Searched for: subject%3A%22automatically%22
(1 - 20 of 24)

Pages

document
Wilschut, Thomas (author), Sense, Florian (author), Scharenborg, O.E. (author), van Rijn, Hedderik (author)
Cognitive models of memory retrieval aim to describe human learning and forgetting over time. Such models have been successfully applied in digital systems that aid in memorizing information by adapting to the needs of individual learners. The memory models used in these systems typically measure the accuracy and latency of typed retrieval...
conference paper 2023
document
Gissurarson, Matthías Páll (author), Applis, L.H. (author), Panichella, A. (author), van Deursen, A. (author), Sands, David (author)
Automatic program repair (APR) regularly faces the challenge of overfitting patches — patches that pass the test suite, but do not actually address the problems when evaluated manually. Currently, overfit detection requires manual inspection or an oracle making quality control of APR an expensive task. With this work, we want to introduce...
conference paper 2022
document
Vlaskin, A. (author), Sun, Junzi (author), Hoekstra, J.M. (author)
The consumer drone sector is expected to grow rapidly in the coming decades. In Europe alone, some predictions show as many as seven million drones will be flying by 2050. This poses a challenge for surveillance. In this paper, we study an Automatic Dependent Surveillance system concept similar to the one for current aircraft surveillance, which...
conference paper 2022
document
Izadi, M. (author), Gismondi, Roberta (author), Gousios, G. (author)
Code completion is an essential feature of IDEs, yet current auto-completers are restricted to either grammar-based or NLP-based single token completions. Both approaches have significant draw-backs: grammar-based autocompletion is restricted in dynamically-typed language environments, whereas NLP-based autocompleters struggle to understand...
conference paper 2022
document
Chen, Hang (author), Zhou, Hengshun (author), Du, Jun (author), Lee, Chin-Hui (author), Chen, Jingdong (author), Watanabe, Shinji (author), Siniscalchi, Sabato Marco (author), Scharenborg, O.E. (author), Liu, Di-Yuan (author)
In this paper we discuss the rational of the Multi-model Information based Speech Processing (MISP) Challenge, and provide a detailed description of the data recorded, the two evaluation tasks and the corresponding baselines, followed by a summary of submitted systems and evaluation results. The MISP Challenge aims at tack-ling speech processing...
conference paper 2022
document
Oncescu, Andreea Maria (author), Cicirello, A. (author)
Health Monitoring strategies rely on tracking the health status of critical engineering structures (Structural Health Monitoring) and of people (monitoring of medical conditions) to detect anomalies in the measurements and make inferences on the health condition for supporting decisions on preventive actions to be implemented to restore...
conference paper 2021
document
Pallotta, Luca (author), Cauli, Michela (author), Clemente, Carmine (author), Fioranelli, F. (author), Giunta, Gaetano (author), Farina, Alfonso (author)
In this paper a method capable of automatically classify radar signals of human hand-gestures exploiting the micro-Doppler signature is designed. In particular, the methodology focuses on the extraction of the Chebyshev moments from the cadence velocity diagram (CVD) of each recorded signal. The algorithm benefits from interesting properties of...
conference paper 2021
document
Feng, S. (author), Żelasko, Piotr (author), Moro-Velázquez, Laureano (author), Abavisani, Ali (author), Hasegawa-Johnson, Mark (author), Scharenborg, O.E. (author), Dehak, Najim (author)
The idea of combining multiple languages’ recordings to train a single automatic speech recognition (ASR) model brings the promise of the emergence of universal speech representation. Recently, a Transformer encoder-decoder model has been shown to leverage multilingual data well in IPA transcriptions of languages presented during training....
conference paper 2021
document
Dudzik, B.J.W. (author), Jansen, Michel Pierre (author), Burger, Franziska (author), Kaptein, F.C.A. (author), Broekens, D.J. (author), Heylen, Dirk K.J. (author), Hung, H.S. (author), Neerincx, M.A. (author), Truong, Khiet P. (author)
An important aspect of human emotion perception is the use of contextual information to understand others' feelings even in situations where their behavior is not very expressive or has an emotionally ambiguous meaning. For technology to successfully detect affect, it must mimic this human ability when analyzing audiovisual input. Databases...
conference paper 2019
document
Moro-Velazquez, Laureano (author), Cho, JaeJin (author), Watanabe, Shinji (author), Hasegawa-Johnson, Mark A. (author), Scharenborg, O.E. (author), Kim, Heejin (author), Dehak, Najim (author)
