15th Annual Conference of the International Speech Communication Association

September 14-18, 2014

Automatic Speech Recognition and Translation of a Swiss German Dialect: Walliserdeutsch

Philip N. Garner, David Imseng, Thomas Meyer

Idiap Research Institute, Switzerland

Walliserdeutsch is a Swiss German dialect spoken in the south west of Switzerland. To investigate the potential of automatic speech processing ofWalliserdeutsch, a small database was collected based mainly on broadcast news from a local radio station. Experiments suggest that automatic speech recognition is feasible: use of another (Swiss German) database shows that the small data size lends itself to bootstrapping from other data; use of Kullback-Leibler HMM suggests that phoneme mapping techniques can compensate for a grapheme-based dictionary. Experiments also indicate that statistical machine translation is feasible; the difficulty of small data size is offset by the close proximity to (high) German.

Full Paper

Bibliographic reference.  Garner, Philip N. / Imseng, David / Meyer, Thomas (2014): "Automatic speech recognition and translation of a Swiss German dialect: Walliserdeutsch", In INTERSPEECH-2014, 2118-2122.