MARATTO

other · Zenodo (CERN European Organization for Nuclear Research)

Mooré Greeting Speech Dataset for English Language Learning

2026Open accessNazi Boni University

In plain language

A dedicated dataset comprising spoken audio recordings in the Mooré language has been compiled and released for research and educational use. These recordings were collected specifically to aid the development and preliminary evaluation of a voice-centred mobile application intended for English language learning in Burkina Faso. The dataset underpins a closed-vocabulary speech-recognition component within the software. Structurally, this recognition system is built upon Mel-frequency cepstral coefficient features and bidirectional long short-term memory models. By capturing regional spoken input, the resource provides the necessary acoustic data to build, train, and assess specialised language-learning interfaces tailored to Mooré speakers.

Key takeaways

  • The dataset consists of Mooré speech recordings gathered for research and educational purposes.
  • The audio was collected to build and evaluate a voice-centred mobile application for English language learning in Burkina Faso.
  • The recordings support a closed-vocabulary speech-recognition component that uses MFCC features and BiLSTM models.

Why it matters

Digital language-learning tools require localized acoustic data to function effectively for speakers of indigenous languages. By offering voice recordings in Mooré, this dataset helps developers construct and assess voice-driven educational mobile applications tailored specifically to language learners in Burkina Faso.

Commercialisation angle

This dataset enables the development of voice-driven mobile tools tailored for Mooré speakers learning English. The intended end users are language learners in Burkina Faso. Regarding technology readiness, the system is at an applied and tested stage, having already supported the prototype development and preliminary evaluation of a closed-vocabulary mobile application.

AI-generated from the published abstract. Always read the original work before citing.

Abstract

This dataset contains Mooré speech recordings collected and used for the development and preliminary evaluation of a voice-centered mobile application for English language learning in Burkina Faso. The recordings support a closed-vocabulary speech-recognition component based on MFCC features and BiLSTM models. The dataset is provided for research and educational purposes.

Read the original research

This page summarises published work. The authoritative version sits with the publisher.

DOI: 10.5281/zenodo.22403548

Is something wrong with this record? Report it or request removal.

Discussion

Discuss this research

Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.

No discussion yet. Open the first thread.