I remember an old Star Trek movie where severely debilitated people without functional vocal chords could readily speak to each other by merely thinking their sentences. Recent research is bringing us closer to having such a capability. The article A Wireless Brain-Machine Interface for Real-Time Speech Synthesis in the current issue of Plos One lays out the progress.
“Brain-machine interfaces (BMIs) involving electrodes implanted into the human cerebral cortex have recently been developed in an attempt to restore function to profoundly paralyzed individuals. — In the current study we use a novel approach to speech restoration in which we decode continuous auditory parameters for a real-time speech synthesizer from neuronal activity in motor cortex during attempted speech. — Neural signals recorded by a Neurotrophic Electrode implanted in a speech-related region of the left precentral gyrus of a human volunteer suffering from locked-in syndrome, characterized by near-total paralysis with spared cognition, were transmitted wirelessly across the scalp and used to drive a speech synthesizer. A Kalman filter-based decoder translated the neural signals generated during attempted speech into continuous parameters for controlling a synthesizer that provided immediate (within 50 ms) auditory feedback of the decoded sound. Accuracy of the volunteer’s vowel productions with the synthesizer improved quickly with practice, with a 25% improvement in average hit rate (from 45% to 70%) and 46% decrease in average endpoint error from the first to the last block of a three-vowel task.”
I take this to mean that machine-training is necessary and that generating normal fluent speech is not yet possible. My impression is that a lot more needs to be done to understand and encode the relationships between neural events and continuous speech. This may take some time. Computer speech recognition research started in the 1950s and decent recognition of continuous speech was not achieved until around 2000. The authors conclude “Our results support the feasibility of neural prostheses that may have the potential to provide near-conversational synthetic speech output for individuals with severely impaired speech motor control. They also provide an initial glimpse into the functional properties of neurons in speech motor cortical areas.”
I speculate that if and as this technology is perfected it would have a number of additional applications for normal non-debilitated people including:
· Telephone calls without talking aloud for privacy or in noisy places or so as not to disturb others,
· Rapid writing or recording of thoughts for people who can think faster than they can talk,
· Private voice conversations not obvious to those you are with, even sneakier than text messaging can be, and
· Controlling machinery or even driving a car with just internally vocalized thoughts.
In the future the situation could get even more extreme when electronics also can short-circuit the human hearing apparatus and thoughts can fly electronically from one brain into another. I don’t want to go there for now. If I live as long as I want to, however, there will surely come a point when I will have to decide whether or not to have a brain implant for voiceless speech synthesis.