Zobrazeno 1 - 10
of 15
pro vyhledávání: '"Franz Pernkopf"'
Publikováno v:
Data in Brief, Vol 53, Iss , Pp 110229- (2024)
Obtaining real-world multi-channel speech recordings is expensive and time-consuming. Therefore, multi-channel recordings are often artificially generated by convolving existing monaural speech recordings with simulated Room Impulse Responses (RIRs)
Externí odkaz:
https://doaj.org/article/d781fc1d53e04858b18d65f2e675dea4
Autor:
Christoph Obermair, Thomas Cartier-Michaud, Andrea Apollonio, William Millar, Lukas Felsberger, Lorenz Fischl, Holger Severin Bovbjerg, Daniel Wollmann, Walter Wuensch, Nuria Catalan-Lasheras, Marçà Boronat, Franz Pernkopf, Graeme Burt
Publikováno v:
Physical Review Accelerators and Beams, Vol 25, Iss 10, p 104601 (2022)
The occurrence of vacuum arcs or radio frequency (rf) breakdowns is one of the most prevalent factors limiting the high-gradient performance of normal conducting rf cavities in particle accelerators. In this paper, we search for the existence of prev
Externí odkaz:
https://doaj.org/article/0b4eb43ea42342609d631e3fc24be917
Autor:
Magdalena Krieber, Katrin D Bartl-Pokorny, Florian B Pokorny, Dajie Zhang, Karin Landerl, Christof Körner, Franz Pernkopf, Thomas Pock, Christa Einspieler, Peter B Marschik
Publikováno v:
PLoS ONE, Vol 12, Iss 2, p e0170986 (2017)
The present study aimed to define differences between silent and oral reading with respect to spatial and temporal eye movement parameters. Eye movements of 22 German-speaking adolescents (14 females; mean age = 13;6 years;months) were recorded while
Externí odkaz:
https://doaj.org/article/a9c99e8745bc42338eb94a0875a3f8be
Autor:
Philipp Aichinger, Franz Pernkopf, Imme Roesner, Berit Schneider-Stickler, Jean Schoentgen, Martin Hagmüller
Publikováno v:
Biomedical Signal Processing and Control. 37:69-81
Background and objectives Fundamental frequency ( f o ) extraction in disordered voices is a prerequisite for many types of clinical analyses. Special attention must be paid if multiple oscillators with different f o s are active simultaneously. Two
Autor:
Nikolaus Mutsam, Franz Pernkopf
Publikováno v:
Pattern Recognition Letters. 77:14-20
A margin-based discriminative training method for hidden Markov models is proposed.The margin criterion is maximized using the extended Baum-Welch algorithm.Classification rate for time series data is on par with state of the art methods. Discriminat
Autor:
Franz Pernkopf, Horst Olschewski, Freyja-Maria Smolle-Jüttner, Stefan Scheidl, Elmar Messner, Paul Swatek, Melanie Fediuk
Publikováno v:
Computers in Biology and Medicine. 122:103831
In this paper, we present an approach for multi-channel lung sound classification, exploiting spectral, temporal and spatial information. In particular, we propose a frame-wise classification framework to process full breathing cycles of multi-channe
Autor:
Michael Wohlmayr, Franz Pernkopf
Publikováno v:
Pattern Recognition
The margin criterion for parameter learning in graphical models gained significant impact over the last years. We use the maximum margin score for discriminatively optimizing the structure of Bayesian network classifiers. Furthermore, greedy hill-cli
Autor:
Franz Pernkopf, Robert Peharz
Publikováno v:
Neurocomputing
Although nonnegative matrix factorization (NMF) favors a sparse and part-based representation of nonnegative data, there is no guarantee for this behavior. Several authors proposed NMF methods which enforce sparseness by constraining or penalizing th
Autor:
Jeremy Jancsary, Christina Drexel, Alexandra Klein, Franz Pernkopf, Johannes Matiasek, Stefan Petrik, Gernot Kubin, Leo Fessler, Harald Trost
Publikováno v:
Computer Speech & Language. 25:363-385
Automatic speech recognition (ASR) has become a valuable tool in large document production environments like medical dictation. While manual post-processing is still needed for correcting speech recognition errors and for creating documents which adh
Publikováno v:
Speech Communication. 51:151-166
We present an approach to broad phonetic classification, defined as mapping acoustic speech frames into broad (or clustered) phonetic categories. Our categories consist of silence, general voiced, general unvoiced, mixed sounds, voiced closure, and p