Every time we see references to real-world speech recognition applications - from near-real time broadcast closed captioning to voice transcription in legal organizations - the name Dragon is associated, with Nuance Communications delivering the underlying technology with its complete suite of solutions. The software’s foundation has a long history, starting in the early eighties, when Dr. James Baker, an expert in speech recognition technology and professor at Carnegie Mellon University created the company Dragon Systems.
Dragon software was released for DOS, Windows and (more recently) Mac and was even licensed to several big multinationals, including Philips and IBM. In 2000, Dragon Systems of Newton, Massachusetts, merged with Lernout & Hauspie Speech Products and was later acquired by Nuance Communications. In 2005, ScanSoft launched a de facto acquisition of Nuance Communications, and rebranded itself as Nuance. Dragon speech recognition software is available (with varying levels of accuracy) for US English, UK English, French, German, Italian, Spanish, Dutch and Japanese.
Now the company raised the bar in speech recognition applications, with updates that the company promises, increase accuracy up to 24%, introduce new important features and enhance recorded audio transcription. All the new Dragon releases also sync vocabulary customizations and auto-texts with Nuance Dragon Anywhere, an online service available separately, to extend the benefits of professional-grade speech recognition to mobile devices running iOS or Android.
Dragon speech recognition accuracy, speed and personalization have long set the standard for voice productivity on the Mac, PC and mobile devices. And with Deep Learning technology at the core of its speech engine, Dragon gradually increases accuracy, with an enhanced ability to learn individuals’ voice patterns and accents, and deftly adapt to acoustics in open office or mobile environments. This latest Dragon release marks the first time Deep Learning capabilities can run embedded on a personal computer leveraging a user’s own speech data to improve their own language and acoustic model.
“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,” says Vlad Sejnoha, chief technology officer, Nuance Communications. “Training such Deep Neural Net models typically requires large amounts of training data and a high-performance computing environment. However, our new Dragon portfolio includes our latest breakthrough that allows Dragon’s Deep Neural Nets to continuously learn from the user’s speech during use on a standard personal computer, and drive accuracy rates in some instances up to 24 percent higher.”
The new Dragon also brings with it advanced transcription, powerful customization, and an improved ability to work with portable touchscreen PCs, extending the benefits of speech recognition to more mobile use cases and environments. As a result, documents are completed with higher accuracy in a fraction of the time, giving professionals across a number of industries – such as legal, public safety, social services and education – the ability to focus more on mission-critical tasks.
Dragon Professional Individual will be available for download in English in the US, UK and Australia for $300 on September 1, 2016. Physical product shipments will be available by mid-September. Dragon Professional Individual is available for $150 for users upgrading from Dragon Professional Individual, version 14 and Dragon Professional, versions 12 and higher, and for $200 for users upgrading from Dragon Premium, versions 12 and higher.
Dragon Professional Individual for Mac will be available for download in English in the US, UK and Australia for $300 on September 1, 2016 with special upgrade pricing of $150 or registered users of Dragon Dictate for Mac, versions 4 and higher.
www.nuance.com
