Open Source Speech and Language Resources for Frisian

In this paper, we present several open source speech and language resources for the under-resourced Frisian language. Frisian is mostly spoken in the province of Fryslân which is located in the north of the Netherlands. The native speakers of Frisian are Frisian-Dutch bilingual and often code-switch in daily conversations. The resources presented in this paper include a code-switching speech database containing radio broadcasts, a phonetic lexicon with more than 70k words and a language model trained on a text corpus with more than 38M words. With this contribution, we aim to share the Frisian resources we have collected in the scope of the FAME! project, in which a spoken document retrieval system is built for the disclosure of the regional broadcaster’s radio archives. These resources enable research on code-switching and longitudinal speech and language change. Moreover, a sample automatic speech recognition (ASR) recipe for the Kaldi toolkit will also be provided online to facilitate the Frisian ASR research.