Listen
Listen

Linguist Refining TTS VoiceThe big day we’ve so eagerly been waiting for has arrived:  it’s CES® opening day! The rSpeak Technologies team is excited to take part in what promises to be the largest, most diverse event experience in the show’s 50-year history. We’re looking forward to interacting about the hottest tech trends – everything from IoT to wearables to the most amazing apps and devices imaginable.

Come and say hello – we’re in the Holland Startup Pavilion at Booth 51431 in Eureka Park, Sands Level 1, Hall G.

At rSpeak Technologies, we’re incredibly proud of the quality we deliver to our customers and we enjoy watching their businesses thrive. Thanks to the meticulous care we put into developing our lifelike rSpeak TTS voices, we’re confident that developers of cutting edge devices and applications are getting the best speech software to power their success. Our ongoing commitment to providing outstanding TTS voices is made possible by our uncompromising production process, designed to guarantee the quality levels that have earned rSpeak TTS recognition as the most accurate synthetic speech software on the market.

As we mentioned in our previous post, the first phase in creating amazing TTS voices is selecting the best voice talent and creating a corpus of voice recordings. Once this phase is complete, it is time to move on to the second, which lasts several weeks. It involves processing the voice recordings and creating a rich mark-up, in which each word, phoneme and stress is annotated along with several other aspects. The recordings and their annotations are then combined into a voice database used by the core rSpeak text-to-speech system.

During the annotation process, the technical team works its magic – using a powerful combination of Artificial Intelligence and machine learning technologies on big amounts of data. These state-of-the-art methodologies are augmented by means of expert linguistic capability.

Once this stage is complete and the new rSpeak TTS voice is born, it is scrutinized and rated in minute detail by mother-tongue experts in a thorough Quality Assurance process. Any errors and imperfections are corrected. A characteristic of rSpeak TTS is its ongoing growth process – the TTS software keeps learning, even after it has been launched, thanks to an optimal feedback and update system.

So, there you have it, a superior-quality, fully-fledged rSpeak text-to-speech voice, ready to make multimedia applications, embedded or mobile devices more engaging and relatable, anytime, anywhere.