The next step will be to monitor the brain activity in the motor cortex obtained from intracortical microelectrodes thus providing the first step to telepathy and managing objects by the power of one’s thoughts.
The mentioned technologies have already left think tank labs having been implemented in real devices and gadgets. In 2002, the Japanese company NTT DoCoMo  created a silent mobile phone which used electromyography and imaging of lip movements.  The main application of the device was public environments with a high level of the background noise. The company’s novice also helped people with limited abilities who have permanently lost their voice. So, the progress is under way though it is much slower than we could have expected.