Countless voice and language applications are flourishing

There’s no escaping devices, applications or services that use voice and language technology as a user interface. From banks to cars, to mobile personal assistants, voice technologies have brought both convenience and productivity to daily life. It’s hard to think of a place where we can’t simply use our voice to get the most out of technology today.

Twenty years before though, when Dragon NaturallySpeaking made its debut, things were very different. In 1997, we introduced an innovative computer software solution for converting speech to text, and it left an indelible mark on the technology industry – setting forth the next generation of voice-enabled applications, devices, cars, healthcare systems – that we see today.

Light years ahead of speech technologies previously available, Dragon was the first-ever continuous dictation product – capable of understanding about 100 words per minute. It was the first time there had been a software technology that allowed people to speak somewhat naturally and have their words appear right before them on a computer screen.

Twenty years later, Dragon continues to transform the way people work and live, and has proved to be an incredibly empowering technology for creating documents and commanding and controlling the computer itself. And the promise of Dragon remains the same as it did decades before. It has moved from the PC to the Mac, and now to the Cloud – and has evolved to deliver incredible time and money-saving value to individual professionals and business enterprises from legal, financial services and more. It makes the computer more comfortable and easier to use for individuals with accessibility issues, while serving as a powerful learning solution for students and educators alike. It also drives mobile productivity for individuals who work in the field or who are constantly on-the-go.

Today, Dragon’s core speech recognition innovation is at the heart of so many solutions here at Nuance – automotive, healthcare, enterprise customer care and a wide range of speech recognition capabilities for the rapidly emerging Internet of Things. The technology set forth an evolution where even twenty years ago it was thought to be the start of where you could use your voice to finally set your VCR correctly or tell your microwave to not burn your popcorn. For those of you born around the same time as Dragon – yes, we had microwaves, and no, we’re not misspelling DVR – which now thanks to our Smart Home and TV solutions inspired by Dragon you can actually talk to, and find virtually any movie from any genre.

Dragon also quickly evolved into a consumer software must-have for just about anyone who wanted to get more done faster. Over time, Dragon has become faster and incredibly accurate, supporting multiple languages and with accuracy in the high 90th percentile.

Driving a revolution

For many, speech recognition is a transformative solution. Take individuals with accessibility issues, from carpal tunnel and Repetitive Strain Injuries (RSI) to learning disabilities. They face unique challenges when it comes to using a computer. The keyboard and mouse can be a barrier, not to mention a cause of pain and frustration. By taking away the mechanical aspects of typing, they have a less physically and cognitively taxing way to interact with the computer, making it easier and more comfortable to use. They can work hands-free and talk to create documents, send email and search and browse the internet, and control their computer by voice. It can also prevent RSI by minimising the use of keyboard and mouse. It’s fair to say then that Dragon has become an invaluable tool for people with accessibility issues that can make typing difficult or painful. Now they can create documents, access data, or navigate a computer desktop simply and easily, just by speaking.

Who is using Dragon today?

Today, Dragon is being used by a wide range of individuals and industries – essentially anyone who needs to create detailed, accurate, documentation. This can range from corporations, government agencies and other organisations that face significant documentation requirements as part of conducting business.

The productivity gains for these users is great. Inefficient or cumbersome documentation workflows often result in missed deadlines, inaccurate documents or too much time and money focused on administrative work. This is a problem for organisation of all sizes, but it’s compounded for SMEs which often have limited staff and other resources. In their case, boosting productivity and managing documentation are top priorities, which is where Dragon excels. Because Dragon lets the user create reports, presentations and spreadsheets, send emails, schedule meetings or control business applications by voice, the efficiency gains achieved is why many businesses use this productivity tool.

The secrets to Dragon’s accuracy

Anyone trying speech recognition for the first time will be impressed at how accurate it is; in fact, Dragon achieves 99 per cent recognition accuracy right from the first use. Speech recognition uses the human voice as the main interface between the user and computer. While relatively simple to use, speech recognition software is highly sophisticated technology that leverages “language modelling” to recognise and differentiate among the millions of human utterances that make up any language. Using statistical models, speech recognition programs analyse an incoming stream of sound and interpret those sounds as commands and dictation.

Raising the bar in speech recognition

Dragon speech recognition accuracy, speed and personalisation have long set the standard for voice productivity on the Mac, PC and mobile devices. And with a next generation speech engine powered by Nuance Deep Learning technology, Dragon delivers increased accuracy for even more users, with an enhanced ability to learn and adapt to a variety of accents and environments, making it ideal for diverse work groups or settings. Deep Learning is a powerful pattern recognition technique inspired by the way the human brain learns and interprets sensory input, which Nuance has leveraged to advance accuracy across our speech recognition technologies, including Dragon.  

So, what do the next twenty years have in store? Nuance’s voice and language technologies will undoubtedly be at the heart of the world’s next generation applications and solutions and continue to define how we interact with the world around us – by voice.

Mark Geremia, Vice President and General Manager, Dragon Professional and Consumer
Image source: Shutterstock/polkadot_photo