Zobrazeno 1 - 10
of 358
pro vyhledávání: '"Schultz Tanja"'
Speech is a rich biomarker that encodes substantial information about the health of a speaker, and thus it has been proposed for the detection of numerous diseases, achieving promising results. However, questions remain about what the models trained
Externí odkaz:
http://arxiv.org/abs/2409.10230
In the study of auditory attention, it has been revealed that there exists a robust correlation between attended speech and elicited neural responses, measurable through electroencephalography (EEG). Therefore, it is possible to use the attention inf
Externí odkaz:
http://arxiv.org/abs/2409.02489
Autor:
Reich, Daniel, Schultz, