Introduction
Learning a new language has become easier with the help of language learning apps and translation tools. However, these technologies often overlook the needs of those who speak Indigenous languages in regions such as North America and New Zealand. Indigenous languages have unique structures and limited recorded speech data, making it challenging to develop language recognition algorithms for technologies like Amazon’s Alexa.
The Challenge of Indigenous Languages
Many Indigenous languages, like polysynthetic languages, have different structures from popular languages like English or Mandarin. In polysynthetic languages, a single word can express a phrase that would require multiple words in English. Additionally, there is a lack of available data sets for most Indigenous languages, making it difficult to train AI models.
Meeting the Challenge
Keoni Mahelona, the chief technical officer of Te Hiku Media, developed a speech-recognition model using only 310 hours of recorded te reo, the Māori language spoken in New Zealand. This breakthrough showed that it is possible to build language models with limited data, providing hope for other Indigenous languages. Mahelona is collaborating on Papa Reo, a platform for te reo speech-recognition apps, making it easier for New Zealanders to interact with their devices in their native language.
Improving Language Learning with AI
Michael Running Wolf, a PhD student studying natural language processing, envisions AI technology that helps individuals practice speaking their ancestral languages. This includes using AI as a tool for children to supplement their language learning, providing real-time corrections and feedback. Additionally, Running Wolf’s wife, Caroline, is designing augmented reality experiences that immerse individuals in their native languages and teach cultural protocols.
Ethical Considerations
While the development of Indigenous language apps and AI technologies is beneficial, Indigenous developers and communities emphasize the importance of respecting their languages and culture. They urge large companies not to monetize Indigenous languages without proper collaboration and agreements with Indigenous-run organizations. This is crucial to rectify the historical injustices caused by colonization.
Conclusion
AI technology has the potential to play a significant role in preserving and reviving Indigenous languages. By developing language recognition algorithms and language learning tools, we can empower Indigenous communities to keep their languages alive. Collaboration, respect, and ethical considerations are essential in this process to ensure that the economic development of Indigenous communities is prioritized.
Reference: Annalee Newitz
