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.

Translation

Text-to-Speech Pipeline for Swiss German -- A comparison

no code implementations • 31 May 2023 • Tobias Bollinger, Jan Deriu, Manfred Vogel

In this work, we studied the synthesis of Swiss German speech using different Text-to-Speech (TTS) models.

Speech Synthesis

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) +4

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

2nd Swiss German Speech to Standard German Text Shared Task at SwissText 2022

1 code implementation • 17 Jan 2023 • Michel Plüss, Yanick Schraner, Christian Scheller, Manfred Vogel

We present the results and findings of the 2nd Swiss German speech to Standard German text shared task at SwissText 2022.

Sentence

Swiss German Speech to Text system evaluation

no code implementations • 1 Jul 2022 • Yanick Schraner, Christian Scheller, Michel Plüss, Manfred Vogel

We compare the four systems to our STT model, referred to as FHNW from hereon after, and provide details on how we trained our model.

SDS-200: A Swiss German Speech to Standard German Text Corpus

1 code implementation • LREC 2022 • Michel Plüss, Manuela Hürlimann, Marc Cuny, Alla Stöckli, Nikolaos Kapotis, Julia Hartmann, Malgorzata Anna Ulasik, Christian Scheller, Yanick Schraner, Amit Jain, Jan Deriu, Mark Cieliebak, Manfred Vogel

We present SDS-200, a corpus of Swiss German dialectal speech with Standard German text translations, annotated with dialect, age, and gender information of the speakers.

Speech Synthesis Translation

Swiss Parliaments Corpus, an Automatically Aligned Swiss German Speech to Standard German Text Corpus

1 code implementation • 6 Oct 2020 • Michel Plüss, Lukas Neukom, Christian Scheller, Manfred Vogel

We present the Swiss Parliaments Corpus (SPC), an automatically aligned Swiss German speech to Standard German text corpus.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

Sample Efficient Reinforcement Learning through Learning from Demonstrations in Minecraft

3 code implementations • 12 Mar 2020 • Christian Scheller, Yanick Schraner, Manfred Vogel

Sample inefficiency of deep reinforcement learning methods is a major obstacle for their use in real-world applications.

reinforcement-learning Reinforcement Learning (RL)