Parkinson’s Disease (PD) affects motor capabilities of patients, who in some cases need to use human-computer assistive technologies to regain independence. The objective of this work is to study in detail the differences in error patterns from state-of-the-art Automatic Speech Recognition (ASR) systems on speech from people with and without PD....
conference paper 2019
document
Du, T. (author), Turrin, M. (author), Jansen, S.C. (author), van den Dobbelsteen, A.A.J.F. (author), Biloria, N.M. (author)
conference paper 2018
document
Chen, G. (author), Yang, J. (author), Hauff, C. (author), Houben, G.J.P.M. (author)
We present LearningQ, a challenging educational question generation dataset containing over 230K document-question pairs. It includes 7K instructor-designed questions assessing knowledge concepts being taught and 223K learner-generated questions seeking in-depth understanding of the taught concepts. We show that, compared to existing datasets...
conference paper 2018
document
Scharenborg, O.E. (author), Ebel, Patrick (author), Ciannella, Francesco (author), Hasegawa-Johnson, Mark (author), Dehak, Najim (author)
For many languages in the world, not enough (annotated) speech data is available to train an ASR system. Recently, we proposed a cross-language method for training an ASR system using linguistic knowledge and semi-supervised training. Here, we apply this approach to the low-resource language Mboshi. Using an ASR system trained on Dutch, Mboshi...
conference paper 2018
document
Hollstein, Frank (author), Wohllebe, Markus (author), Herling, Martin (author), Cacho, Iñigo (author), Arnaiz, Sixto (author)
A basic step to achieve a holistic recycling process for Construction and Demolition Waste (C&DW) is a relevant improvement in (automatic) sorting technologies. Hyperspectral- Imaging (HSI) is an outstanding candidate to support the process. Currently the biggest challenges with regard to C&DW detection cover the need of overlapping VIS, NIR and...
conference paper 2017
document
Knoop, V.L. (author), Keyvan-Ekbatani, M. (author), de Baat, Marco (author), Taale, Henk (author), Hoogendoorn, S.P. (author)
Freeways form an important part of the road network. Drivers’ behavior can be split in longitudinal (acceleration and deceleration) and lateral behavior (lane changing). The combination of these two behaviors on freeways play a key role in traffic operations. This paper tries to describe the driving behavior, emphasizing the relation between the...
conference paper 2017
document
Roy, S. (author), Hermans, F.F.J. (author), Aivaloglou, E.A. (author), Winter, J. (author), van Deursen, A. (author)
Spreadsheets are popular end-user computing applications and one reason behind their popularity is that they offer a large degree of freedom to their users regarding the way they can structure their data. However, this flexibility also makes spreadsheets difficult to understand. Textual documentation can address this issue, yet for supporting...
conference paper 2016
document
Scholte, K. (author), Rothkrantz, L.J.M. (author)
Many services provide weather forecasts, including severe weather alerts for the marine. It proves that many ships neglect the warnings because they expect to be able to handle the bad weather conditions. In order to identify possible unsafe situations the Coast Guard needs to observe marine vessel traffic 24 hours, 7 days a week. In this paper...
conference paper 2014
document
Heydra, C.G. (author), Jansen, R.J. (author), Van Egmond, R. (author)
This paper focuses on the design of an auditory signal for the Automatic Number Plate Recognition system of Dutch national police. The auditory signal is designed to alert police officers of suspicious cars in their proximity, communicating priority level and location of the suspicious car and taking into account the auditory environment of the...
conference paper 2014
document
Kauko, T.J. (author)
Given the pivotal role of the housing bubble in the subsequent credit crunch, the following question may be raised: could the global financial crisis have been moderated if prude property valuations had been made at the time of issuing bank loans, and if governments and institutions had been concerned about raising the quality of market...
conference paper 2009
document
Ten Holt, G.A. (author), Arendsen, J. (author), De Ridder, H. (author), Van Doorn, A.J. (author), Reinders, M.J.T. (author), Hendriks, E.A. (author)
Current automatic sign language recognition (ASLR) seldom uses perceptual knowledge about the recognition of sign language. Using such knowledge can improve ASLR because it can give an indication which elements or phases of a sign are important for its meaning. Also, the current generation of data-driven ASLR methods has shortcomings which may...
conference paper 2009
Searched for: subject%3A%22automatically%22
(1 - 20 of 24)

Pages