These newer computerized voices aim to retain the mechanical essence and surprising expressiveness of Hawking’s synthesized speech, while updating particulars like using British accents or training on Hawking speech data. Another is FineVoice, an AI voice studio for generating synthetic voices, including one based on Hawking. A recreation called the Stephen Hawking Voice Generator uses the JavaScript eSpeak library to mimic his voice. There are also open source and online projects. This offers those with disabilities the chance to communicate using a variant of his legendary voice. For example, CereProc has developed related voices with British accents.Īnother is ALS TTS, part of the ACCLAIM project, which used AI neural networks to create a voice trained on Hawking speech recordings. Hawking’s voice inspired the creation of several modern AI voice models that seek to emulate the scientist’s unique tones. This computer setup gave Hawking a unique mobility and ability to “speak” lectures on physics all over the world. The voice synthesizer was mounted on one arm of his wheelchair, with the text entry system on another arm. The voice had an American accent as this was the easiest available vocal formant to replicate at the time.Īs text input took effort for Hawking, he became renowned for his ability to convey complex concepts and humor with only a few entered words generated through the CallText. The technology was advanced for the era, but led to the synthesized sound of Hawking’s voice. Formant synthesis works by simulating the different resonances that occur in the human vocal system. This was made possible by DECtalk speech synthesis technology, based on the KLATT formant synthesizer from MIT. The CallText contained a processor that translated the entered text into speech. The speech synthesizer worked by having Hawking laboriously enter text character-by-character using a hand clicker. Hawking ended up using the Speech Plus CallText 5010 for over 3 decades until his death in 2018. Physicists have noted that keeping the original voice was helpful – it meant focus remained on his ideas and discoveries, not the assistive technology needed due to his disabilities. This consistent voice also meant that most people immediately recognized Hawking when he gave lectures or interviews. His synthetic tone had essentially become ‘him’. His daughter once said that she could always recognize her father’s voice on TV, even after not seeing him for a while. Once he said of change: “I keep it because I have not heard a voice I like better and because I have identified with it.” When offered upgrades, Hawking resisted, having become attached to the voice and not wishing to change this notable part of his persona. But by this time, Hawking’s unique voice had become legendary. ![]() ![]() Pika Labs AI Review: Features, Price, Use, Download & More Hawking’s Resistance to Upgradesīy the 1990s and 2000s, assistive speech technology had advanced considerably, offering more humanlike voices. At the time, this was cutting-edge technology mostly used in automated telephone systems. The CallText contained a processor that turned text into speech. This became the synthesizer that Hawking used for the rest of his life. In 1988, Hawking first used the Speech Plus CallText 5010 – a model given to him when he visited the company that made it. ![]() The original hardware was large and cumbersome by today’s standards. The system operated through a computer system mounted to Hawking’s wheelchair. The first voice used for Hawking was developed in the early 1980s by MIT engineer Dennis Klatt, one of the pioneers of text-to-speech algorithms. ![]() By 1985, his condition meant he could no longer speak, and required a computerized system to communicate. Hawking’s distinctive voice was necessitated due to his long battle with amyotrophic lateral sclerosis (ALS), the motor neuron disease that left him almost completely paralyzed.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |