Patent rights for Emotional Speech Synthesis give prime position to CereProc in providing best of breed custom built voices which are natural and full of character.
Industry leading text-to-speech (TTS) technology company, CereProc, has been granted a UK patent protecting its exclusive rights to the Emotional Speech Synthesis system, designed to produce full speech synthesis with emotion, for use in multiple sectors.
Chris Pidcock, Chief Voice Engineer at CereProc explained: “One of our core aims is to create voices that are authentic and full of expression – and emotion is a part of this. We believe that higher quality, more realistic voices will increase the uptake of text-to-speech technology, and open up new markets to us.”
Committed to the research and development of new technologies, CereProc’s latest patent asserts the company’s unique position at the forefront of the global TTS technology industry. Outstripping TTS technology solutions currently available on the market, those which produce robotic and unnatural voices, CereProc’s Emotional Speech Synthesis goes beyond the practices – such as the insertion of laughter or yawns – which are commonplace in the quest to produce more realistic voices.
Achieving greater emotional variation in the actual speech than any competitors on the market, CereProc’s method results in the efficient and cost-effective delivery of custom built voices by simulating multiple emotional states. Producing an increased emotional range, in addition to the widely used insertion of pre-recorded sounds, the patented technology centres on the analysis and manipulation of a constrained set of data.
Enhancing user experience and moving away from the unnatural voices which are limited in use, CereProc’s pioneering TTS technology is effective for use in consumer engagement and marketing initiatives, building a stronger corporate persona through the distribution of brand-matched custom built voices. The Entertainment and Computer Games industries, particularly those projects which involve animation, are also set to benefit from CereProc’s Emotional Speech Synthesis, while the pioneering technology is increasingly valuable to the Healthcare and Education sectors.
“In addition to our other ongoing projects, we are currently working with Augmentative and Alternative Communication (AAC) providers to add emotional TTS to the voice output of their devices. The prospect that these joint ventures could result in enabling people with serious neurological conditions such as Motor Neurone Disease or Cerebral Palsy, to speak with emotion, and in some cases for the first time ever, is really exciting. That is something which the team is truly proud of,” continued Pidcock.
Further information detailing the Emotional Speech Synthesis techniques can be found at: