My-own-voice, the CES Innovation Award-winning solution, was showcased in its latest version at the event, unveiling unequalled quality for the Assistive market and Acapela's aim to open to new usages in a near future.
CES, Las Vegas, January 5-8, 2023. ‘My-own-voice’ is an online service, based on the latest innovations made with DNN (Deep Neural Networks). It offers individuals diagnosed with speech or language disorders the possibility to create their own digital voice. The new version revealed at CES 2023 benefits from the state of the art technology and provides unequalled quality.
Bradley Heaven and Daniel O’Connor honored us with their presence on Friday 6th January 2023 and shared their experience and usage of my-own-voice on their Tobii Dynavox device.
HOW DOES IT WORK?
The user accesses the service online and records a set of 50 sentences. The recording process is web-based and has been adapted to make it accessible to everyone. My-own voice enables anyone to create his voice, simply using a computer, a standard headset and an internet connection. No specific skills are required.
The set of 50 recorded sentences is used as raw material and is processed through our Neural text to speech technology to generate the synthetic voice. The digital voice, created with the end user’s recordings, is then ready to be used to read any text with an assistive device.
Once the synthetic voice is created it can be tested for free in a type & talk box on the Acapela my-own-voice app and also in TD Talk from Tobii Dynavox, prior to purchasing it for use with SAPI on Windows, with Google’s TTS API for Android or in a partner application.
LIFE CHANGING DNN TECHNOLOGY
‘My-own-voice’ online service offers individuals diagnosed with speech or language disorders the possibility to preserve a person’s voice identity, even if their voice is damaged and low energy levels makes recording difficult. It is the first step towards preserving the voice and maintaining the ability to communicate with this essential part of their identity.
With the recording of only 50 sentences, the service generates a voice that keeps the essence of the original voice in terms of timbre, accent and intonation. The voice and way of speaking are instantly recognizable. The full process is short and simple and based on the latest innovations and model of Deep Neural Network methodology.
Already used by over 3 000 users worldwide, mostly by people suffering from degenerative diseases, Acapela Group is targeting 10 000 users by 2024.To address the users, Acapela Group relies on the collaboration with new associations and partners in various health fields (pediatrics, cancer, Parkinson’s disease…). Acapela Group is also looking for other application domains that may strongly benefit from voice banking.
VIRTUAL AND AUGMENTED REALITY
Thanks to the standard voices format and specific partnerships signed, my-own-voice is ready to be integrated in most of major Accessibility devices on the market … And tomorrow in the Virtual & AR. New emerging usages include virtual and augmented reality and 3D virtual worlds focusing on social connection where the user’s digital voice will step in to enrich the identity.
About Acapela Group: Acapela is the European leader of voice solutions. The company aims to create digital voices that sound different, based on Neural text to speech. Custom & personalized voices adapted to the needs and context of application, based on promising results of VoiceAI. Acapela Group is an independent subsidiary of Tobii Dynavox, the global leader in assistive technology for communication.