SERVICES
INDUSTRY
TECHNOLOGIES USED
TEAM
LOCATION
PROJECT DURATION
The client provides online counseling and speech and language therapy for children and young people, with a mission to make therapeutic support more accessible and engaging through innovative technology.
Their platform hosts therapy sessions enriched with interactive activities, creative tools, and games. This gamified approach helps reduce anxiety, encourages participation, and supports a wide range of therapeutic methods.
To expand the platform’s capabilities, the client partnered with It-Jim to explore how AI could automate parts of speech therapy – starting with a system that detects and corrects children’s pronunciation mistakes using speech recognition.
The project set out to solve a key challenge in paediatric speech therapy: automatically identifying and tracking pronunciation mistakes without constant therapist involvement. The goal was to develop an AI system that detects mispronounced phonemes in real time, handles non-linear speech patterns, and delivers feedback as accurately as – or better than – a trained therapist. But children’s speech brings a unique set of challenges:
Children’s pronunciation changes as they grow, making phoneme boundaries inconsistent and difficult for traditional models to interpret.
Regional and individual pronunciation differences required the model to handle a wide range of phonetic variations.
Sessions often take place outside ideal recording conditions, with background noise, interruptions, or low-quality microphones.
Few existing datasets capture the variety of children’s voices and speech errors needed to train accurate recognition models.
We brought the vision to life through a multi-stage approach, from research and model selection to dataset creation and deployment. Each step addressed specific technical and data challenges while aligning with therapy needs. Using advanced speech recognition, phoneme-level training, and a custom child speech dataset, we built an AI system that delivers reliable, actionable feedback even in noisy, real-world environments.
The client’s vision was clear: automate pronunciation correction for children. But traditional speech recognition models weren’t designed for the nuances of kids’ speech, especially with accents, articulation variability, and noise.
This gave the project a clear path forward and the confidence that the goal was technically achievable.
Wav2Vec 2.0 had strong potential, but it needed careful fine-tuning. Children’s speech is less structured and more variable than adult audio, which makes direct transcription difficult.
The result was a fine-tuned model capable of understanding real-world, imperfect children speech.
Data availability was a critical roadblock. Existing datasets lacked both the quantity and diversity needed for children’s phoneme-level speech.
The dataset became the foundation that enabled real-world accuracy rather than just lab success.
With the model trained and validated, we moved into deployment, focusing on usability, monitoring, and production-readiness.
This collaboration demonstrated how AI and computer vision can bring lab-level insights into users’ pockets, redefining how personal health can be tracked and understood.
Whether you’re working on health tech, education, or human development – we’re here to bring AI into the real world with you. No buzzwords. No overpromising. Just a thoughtful conversation with our technical team to explore your idea.
Automated transformation of photos into 3D memorial keepsakes using a hybrid of classical computer vision and 3D generative AI.
Hormone tracking application powered by Computer Vision with 93%+ accuracy in real-life conditions.