Search

We present STT4SG-350 (Speech-to-Text for Swiss German), a corpus of Swiss German speech, annotated with Standard German text at the sentence level. The data is collected using a web app in which the speakers are shown Standard German sentences, which they translate to Swiss German and record. We make the corpus publicly available. It contains 343 hours of speech from all dialect regions and is the largest public speech corpus for Swiss German to date. Application areas include automatic speech recognition (ASR), text-to-speech, dialect identification, and speaker recognition. Dialect information, age group, and gender of the 316 speakers are provided. Genders are equally represented and the corpus includes speakers of all ages. Roughly the same amount of speech is provided per dialect region, which makes the corpus ideally suited for experiments with speech technology for different dialects. We provide training, validation, and test splits of the data. The test set consists of the same spoken sentences for each dialect region and allows a fair evaluation of the quality of speech technologies in different dialects. We train an ASR model on the training set and achieve an average BLEU score of 74.7 on the test set. The model beats the best published BLEU scores on 2 other Swiss German ASR test sets, demonstrating the quality of the corpus.

In this work, we studied the synthesis of Swiss German speech using different Text-to-Speech (TTS) models. We evaluated the TTS models on three corpora, and we found, that VITS models performed best, hence, using them for further testing. We also introduce a new method to evaluate TTS models by letting the discriminator of a trained vocoder GAN model predict whether a given waveform is human or synthesized. In summary, our best model delivers speech synthesis for different Swiss German dialects with previously unachieved quality.

Eine der größten gesellschaftlichen Herausforderungen des 21. Jahrhunderts ist die Eindämmung des Klimawandels. Ein Ansatz, der vor allem in der Kraftfahrzeugindustrie in den letzten Jahren zunehmend an Bedeutung gewonnen hat, ist der ganzheitliche Leichtbau, wodurch vor allem konventionelle Fertigungstechnologien im Bereich der Umformtechnik zunehmend an ihre Grenzen stoßen. Durch Anwendung der innovativen Prozessklasse der Blechmassivumformung können Funktionsbauteile mit einem hohen Grad der Funktionsintegration prozesssicher, sowie energie- und kostenoptimiert hergestellt werden. Dabei konnte vor allem durch den Einsatz von prozessangepassten Halbzeugen eine gesteigerte Materialeffizienz nachgewiesen werden. Vor allem inkrementelle Umformverfahren weisen dafür ein hohes Potential auf. Im Rahmen der vorliegenden Arbeit wird daher das Ziel verfolgt, ein ganzheitliches Prozessverständnis zur Herstellung von Tailored Blanks durch einen neuartigen flexiblen Walzprozess aufzubauen. Zur Ableitung physikalischer Zusammenhänge wird eine grundlegende experimentelle Prozess- und Einflussanalyse durchgeführt und darauf aufbauend eine ganzheitliche Methodik zur Herstellung einer rotationssymmetrischen Materialvorverteilung abgeleitet. Unter Anwendung der gewonnenen Erkenntnisse wird anschließend die Übertragbarkeit der Methodik auf höherfeste Werkstoffklassen und variierende Halbzeugdicken sowie die Einsatzfähigkeit der Halbzeuge in einem nachgelagerten Tiefzieh-Stauchprozess bewertet., One of the greatest social challenges of the 21st century is the mitigation of climate change. One approach that has become increasingly important in recent years, especially in the automotive industry, is holistic lightweight construction, which is increasingly pushing conventional manufacturing technologies in the area of forming technology to their limits. By applying the innovative process class of sheet bulk metal forming, functional components with a high degree of functional integration can be manufactured in a process-safe, energy-and cost-optimized manner. The use of process-adapted semifinished products in particular has proven to increase material efficiency. In particular, incremental forming processes show a high potential. The aim of the present work is therefore to develop a holistic process understanding for the production of tailored blanks by means of a new flexible rolling process. To derive physical relationships, a fundamental experimental process and influence analysis is carried out and, based on this, a holistic methodology for the manufacturing of a rotationally symmetrical material pre-distribution is derived. Using the knowledge gained, the transferability of the methodology to higher-strength material classes and varying semi-finished product thicknesses, as well as the usability of the semi-finished products in a downstream combined deep-drawing and upsetting process is evaluated., FAU Studien aus dem Maschinenbau; 411

We present the results and findings of the 2nd Swiss German speech to Standard German text shared task at SwissText 2022. Participants were asked to build a sentence-level Swiss German speech to Standard German text system specialized on the Grisons dialect. The objective was to maximize the BLEU score on a test set of Grisons speech. 3 teams participated, with the best-performing system achieving a BLEU score of 70.1., Comment: 3 pages, 0 figures, to appear in proceedings of SwissText 2022

