Paper ID: 2310.09088

Dialect Transfer for Swiss German Speech Translation

Claudio Paonessa, Yanick Schraner, Jan Deriu, Manuela Hürlimann, Manfred Vogel, Mark Cieliebak

This paper investigates the challenges in building Swiss German speech translation systems, specifically focusing on the impact of dialect diversity and differences between Swiss German and Standard German. Swiss German is a spoken language with no formal writing system, it comprises many diverse dialects and is a low-resource language with only around 5 million speakers. The study is guided by two key research questions: how does the inclusion and exclusion of dialects during the training of speech translation models for Swiss German impact the performance on specific dialects, and how do the differences between Swiss German and Standard German impact the performance of the systems? We show that dialect diversity and linguistic differences pose significant challenges to Swiss German speech translation, which is in line with linguistic hypotheses derived from empirical investigations.

Submitted: Oct 13, 2023