Skip to main content

Speech Recognition for Swiss German

The FHNW Institute for Data Science is working on speech recognition technology to transform speech in various Swiss dialects to Standard German text.

Spracherkennung für Schweizerdeutsch-forschungsprojekt.jpg

Current state of the art

Speech recognition for English or Standard German works fairly well and is already part of our daily lives with Alexa, Siri etc. Unfortunately, this is not the case for Swiss German. The main reasons are the diversity of dialects, the lack of a standardized writing system and the small number of speakers. While solutions for specific use cases, e.g. a scenario with a restricted domain and only one dialect, are available, they are expensive and not reusable.

Goals

    The goal of this project is to create a speech recognition system that works for all domains and dialects. This would considerably decrease costs and enable many new applications, including voice assistants, transcription of meetings or phone calls and voice-controlled robots.

    Results

      Our approach is based on the latest research in Deep Learning and Natural Language Processing. We trained a single combined speech recognition and translation model to directly translate Swiss German speech to Standard German text. This requires a huge amount of training data, i.e. hundreds or thousands of hours of spoken Swiss German sentences aligned to the corresponding Standard German text.

      To acquire enough data, we developed an alignment procedure to automatically extract sentence-level speech-text-pairs from long speech recordings and their text transcripts, e.g. parliament discussions with detailed transcripts. Details can be found in our paper. Also, we published a dataset created using this procedure. It can be downloaded here. Our model trained on this dataset achieves a word error rate of 29 % and a BLEU score of 54.

      Project information

      Partner

      FHNW Institute for Data ScienceSwissNLP, ZHAW, Universität Zürich

      Project team

      Prof. Dr. Manfred Vogel, Michel Plüss, Lukas Neukom, Christian Scheller


      Share this page: