evidoria

← Back to browse

Good practice Imported

Tilde × Microsoft — A Wearable-Mic Speech-to-Text Pilot for Deaf and Hard-of-Hearing Students in Latvia

Latvia · Riga · See the Latvia profile · See the Riga profile

Evidence: Descriptive / self-reported Top 89% 27/100 · Ask Evidence Copilot about this practice

Latvian language-tech firm Tilde and Microsoft piloted a cordless wearable microphone with real-time speech-to-text captioning for deaf and hard-of-hearing pupils in two Latvian schools. Results so far are proof-of-concept only, with no published outcome data yet.

Tilde × Microsoft — A Wearable-Mic Speech-to-Text Pilot for Deaf and Hard-of-Hearing Students in Latvia

Details

Maturity
Pilot
Promoter
Tilde
Period
2023 (proof-of-concept)
Keywords
speech recognition, assistive technology, K-12 education, hearing impairment

Context

The World Health Organization estimates around 430 million people worldwide live with disabling hearing loss, a gap Latvian schools had limited tools to close for deaf and hard-of-hearing pupils. Latvian language-technology company Tilde, working with Microsoft and supported by NGOs and schools, built an automatic speech-recognition system paired with a cordless wearable microphone that transcribes teacher speech live as captions on interactive whiteboards, classroom monitors, PCs or mobile devices.

Activities

The system was tested as a proof-of-concept with mathematics, literature and informatics teachers and their students in two Latvian schools, as reported by the American Chamber of Commerce in Latvia and by trade outlet Slator in October 2023.

Conclusions

This is an early-stage, unevaluated pilot: no accuracy figures, number of students reached, or learning-outcome data have been published, and no funding or national rollout plan has been announced.

Implementation
Indicative cost
Low (< €50k)
Time to results
Short (< 1 year)
Staffing & skills
Tilde (language-technology developer), Microsoft (technology partner), NGOs and schools (support and testing)

Conditions for success

  • Real-time captions displayed on existing classroom hardware (whiteboards, monitors, PCs, mobile devices)
  • Teacher buy-in across multiple subjects (mathematics, literature, informatics)

Common failure modes

  • No accuracy or outcome data published to confirm effectiveness beyond proof-of-concept

Commonly funded by

Own resources / municipal budget

Indicative funding routes for practices of this type — always check each programme's current calls and eligibility rules.

Do you run this practice? Claim it — verified implementers get a public contact pathway and can propose corrections.

Data sources

Where this practice's information was retrieved from, and when.

Attachments

Similar practices you may find useful