Dialect Transfer for Swiss German Speech Translation

no code implementations • 13 Oct 2023 • 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.

Diversity Translation

STT4SG-350: A Speech Corpus for All Swiss German Dialect Regions

no code implementations • 30 May 2023 • Michel Plüss, Jan Deriu, Yanick Schraner, Claudio Paonessa, Julia Hartmann, Larissa Schmidt, Christian Scheller, Manuela Hürlimann, Tanja Samardžić, Manfred Vogel, Mark Cieliebak

We train an ASR model on the training set and achieve an average BLEU score of 74. 7 on the test set.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +5

Improving Metrics for Speech Translation

no code implementations • 22 May 2023 • Claudio Paonessa, Dominik Frefel, Manfred Vogel

We introduce Parallel Paraphrasing ($\text{Para}_\text{both}$), an augmentation method for translation metrics making use of automatic paraphrasing of both the reference and hypothesis.

Translation