Khaya African Language Translation and Speech Recognition AI Demonstrates Major Improvements

The following describes work done by the NLP Ghana and Algorine teams to democratize modern machine learning tool access for Ghanaian and other African Languages. It culminates in the release of version 1.0.4 of the Khaya AI app, pushing further the automatic speech recognition (ASR) and machine translation “state-of-the-art” for over 60 million people in West Africa.

What Is The Inspiration Behind The Name Khaya AI?

Fig 1. Khaya AI is named after the Khaya African Mahogany tree. Just like the tree, it is rooted in Africa. We hope it will similarly become a nourishing, sustaining resource for Africa and Africans in the digital future. It is also a word for “home” in several Southern African languages.

What could the Previous Version of Khaya AI do?

Fig 2. Nine months ago, version 1.0.3 of the Khaya App was released — providing the world with Twi and Yoruba Automatic Speech Recognition (ASR) capabilities, as well as Ga, Ewe, Twi and Yoruba neural text translators.
Fig 3. Khaya AI Improves over time by learning from user feedback. The improvements described in this article were achieved over a period of 9 months, and usage of the translators by tens of thousands of people.

What Can The New Version of Khaya AI Do?

Highlights

1. Addition of Dagbani translation and speech recognition marks the beginning of expansion of the AI into Northern Ghana — Hausa, Frafra and Buli are in the release pipeline next, among others. We are committed to a fairness of linguistic coverage.

2. Our Yoruba text translator outperforms Google Translate. We are committed to providing world-class solutions across Africa

3. Across the board improvements in text translation have been achieved — as measured by the BLEU metric, confirmed by human evaluators, and shown in Table 1.

4. Across the board improvements in Automatic Speech Recognition (ASR) has been achieved — as measured by the Word Error Rate (WER), confirmed by human evaluators, and shown in Table 2.

5. Collaboration with the Harvard African Language School on East African Languages — to date including Swahili, Kikuyu and Kimeru — furthers our commitment to providing world-class solutions across Africa

Fig 4. Khaya AI can help speakers of different languages to communicate with each other, by translating African languages — such as Twi, Ewe and Ga — into English and vice versa. By learning from user feedback, it improves over time.
Table 1. Measured improvements in text translator performance using the BLEU metric (higher is better). Improvements were confirmed using human evaluators. Yoruba text translators outperform Google Translate by 1.5 BLEU points for the Yoruba to English direction and 9.8 BLEU points for the English to Yoruba direction on our benchmarks. Dagbani showing ∞ improvement indicates a previously nonexistent model. Ga improvements are ongoing, and it has been left out from this table
Fig 5. Khaya AI can help speakers of African languages to communicate with their phones and other devices, by transcribing African languages speech — such as Twi, Ewe, Yoruba and Ga — into text. This text can then be used by Alexa to control a smartphone, for instance, or further processed for a variety of applications
Table 2. Measured improvements in Automatic Speech Recognition (ASR) performance using the WER metric (lower is better). Improvements were confirmed using human evaluators. ∞ improvement indicates a previously nonexistent model.

What Comes Next?

HOW TO SUPPORT OUR WORK

Fig 6. We are building a more inclusive world with cutting-edge African language tech, will you help us?
Fig 7. You can support our work by purchasing a cheap ad-free subscription to the app.

--

--

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store