About
33
Publications
3,961
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
389
Citations
Citations since 2017
Introduction
Jeska Buhmann is working as a postdoctoral researcher at CLiPS (University of Antwerp). She obtained her master's degree at the Radboud University of Nijmegen, in the field of Language, Speech & Informatics, specialising in the prediction of intonation for single sentences with recurrent neural networks. In the past, she worked at IPEM (Ghent University), focusing on the interaction between human walking or running and music, and on musical interaction in general. At CLiPS her focus is on language interaction between humans and conversational agents.
For more info:
www.linkedin.com/in/jeska-buhmann-21527941
Publications
Publications (33)
Background:
Chatbots are increasingly used to support COVID-19 vaccination programs. Their persuasiveness may depend on the conversation-related context.
Objective:
To investigate the moderating role of the conversation quality and chatbot expertise cues in the effects of expressing empathy/autonomy-support by COVID-19 vaccine chatbots.
Methods...
Automatic evaluation of open-domain dialogs remains an unsolved problem. Moreover, existing methods do not correlate strongly with human annotations. This paper presents a new automated evaluation method using follow-ups: we measure the probability that a language model will continue the conversation with a fixed set of follow-ups (e.g., not really...
BACKGROUND
Chatbots are increasingly used to support COVID-19 vaccination programs. Their persuasiveness may depend on the conversation-related context.
OBJECTIVE
This study aims to investigate the moderating role of the conversation quality and chatbot expertise cues in the effects of expressing empathy/autonomy support using COVID-19 vaccination...
Knowledge Grounded Conversation Models (KGCM) are usually based on a selection/retrieval module and a generation module, trained separately or simultaneously, with or without having access to a gold knowledge option. With the introduction of large pre-trained generative models, the selection and generation part have become more and more entangled,...
In this paper, we present the first multilingual FAQ dataset publicly available. We collected around 6M FAQ pairs from the web, in 21 different languages. Although this is significantly larger than existing FAQ retrieval datasets, it comes with its own challenges: duplication of content and uneven distribution of topics. We adopt a similar setup as...
Knowledgeable FAQ chatbots are a valuable resource to any organization. Unlike traditional call centers or FAQ web pages, they provide instant responses and are always available. Our experience running a COVID19 chatbot revealed the lack of resources available for FAQ answering in non-English languages. While powerful and efficient retrieval-based...
Matching exercise behavior to musical beats has been shown to favorably affect repetitive endurance tasks. In this study, our aim was to explore the role of spontaneous versus instructed entrainment, focusing on self-paced exercise of healthy, recreational runners. For three 4-min running tasks, 33 recreational participants were either running in s...
Transformers have shown incredible capabilities for conversation modeling, however, they store factual knowledge in their learned parameters, which is costly to update with new knowledge since it requires retraining. Models trained before the Coronavirus pandemic do not know about COVID-19. In this paper, we investigate how a BART model can be adap...
Music is believed to work as a bio-social tool enabling groups of people to establish joint action and group bonding experiences. However, little is known about the quality of the group members’ interaction needed to bring about these effects. To investigate the role of interaction quality, and its effect on joint action and bonding experience, we...
The BeatHealth system aims to develop a mobile music listening device synchronizing in a personalized way music and movement, and dedicated to improving the kinematics of the runner. Thanks to inertial units connected to a smartphone, the runner's steps are detected in real time by the mobile application. A dedicated algorithm adapts the pulsation...
The use of music and specifically tempo-matched music has been shown to affect running performance. But can we maximize the synchronization of movements to music and does maximum synchronization influence kinematics and motivation? In this study, we explore the effect of different types of music-to-movement alignment strategies on phase coherence,...
Background: Interdisciplinary work is needed for scientific progress, and with this review, our interest is in the scientific progress toward understanding the underlying mechanisms of auditory-motor coupling, and how this can be applied to gait rehabilitation. Specifically we look into the process of entrainment and synchronization; where entrainm...
The use of music in the fields of sport and rehabilitation has been explored in several ways. Mostly, these studies have dealt with the effect of different types or genres of music and the difference between using synchronous or asynchronous music. Within the studies on synchronous music there is some discrepancy as to what is considered to be sync...
In de sport en motorische rehabilitatie is het zeer belangrijk om fysiologische processen en fysieke bewegingen optimaal te reguleren en controleren. Real-time auditieve feedback van zulke fysiologische en fysieke parameters door middel van geluiden (ook wel "sonificatie" genoemd) blijkt hier uitermate geschikt voor te zijn. In dergelijke biofeedba...
In the domain of sports and motor rehabilitation, it is of major importance to regulate and control physiological processes and physical motion in most optimal ways. For that purpose, real-time auditory feedback of physiological and physical information based on sound signals, often termed " sonification, " has been proven particularly useful. Howe...
A regular rhythm in music is a strong driver for establishing a synchronized human rhythm. Typically human rhythm tends to go along with the musical rhythm in such a way that a salient feature of the human rhythm matches the timing of a salient feature of the musical rhythm. But what are the underlying mechanisms behind music-movement synchronizati...
The expressive features of music can influence the velocity of walking. So far, studies used instructed (and intended) synchronization. But is this velocity effect still present with non-instructed (spontaneous) synchronization? To figure that out, participants were instructed to walk in their own comfort tempo on an indoor track, first in silence...
List of music that was selected and used in this study.
The table contains the song ID, average BPM, artist and song title.
(XLSX)
Since accumulating evidence suggests that step rate is strongly associated with running-related injuries, it is important for runners to exercise at an appropriate running cadence. As music tempo has been shown to be capable of impacting exercise performance of repetitive endurance activities, it might also serve as a means to (re)shape running cad...
This paper describes experiments concerning the prediction of a good intonation for the synthesis of structured documents. The paper extends our previous research in four important aspects: (i) models are trained and evaluated on read text material (no isolated sentences), (ii) the intonation model is evaluated while fully inte- grated in the entir...
Abstract This paper first describes the aims of the prosodic annotation for (part of) the Spoken Dutch Corpus (Corpus Gesproken Nederlands, CGN), and the procedures that are currently being developed to produce the annotation. It further reports on a pilot study that was run to estimate the costs and the attainable quality (in terms of inter-transc...
