This paper describes the first, three-year phase of a project at the National Research Council of Canada that creates software to assist Indigenous communities in preserving their languages and extending their use. The project aimed to work within the empowerment paradigm, where collaboration with communities and fulfillment of their goals is central. Since many of the technologies we developed were in response to community needs, the project ended up as a collection of diverse subprojects, including the creation of a sophisticated framework for building verb conjugators for highly inflectional polysynthetic languages (such as Kanyen'kéha, in the Iroquoian language family), release of what is probably the largest available corpus of sentences in a polysynthetic language (Inuktut) aligned with English sentences and experiments with machine translation (MT) systems trained on this corpus, free online services based on automatic speech recognition (ASR) for easing the transcription bottleneck for speech recordings, software for implementing text prediction and read-along audiobooks for Indigenous languages, and several other subprojects. Sociolinguistic BackgroundThere are about 70 Indigenous languages from 10 distinct language families currently spoken in Canada (Rice, 2008). Most of these languages have complex morphology; they are polysynthetic or agglutinative. Commonly, a single word carries the meaning of an entire clause in Indo-European languages.

This paper describes the motivation and development of speech synthesis systems for the purposes of language revitalization. By building speech synthesis systems for three Indigenous languages spoken in Canada, Kanien'kéha, Gitksan & SENĆOŦEN, we re-evaluate the question of how much data is required to build low-resource speech synthesis systems featuring state-of-the-art neural models. For example, preliminary results with English data show that a FastSpeech2 model trained with 1 hour of training data can produce speech with comparable naturalness to a Tacotron2 model trained with 10 hours of data. Finally, we motivate future research in evaluation and classroom integration in the field of speech synthesis for language revitalization.

Language technologies are an increasingly common part of daily life for people around the world. Millions of users per day access services like Google Translate and Apple's Siri in a technology ecosystem that favours a handful of the world's most common languages. In a form of digital colonization, Indigenous languages are pushed aside in a profit-based system of research and development that results in both values conflicts and technological misalignments. Despite the hostile environment that disincentivizes the use of Indigenous languages, Indigenous language communities are pushing back by engaging language technologies to proactively support their work of language maintenance and revitalization. This paper argues that Indigenous leadership in the development of language technologies encourages the development of responsive and responsible Indigenous language technologies (ILT) that push back against dominant cultural and technical limitations.