We are committed to the preservation of indigenos languages and using
technology in a respectful way to achieve this goal. Modern Automatic Speech
Recognition (ASR) advancements, along with Natural
Language Processing (NLP), has enabled voice assistants, such as Siri, and
education apps like Duolingo. Unfortunately, as is the case for most Indigneous
languages, this technology does not exist for Makah and other languages in
the Wakashan language family. The specific problem is a lack of necessary
research and engineering to build ASR AI for Makah and related languages.
There's a lack of annotated audio suitable for machine learning, basic research
to build polysynthetic ASR for Makah, and community skills to conduct this
work. That where we come in. The purpose of this website is to collect audio data
that we can use to train an AI model that we'll be able to use in future to teach
Makah to anyone in the world. Our project is indigenous-lead and we are working
closely with the Wakashan community to ensure that everyone's privacy is respected
and data is collected with respect to the community's wishes.