Fraunhofer-Publica
The Fraunhofer-Publica has been successfully documenting the research results of the Fraunhofer-Gesellschaft for over 30 years. The platform enables the collaborative linking of research-relevant objects and disseminates within the international scientific community.
The Fraunhofer-Publica thus fulfils its responsibility to promote the transfer of knowledge and know-how to industry and society.
Categories
Research outputs
As an application-oriented research organisation, Fraunhofer aims to conduct highly innovative and solution-oriented research - for the benefit of society and to strengthen the German and European economy.
Projects
Fraunhofer is tackling the current challenges facing industry head on. By pooling their expertise and involving industrial partners at an early stage, the Fraunhofer Institutes involved in the projects aim to turn original scientific ideas into marketable products as quickly as possible.
Researchers
Scientific achievement and practical relevance are not opposites - at Fraunhofer they are mutually dependent. Thanks to the close organisational links between Fraunhofer Institutes and universities, science at Fraunhofer is conducted at an internationally first-class level.
Institutes
The Fraunhofer-Gesellschaft is the leading organisation for applied research in Europe. Institutes and research facilities work under its umbrella at various locations throughout Germany.
Recent Additions
-
-
-
PublicationLow-Resource Text-to-Speech Using Specific Data and Noise Augmentation( 2023)Many neural text-to-speech architectures can synthesize nearly natural speech from text inputs. These architectures must be trained with tens of hours of annotated and high-quality speech data. Compiling such large databases for every new voice requires a lot of time and effort. In this paper, we describe a method to extend the popular Tacotron-2 architecture and its training with data augmentation to enable single-speaker synthesis using a limited amount of specific training data. In contrast to elaborate augmentation methods proposed in the literature, we use simple stationary noises for data augmentation. Our extension is easy to implement and adds almost no computational overhead during training and inference. Using only two hours of training data, our approach was rated by human listeners to be on par with the baseline Tacotron-2 trained with 23.5 hours of LJSpeech data. In addition, we tested our model with a semantically unpredictable sentences test, which showed that both models exhibit similar intelligibility levels.
-
PublicationLPC-GAN for Speech Super-Resolution( 2023)Up to today telephone speech lacks of perceptual quality and intelligibility due to bandwidth removal and quantisation artefacts in the encoding process. Super-resolution artificially regenerates this missing frequency content and thus improves the perceptual quality and intelligibility. This work proposes a novel approaches for super-resolution based on generative adversarial networks with convolutional architectures. Motivated by the source-filter model of the human speech production, the proposed system decomposes the speech signal into spectral envelope and excitation signal. The missing frequency-content of envelope and excitation are restored with dedicated networks. The network restoring the excitation signal is trained such that there is no mismatch between the excitation signal and the envelope. By this, we achieve better perceptual quality at lower computational complexity.
Most viewed
-
PublicationBarkhausen-Effect and Eddy Current Testing for the Characterization of the Microstructure and Residual Stress States with Local Resolution( 1997)The IZFP has developed a microscope based on micromagnetic and eddy-current techniques. By using miniaturized inductive transducers with some tenths of a µm slit width, speciments are scanned in down to one µm increments. Concering the micromagnetic techniques, the magnetic Barkhausen noise is measured, which is mainly sensitive to microstructure and residual stress states. The applied eddy-current technqiue is sensitive to microscopic defects, local changes in permeability and conductivity.
-
-
PublicationComputer-aided cutting-edge research on history for home edutainment and exploratory learning( 2012)Webbles are the most recent form of IntelligentPad. Webbles are objects in a browser window that allow for direct manipulation by drag and drop. One may pick up any Webble and move it over any other one for operational combination. The new Webble is plugged into the previous one and data between them flow through predefined slots. Human users may freely reconfigure the slot connections of Webbles as necessary. Within the authors' adaptive interactive dynamic atlas project, historians have the historical data literally at their fingertips. Historical data have some visual appearance on the screen and may be directly manipulated by actions such as drag and drop. The professional research interface is accessible via any Web browser and, thus, allows for participation of a wide audience. Contemporary technologies are bringing science to private homes where families may playfully explore history in manifold ways.
-