Dirk Van Compernolle

Learn More
SPRAAK is a toolkit intended for • Speech recognition research • Development of speech recognition applications (niche markets) Licensing • Free source code license for academic usage (open source concept) • Commercial license Development History • Derived from HMM75 that has a >15 year development history at KULeuven • Modernization & Conversion was(More)
All rights reserved. No part of this publication may be reproduced in any form by print, photoprint, microfilm or any other means without written permission from the publisher. Summary Over the past 25 years, research in automatic speech recognition has been dominated by systems based on hidden Markov models (HMMs). In this dissertation, an example based(More)
Exemplar based recognition systems are characterized by the fact that, instead of abstracting large amounts of data into compact models , they store the observed data enriched with some annotations and infer on-the-fly from the data by finding those exemplars that resemble the input speech best. One advantage of exemplar based systems is that next to(More)
Direct electrical stimulation of the auditory nerve can be used to restore some degree of hearing to the profoundly deaf. Percepts due to electrical stimulation have characteristics corresponding approximately to the acoustic percepts of loudness, pitch, and timbre. To encode speech as a pattern of electrical stimulation, it is necessary to determine the(More)
The dominant acoustic modeling methodology based on Hidden Markov Models is known to have certain weaknesses. Partial solutions to these flaws have been presented, but the fundamental problem remains: compression of the data to a compact HMM discards useful information such as time dependencies and speaker information. In this paper, we look at pure example(More)
In pursuance of better performance, current speech recognition systems tend to use more and more complicated models for both the acoustic and the language component. Crossword context dependent phone models and long-span statistical language models are now widely used. In this paper, we present a memory-efficient search topology that enables the use of such(More)