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

Philip Neil Garner, David Imseng, Thomas Meyer
2014
Conference paper

Abstract

Walliserdeutsch is a Swiss German dialect spoken in the south west of Switzerland. To investigate the potential of automatic speech processing of Walliserdeutsch, 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.

Official source

https://infoscience.epfl.ch/record/202570?ln=en

About this result

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Related concepts

Related publications

Implicitation of Discourse Connectives in (Machine) Translation

Thomas Meyer

Explicit discourse connectives in a source language text are not always translated to comparable words or phrases in the target language. The paper provides a corpus analysis and a method for semi-automatic detection of such cases. Results show that discourse connectives are not translated into comparable forms (or even any form at all), in up to 18% of human reference translations from English to French or German. In machine translation, this happens much less frequently (up to 8% only). Work in progress aims to capture this natural implicitation of discourse connectives in current statistical machine translation models.

2013

Disambiguating Discourse Connectives for Statistical Machine Translation

Thomas Meyer, Andrei Popescu-Belis

This paper shows that the automatic labeling of discourse connectives with the relations they signal, prior to machine translation (MT), can be used by phrase-based statistical MT systems to improve their translations. This improvement is demonstrated here when translating from English to four target languages - French, German, Italian and Arabic - using several test sets from recent MT evaluation campaigns. Using automatically labeled data for training, tuning and testing MT systems is beneficial on condition that labels are sufficiently accurate, typically above 70%. To reach such an accuracy, a large array of features for discourse connective labeling (morpho-syntactic, semantic and discursive) are extracted using state-of-the-art tools and exploited in factored MT models. The translation of connectives is improved significantly, between 0.7% and 10% as measured with the dedicated ACT metric. The improvements depend mainly on the level of ambiguity of the connectives in the test sets.

2015

We first present our work in machine translation, during which we used aligned sentences to train a neural network to embed n-grams of different languages into an d-dimensional space, such that n-grams that are the translation of each other are close with respect to some metric. Good n-grams to n-grams translation results were achieved, but full sentences translation is still problematic. We realized that learning semantics of sentences and documents was the key for solving a lot of natural language processing problems, and thus moved to the second part of our work: sentence compression. We introduce a flexible neural network architecture for learning embeddings of words and sentences that extract their semantics, propose an efficient implementation in the Torch framework and present embedding results comparable to the ones obtained with classical neural language models, while being more powerful.

2009