CereProc releases the first synthesiser to use statistical parametric singing synthesis

Edinburgh, Scotland February 2019 – Text-to-Speech experts CereProc announced that they have created the first singing synthesiser of its kind that employs statistical parametric singing synthesis. This technology was premiered on ‘The Tonight Show’ with ‘Sophia’ the robot and Jimmy Falcon singing the first ever robot-human duet. To celebrate Burns night,
CereProc’s speech synthesis experts created a hilarious video containing a singing duet featuring Donald Trump and CereProc’s Dodo voice using their singing synthesiser and latest WaveNet Style technology. Please follow the link for the full version: https://www.youtube.com/watch?v=8mwuhO1iomY&feature=youtu.be

CereProc’s singing synthesiser uses both HMM and Deep Neural Network (DNN) systems.
The systems in the past have used unit-selection style synthesis requiring a large singing database. CereProc have developed the first commercial system that only requires one or two hours of spoken data. CereProc has pushed its technology to the next level by not only giving any individual the ability to sing, but this technology has the potential to change the music industry.

Matthew Aylett CSO, CereProc, stated: “There isn’t a ceiling on the potential quality of the voice in singing TTS. This sort of technology could be used both as in instrument itself, a training aid for musicians, accompaniment for live performance, and as a replacement for a human vocalist altogether”

CereProc are in the process of commercialising the singing system with selected key partners and expect to release the full system for sale later in 2019.

Paul Welham CEO, CereProc, concluded: “As an independent British company, CereProc continues to develop exciting innovation in all areas of speech technology, this astounding development, continues our track record of offering technology that disrupts the status-quo in speech technology. CereProc world's first personal voice cloning system in 2014 CereVoiceMe, which the latest 2019 release incorporates both AI and DNN technologies. CereProc's management have a 100% commit to continuous innovation, our singing TTS proves this”

Ends…

• CereProc is the only text-to-speech company in the UK. We’re based in Edinburgh, Scotland, the home of advanced speech synthesis research, with a sales office in London.
• The CereProc team consists of leading speech experts who have extensive experience across the entire speech technology domain.
• CereProc was founded a decade ago to push the boundaries of speech technology, expand it into new markets, and use it to help people.
• In 2018, we used experimental deep learning technology on the JFK Unsilenced project to create the speech that JFK was due to give on the day he was assassinated in 1963.
• Also in 2018, CereProc gave radio journalist Jamie Dupree his voice back after it was taken by a rare medical disorder.
• In 2010, we used experimental technology for the first time to build a voice from past recordings for the film critic Roger Ebert.
• CereProc developed the world’s first Gaelic voice.

Contact: Sophie Henderson
Email: sophie@cereproc.com
Tel: +44 (0)131 516 8532
Website: www.cereproc.com
Twitter: @cereproc

This release was published on openPR.