The 2016 Speech Industry Star Performers: Acapela Group
Acapela Group’s Assistive Technology Personalizes Voices for Children and Adults
More than 1,000 companies in very different markets across the globe have already adopted Acapela Group’s text-to-speech voices, but the company’s assistive technology also helps thousands of disabled children around the world who are now speaking as a result of its unique technology.
Acapela, based in Belgium, broke the mold on augmentative and alternative communication (AAC) solutions when it started to offer children with communication difficulties a voice of their own. Traditional AAC systems had relied on adult voices.
“These new voices will make such a difference to [children] and to their families, in particular in terms of enabling them to be included, to have normal relationships with their peers and enjoy everything that so many other children take for granted,” said Anna Reeves, England’s national AAC coordinator, in a statement.
The challenge was to find, coach, and record kids. Creating the first two voices took more than 2,500 hours of research, recording, processing, and development.
Since then, Acapela has been back to the lab many times perfecting the app and adding new languages.
This year alone, the company expanded its offering to include Norwegian, French, and Swedish, adding to those already available in U.S., U.K., and Australian English; German; and bilingual American English/Spanish. Partnerships with assistive technology providers Crick Software and Speak for Yourself expanded the scope of its children’s voice offerings even further.
But disabled children aren’t the only ones benefiting from Acapela’s innovation in speech technologies. With the My-Own-Voice service, people with amyotrophic lateral sclerosis (ALS) and other disorders that slowly deprive them of their ability to speak can capture and preserve their own voices in text-to-speech (TTS) format before losing them. This groundbreaking invention will enable users to keep speaking with their own voices rather than the standard anonymous synthetic voices. This year, the company added Italian, bringing the number of supported languages to 11. It has already run more than 80 voice recordings with users about to lose their voices.
Acapela has also brought its custom voice technology to the transportation sector with a February contract to provide Jernbaneverket, the Norwegian government agency for railway services, with a custom TTS program based on one employee’s voice. The custom voice will guide rail passengers in Norway while an English voice from the Acapela catalog will be available for international travelers.
The company’s work with government agencies didn’t end there. Acapela also in February signed a contract with the Swiss Federal Department of Foreign Affairs (FDFA) to deploy an interactive voice response (IVR) system vocalized by Acapela voices at more than 170 locations worldwide. Using Acapela’s on-demand cloud solution, every FDFA team can generate its own custom voice messages and make changes instantaneously, in any of Acapela’s available 34 TTS languages.
The company, which was formed in 2003 following the merger of three European TTS providers—Infovox, Babel Technologies, and Elan Speech, is also involved in research projects such as Emospeech, which enhances the expressiveness of voices in gaming contexts.
Acapela gained another foothold in the gaming area in September 2015 when it signed a contract with Serious Factory to integrate its speech synthesis into Serious Factory’s Virtual Training Suite, an immersive training simulator that extends the learning process through a new technology called serious gaming.
Virtual Training Suite is using Acapela’s cloud solution, which enables the online, real-time generation of voice files. With both a 3-D real-time graphic environment and contextual vocal information, the learner evolves in a virtual environment very similar to his own professional daily routine. Personalization, immediate audio feedback via speech synthesis, and a conversational engine that makes the avatars smarter are also part of the solution.
And Acapela’s technology is only going to get better as it integrates technology gained during its 2015 acquisition of CreaWave, a French start-up specializing in voice interfaces. CreaWave owns Flexiwave, a concept-to-speech technology that will complement and significantly expand the voice solutions Acapela can offer.
Flexiwave’s concept-to-speech technology delivers human voices for domain-specific dialogue applications. While TTS is based on text input, concept-to-speech uses recurring domain-specific parameters to generate audio messages. This technology complements Acapela’s range of voice solutions and offers new capabilities that push the boundaries of speech technology for an unprecedented, personalized user experience.