“Finding a communication solution for people living with cerebral palsy and dysarthria has long been a central focus.”
More than 50% of people with cerebral palsy have difficulty speaking and being understood verbally — a condition known as dysarthria. While assistive technology exists, these solutions often take 15 to 20 times longer to convey a message compared to normal speech.
Cerebral Palsy Alliance enlisted Kablamo to help explore how to give children with CP the same rights, access and opportunities as anyone else.
The Challenge
The lack of quality data on the voices of children with CP is a major barrier in the development of assistive technology solutions. Engineers and researchers need large datasets of dysarthric speech to train and test new technology, but collecting this data is difficult and time-consuming.
CPA needed a platform that could make data collection accessible, engaging, and scalable — while respecting the needs and limitations of children with CP.
Traditional voice data collection methods fail children with CP because they require sustained attention and repetitive tasks. A new approach was needed that made data collection feel like play, not work.
The Platform
My Voice Library brings together gamification, accessibility, and research in a unified platform
Kablamo designed My Voice Library — a world-first platform for collecting voice and orofacial data. By gamifying the collection process, the platform makes it easier and quicker to assemble a significant, open-source library that biomedical engineers, speech pathologists and researchers can use to develop the next generation of assistive technology.
Design Approach
The solution was celebrated for its user-friendly and engaging experience — accessible and enjoyable for children, enabling them to explore themed worlds, level up, and actively participate in expanding the voice library.
- •Clinical, sterile environments
- •Repetitive, boring tasks
- •High dropout rates
- •Limited dataset growth
- •Inaccessible to many children
- ◆Fun, themed game worlds
- ◆Engaging characters and stories
- ◆Progressive rewards system
- ◆Scalable, growing dataset
- ◆Designed for all abilities
How It Works
Technical Architecture
The platform required a cost-effective, scalable architecture that could handle unpredictable usage patterns while maintaining strict data security for sensitive voice recordings from children.
Kablamo implemented a fully serverless approach using S3 and CloudFront for the static frontend, with a lightweight Lambda and API Gateway backend connected to DynamoDB. Voice data uploads flow directly to S3 with restrictive bucket policies ensuring that once uploaded, recordings cannot be re-downloaded by the application.
This serverless architecture keeps ongoing hosting costs extremely low while scaling automatically. CloudTrail logging ensures complete auditability of all data access — critical for research involving minors.
A World First
“My Voice Library is unique — it's the first time we've been able to collect voice samples of children who have a dysarthric speech condition. The gamified modules make it easier for children to go through the tasks.”
Personal Impact
“My cerebral palsy is who I am and I am very proud of it. But my biggest disability is my speech, and not being able to have instant communication without planning the best way to get my message across.”
Results
Recognition
My Voice Library was recognized at the 2023 Good Design Awards, receiving accolades for its innovative approach to accessible technology and human-centered design.
Looking Forward
My Voice Library represents a new approach to assistive technology development — one that puts the people who will benefit from the technology at the centre of the research process. As the library grows, it will enable engineers and researchers to develop and test new communication solutions that could transform the lives of people with dysarthria.
The platform demonstrates how thoughtful design, combined with modern cloud architecture, can create meaningful impact for underserved communities while building valuable research infrastructure for the future.
