Modern speech synthesis techniques can produce natural-sounding speech given sufficient high-quality data and compute resources. However, such data is not readily available for many languages. This paper focuses on speech synthesis for low-resourced African languages, from corpus creation to sharing and deploying the Text-to-Speech (TTS) systems. We first create a set of general-purpose instructions on building speech synthesis systems with minimum technological resources and subject-matter expertise. Next, we create new datasets and curate datasets from "found" data (existing recordings) through a participatory approach while considering accessibility, quality, and breadth. We demonstrate that we can develop synthesizers that generate intelligible speech with 25 minutes of created speech, even when recorded in suboptimal environments. Finally, we release the speech data, code, and trained voices for 12 African languages to support researchers and developers.
Bio
Perez Ogayo is a masters student at Carnegie Mellon University in the Language Technologies Institute(LTI) where she is focusing on low resource natural language processing. Her interests in NLP are multilingual machine translation, speech synthesis and recognition and NLP for endangered languages. She is a researcher at Masakhane working on Luo and Kiswahili.
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License (CC-BY-NC-SA 4.0)
