document

Identification of Neolithic Circular Enclosures through Aerial Imagery

MENG, YUQI (author)

Traditionally, archaeological investigations, especially archaeological remains detection, mostly depend on human observation. In order to find the objects in large areas, a lot of fieldwork has to be done and it takes a long time for archaeologists to travel around. Nowadays, the development of LIDAR provides accurate 3D geometric information,...

master thesis 2023

document

Physics-informed Data Augmentation for Human Radar Signatures

Focante, Edoardo (author)

In recent years, neural networks (NNs) have seen a surge in popularity due to their ability to model complex patterns and relationships in data. One of the challenges of using NNs is the requirement for large amounts of labelled data to train the model effectively. In many real-world applications such as radar, labelled data may be scarce due to...

master thesis 2023

document

Learning from Few Demonstrations with Frame-Weighted Motion Generation

Sun, Jianyong (author)

Learning from Demonstration (LfD) aims to learn versatile skills from human demonstrations. The field has been gaining popularity since it facilitates transferring knowledge to robots without requiring much expert knowledge. During task executions, the robot motion is usually influenced by constraints imposed by environments. In light of this,...

master thesis 2022

document

Enriching Diversity of Synthetic Images for Person Detection

POLYA RAMESH, CHINMAY (author)

Camera-based patient monitoring is undergoing rapid adoption in the healthcare sector with the recent COVID-19 pandemic acting as a catalyst. It offers round-the-clock monitoring of patients in clinical units (e.g. ICUs, ORs), or at their homes through installed cameras, enabling timely, pre-emptive care. These are powered by Computer Vision...

master thesis 2022

document

Bias Mitigation Against Non-native Speakers in Dutch ASR

Zhang, Yixuan (author)

One of the most important problems that needs tackling for wide deployment of Automatic Speech Recognition (ASR) is the bias in ASR, i.e., ASRs tend to generate more accurate predictions for certain speaker groups while making more errors on speech from others. In this thesis, we aim to reduce bias against non-native speakers of Dutch compared...

master thesis 2022

document

Improving ASR performance on Jasmin Flemish Dutch data by performing frequency perturbation

Sweijen, Neal (author)

ASR (automatic speech recognition) systems are used widely in our current day and age. However, for a technology that is used so much in our daily life it contains a lot of bias. This means that not all people can use it equally, people with a different gender, age and dialect will all see different results. The goal of this paper is to reduce...

bachelor thesis 2022

document

Improving Northern Regional Dutch Speech Recognition by Adapting Perturbation-based Data Augmentation

Zhlebinkov, Nikolay (author)

Automatic speech recognition (ASR) does not perform equally well on every speaker. There is bias against many attributes, including accent. To train Dutch ASR, there exists CGN(Corpus Gesproken Nederlands) and as an extension, the JASMIN corpus with annotated accented data. This paper focuses on improving ASR performance for NRAD (Northern...

bachelor thesis 2022

document

From Feature Selection to Data Augmentation: the ADA Algorithm

Cruset Pla, Eduard (author)

The democratization of data science, and in particular of the machine learning pipeline, has focused on the automation of model selection, feature processing, and hyperparameter tuning. Nevertheless, the need for high-quality data for increased performance has sparked interest in the inclusion of data augmentation in these automatic machine...

bachelor thesis 2022

document

Evaluating the Use of Pitch Shifting to Improve Automatic Speech Recognition Performance on Southern Dutch Accents

Mešić, Amar (author)

Building Automatic Speech Recognizers (ASRs) has been a challenge in languages with insufficiently sized corpora or data sets. A further large issue in language corpora is biases against regionally accented speech and other speaker attributes. There are some techniques to improve ASR performance and reduce biases in these corpora, known as data...

bachelor thesis 2022

document

Constructing and Evaluating Complex Event-based Datasets for Increasing Performance of Instance Segmentation Models

Manolache, Alexandru-Dragos (author)

Event-based cameras represent a new alternative to traditional frame based sensors, with advantages in lower output bandwidth, lower latency and higher dynamic range, thanks to their independent, asynchronous pixels. These advantages prompted the development of computer vision methods on event data in the last decade, however event-based...

bachelor thesis 2022

document

Automatic feature augmentation ranking: XGBoost

Neut, Oliver (author)

Automatic machine learning is a subfield of machine learning that automates the common procedures faced in predictive tasks. The problem of one such procedure is automatic data augmentation, where one desires to enrich the existing data to increase model performance. In relational data repositories, the data is stored in normal form. This causes...