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. This method counteracts the typically misleading results of speech translation metrics such as WER, CER, and BLEU if only a single reference is available. We introduce two new datasets explicitly created to measure the quality of metrics intended to be applied to Swiss German speech-to-text systems. Based on these datasets, we show that we are able to significantly improve the correlation with human quality perception if our method is applied to commonly used metrics., Comment: Preprint SwissText 2023

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. The dataset allows for training speech translation, dialect recognition, and speech synthesis systems, among others. The data was collected using a web recording tool that is open to the public. Each participant was given a text in Standard German and asked to translate it to their Swiss German dialect before recording it. To increase the corpus quality, recordings were validated by other participants. The data consists of 200 hours of speech by around 4000 different speakers and covers a large part of the Swiss-German dialect landscape. We release SDS-200 alongside a baseline speech translation model, which achieves a word error rate (WER) of 30.3 and a BLEU score of 53.1 on the SDS-200 test set. Furthermore, we use SDS-200 to fine-tune a pre-trained XLS-R model, achieving 21.6 WER and 64.0 BLEU.

In this paper, we present a learning rate method for gradient descent using only first order information. This method requires no manual tuning of the learning rate. We applied this method on a linear neural network built from scratch, along with the full-batch gradient descent, where we calculated the gradients for the whole dataset to perform one parameter update. We tested the method on a moderate sized dataset of housing information and compared the result with that of the Adam optimizer used with a sequential neural network model from Keras. The comparison shows that our method finds the minimum in a much fewer number of epochs than does Adam.

A 3D web-service has been developed for the modeling and for the management of karst aquifers and related groundwater resources. Visual KARSYS allows users to build explicit models of karst aquifers via a 3D geological modeller (gmLib Python library) and a series of tools (i.e. algorithms) which provide characteristics of groundwater bodies by applying hydraulic principles. Visual KARSYS is designed for geologists or hydrogeologists working for public institutions or private companies, but also for administration or decision makers facing various issues in karst environments: groundwater resources, natural hazards, geothermal energy, civil engineering, etc. Outputs from Visual KARSYS (data, models and resulting documentation) can be shared between users for being consulted or edited. The web-service is available at visualkarsys.com and it is currently free-of-charge and we encourage users to use it. In March 2021, more than 425 users already registered and ~150 persons attended the training courses. The Visual KARSYS project is supported by the Swiss Federal Office for Environment via the grant for the promotion of environmental technology (2016-2019, UTF 537.13.16).

Sample inefficiency of deep reinforcement learning methods is a major obstacle for their use in real-world applications. In this work, we show how human demonstrations can improve final performance of agents on the Minecraft minigame ObtainDiamond with only 8M frames of environment interaction. We propose a training procedure where policy networks are first trained on human data and later fine-tuned by reinforcement learning. Using a policy exploitation mechanism, experience replay and an additional loss against catastrophic forgetting, our best agent was able to achieve a mean score of 48. Our proposed solution placed 3rd in the NeurIPS MineRL Competition for Sample-Efficient Reinforcement Learning., 10 pages, 2 figures

We present the Swiss Parliaments Corpus (SPC), an automatically aligned Swiss German speech to Standard German text corpus. This first version of the corpus is based on publicly available data of the Bernese cantonal parliament and consists of 293 hours of data. It was created using a novel forced sentence alignment procedure and an alignment quality estimator, which can be used to trade off corpus size and quality. We trained Automatic Speech Recognition (ASR) models as baselines on different subsets of the data and achieved a Word Error Rate (WER) of 0.278 and a BLEU score of 0.586 on the SPC test set. The corpus is freely available for download., Comment: 8 pages, 0 figures

The presented work focuses on the presentation of a discrete event simulator which can be used for automated sequencing and optimization of building processes. The sequencing is based on the commonly used component–activity–resource relations taking structural and process constraints into account. For the optimization a genetic algorithm approach was developed, implemented and successfully applied to several real life steel constructions. In this contribution we discuss the application of the discrete event simulator including its optimization capabilities on a 4D process model of a steel structure of an automobile recycling facility.

Concilium, Bd. 13 Nr. 3 (1977): Concilium: Internationale Zeitschrift für Theologie, Band 13, Heft 3

The invention relates to the use of L-xylulose as an inhibitor for saccharase and maltase enzyme activity.