Sefism is free for learners. We are here to help you grow, one step at a time.Join for free
Sefism.
Other

Bilingual AAC Communication Board for Non-Speaking Children

An offline-first picture communication app (AAC) for non-speaking children and adults, with Urdu and English boards, natural text-to-speech, and a simple editor for parents and therapists. An accessibility final year project built with speech therapists and families, and tested for motor and visual access needs.

Topics
Difficulty

Beginner

Achievable by one student in a semester with familiar tools.
Effort

1 semester · 2 students, or 2 semesters · 2 students with the study

Deliverables

7 to ship

3 optional extras

Suggested stack

Flutter or React NativeSQLite for offline storageDevice text-to-speech enginesOpen symbol sets (ARASAAC)Firebase or Supabase for optional syncFigma
A suggestion, not a requirement. Swap anything for what you already know.

What you should ship

  • A tablet and phone app that shows grids of symbol tiles which speak a word or phrase when tapped, and builds a sentence strip from several taps.
  • Core vocabulary boards in both Urdu and English, reviewed by at least one speech and language therapist, with a one-tap language switch.
  • Offline operation for every core feature, including speech, so the app works without internet or during power and network outages.
  • A caregiver mode, locked behind a simple gate, to add tiles with a photo from the camera, record a family member's voice, and reorder or hide tiles.
  • Access settings for grid size, tile spacing, touch hold time, accidental double-tap filtering and high-contrast themes.
  • Export and import of a full board set as one file so a therapist can share a set with several families.
  • A usability study report with at least three families or a therapy centre, including observed sessions and caregiver interviews.

If you have time left

  • Switch scanning for users who cannot tap reliably, using an external switch or a large on-screen button.
  • Word prediction in the sentence strip based on the child's own usage history, stored only on the device.
  • Roman Urdu labels and additional regional languages contributed by therapists.

The problem for non-speaking children and their families

Children with autism, cerebral palsy, Down syndrome or other conditions that affect speech often understand far more than they can say. Augmentative and alternative communication (AAC) gives them a voice: they tap pictures and a device speaks. Speech and language therapists use AAC widely, but in many countries families face three barriers. The best known apps are expensive and tied to iPads. Vocabularies and voices are designed for English, so a child at home in Urdu, Punjabi or Pashto hears a language nobody at home speaks. And therapists end up printing paper picture cards because nothing digital fits.

A child who can only ask for "water" or "toilet" in a language their grandmother does not understand is still not being heard.

What already exists and the gap

  • Proloquo2Go by AssistiveWare is a leading symbol-based AAC app for iOS, sold as a premium one-time purchase on the App Store, a price many families cannot stretch to.
  • Cboard is a free, open source web AAC app with thousands of symbols and support for many languages through the browser's speech engine.
  • Avaz is a commercial AAC app developed in India with several Indian language options.
  • Printed PECS cards remain common in therapy centres because they are cheap and familiar.

The gap is an affordable, offline-first app designed from the start for bilingual Urdu and English families, with voices recorded by family members where synthetic Urdu speech falls short, and an editor simple enough for a parent with no technical background.

What you build

Two modes in one app.

  • Communicator mode for the child: large, consistent grids of symbol tiles grouped into folders (food, feelings, people, places, needs). Tapping speaks immediately. A sentence strip at the top collects tiles so the child can say "I want juice" and replay it. Core words stay in the same position on every board, which matters for motor learning.
  • Caregiver mode, behind a simple gate (a long press plus a sum, for example): add a tile by taking a photo, type a label in Urdu or English, record a voice clip, hide tiles that confuse the child, and see which words were used this week.
  • Sharing: a therapist builds a board set once and exports it to every family on their caseload.

Use an open symbol library such as ARASAAC (check its licence terms) and let families replace symbols with their own photos.

The technically interesting part

This is an accessibility and human-computer interaction project, and the challenge is design under real constraints. You need to get Urdu right: right-to-left layout, correct font shaping, and a speech strategy that falls back from device text-to-speech to recorded clips when the synthetic voice is poor. You need touch handling that forgives tremor and accidental double taps without making the app feel slow. And everything must work offline on a mid-range Android tablet.

What your evaluators should see is the research loop: you observed real sessions, changed the design because of what you saw, and measured the difference.

How to evaluate it

  • Task success: in observed sessions, how many intended requests the child completed with the app versus with paper cards, as judged by the therapist.
  • Caregiver setup: time for a parent to add a new tile with a photo and voice, first attempt and after a week.
  • Accessibility audit: check against WCAG 2.2 success criteria that apply to touch apps, including target size and contrast, and test with the platform screen reader for caregiver screens.
  • Performance: time from tap to speech on a low-cost Android tablet, and battery use over an hour of active use.
  • Qualitative: structured interviews with at least three caregivers and one therapist.

Suggested plan

  1. Weeks 1 to 3: contact a therapy centre or special education school, get consent processes approved by your department, observe two sessions.
  2. Weeks 4 to 6: paper and Figma prototypes of the boards, reviewed by the therapist.
  3. Weeks 7 to 10: communicator mode, offline storage, speech with fallbacks.
  4. Weeks 11 to 13: caregiver mode, access settings, export and import.
  5. Weeks 14 to 16: field sessions, fixes, study report.

Path to a product

Keep the core app free for families, since cost is the main barrier. Sell a therapist and school plan: board sharing across a caseload, usage reports and priority support, priced per therapist per month or as a yearly licence for a centre. NGOs working in disability inclusion and special education schools are realistic first partners, and they often have grant funding for exactly this. Scale by adding languages with volunteer therapists.

Scope warning

Do not make medical or diagnostic claims. Do not build eye tracking or custom hardware. Do not collect children's data on a server by default; any sync must be optional and consented. Do not skip the therapist: a board designed without one will be wrong in ways you cannot see.

Learn what you need on Sefism

Get help with this idea

Projects with families and therapists need ethics care and patience, and the payoff is a project with real users from day one. If you want a second opinion on scope, stack or how to evaluate it before you pitch it to your supervisor, bring your draft proposal and we will pressure-test it together. You build it; the guidance is on the decisions.

New here? Create a free account first.

Ideas and guidance, not finished projects

These are project ideas and scoping guidance, published free for students to use as a starting point. I do not build, write, or sell final-year projects, and I do not complete coursework for anyone. Take an idea, make it yours, and build it.

Not sure this one fits you?

I help students pick an idea that matches their skills and their deadline, then scope it down until it is finishable. Guidance only, never done for you.

Discuss this idea
Work with me

Stuck on something specific?

Writing only gets you so far. If you want an answer to your situation rather than the general case, book a session and we will work through it together. Sessions are free for approved Sefism members, and a few slots open each week.

Book a free sessionSee all services

Follow along

New writing, resources and project ideas land here first.