bachelor thesis 2022

document

Mitigating bias against non-native accents

Zhang, Yuanyuan (author)

Automatic Speech Recognition (ASR) systems have seen substantial improvements in the past decade; however, not for all speaker groups. Recent research shows that bias exists against different types of speech, including non-native accents, in state-of-the-art (SOTA) ASR systems. To attain inclusive speech recognition, i.e., ASR for everyone...

master thesis 2022

document

Federated learning from non-iid data: Improving accuracy through data-augmentation and communication efficiency

Cornelis, Izaak (author)

Federated learning allows multiple parties to collaboratively develop a deep learning model, without sharing private data. Models can be generated from the most up-to-date data while taking unique and not publicly available data into account. However, the distributed nature of federated learning causes problems too, and clients are not...

master thesis 2022

document

Audio-Visual Speech Recognition in MISP2021 Challenge: Dataset Release and Deep Analysis

Chen, Hang (author), Du, Jun (author), Dai, Yusheng (author), Lee, Chin Hui (author), Siniscalchi, Sabato Marco (author), Watanabe, Shinji (author), Scharenborg, O.E. (author), Chen, Jingdong (author), Yin, Bao Cai (author), Pan, Jia (author)

In this paper, we present the updated Audio-Visual Speech Recognition (AVSR) corpus of MISP2021 challenge, a large-scale audio-visual Chinese conversational corpus consisting of 141h audio and video data collected by far/middle/near microphones and far/middle cameras in 34 real-home TV rooms. To our best knowledge, our corpus is the first...

journal article 2022

document

Mitigating bias against non-native accents

Zhang, Y. (author), Zhang, Yixuan (author), Halpern, B.M. (author), Patel, T.B. (author), Scharenborg, O.E. (author)

Automatic speech recognition (ASR) systems have seen substantial improvements in the past decade; however, not for all speaker groups. Recent research shows that bias exists against different types of speech, including non-native accents, in state-of-the-art (SOTA) ASR systems. To attain inclusive speech recognition, i.e., ASR for everyone...

journal article 2022

document

Supervised Contrastive Learning Approach for Contextual Ranking

Anand, Abhijit (author), Leonhardt, Jurek (author), Rudra, Koustav (author), Anand, A. (author)

Contextual ranking models have delivered impressive performance improvements over classical models in the document ranking task. However, these highly over-parameterized models tend to be data-hungry and require large amounts of data even for fine tuning. This paper proposes a simple yet effective method to improve ranking performance on...

conference paper 2022

document

Audio-Visual Wake Word Spotting in MISP2021 Challenge: Dataset Release and Deep Analysis

Zhou, Hengshun (author), Du, Jun (author), Zou, Gongzhen (author), Nian, Zhaoxu (author), Lee, Chin Hui (author), Siniscalchi, Sabato Marco (author), Watanabe, Shinji (author), Scharenborg, O.E. (author), Chen, Jingdong (author)

In this paper, we describe and release publicly the audio-visual wake word spotting (WWS) database in the MISP2021 Challenge, which covers a range of scenarios of audio and video data collected by near-, mid-, and far-field microphone arrays, and cameras, to create a shared and publicly available database for WWS. The database and the code ...

journal article 2022

document

Fake It Till You Make It: Data Augmentation Using Generative Adversarial Networks for All the Crypto You Need on Small Devices

Mukhtar, Naila (author), Batina, Lejla (author), Picek, S. (author), Kong, Yinan (author)

Deep learning-based side-channel analysis performance heavily depends on the dataset size and the number of instances in each target class. Both small and imbalanced datasets might lead to unsuccessful side-channel attacks. The attack performance can be improved by generating traces synthetically from the obtained data instances instead of...

conference paper 2022

document

Domain Adaptation for Rare Classes Augmented with Synthetic Samples

Das, Tuhin (author)

To alleviate lower classification performance on rare classes in imbalanced datasets, a possible solution is to augment the underrepresented classes with synthetic samples. Domain adaptation can be incorporated in a classifier to decrease the domain discrepancy between real and synthetic samples. While domain adaptation is...

bachelor thesis 2021

document

Data Augmentation Techniques using Generative Adversarial Neural Networks on Side Channel Analysis

Vlogiaris, Achilleas (author)

Side-channel Attacks can be performed in various ways by measuring the power consumption, the electromagnetic emission, or even by measuring an algorithm's execution time on the targeted device. More or less sophisticated methods can be used to utilize this information in order to perform a Side-channel attack, more specifically by training...

master thesis 2021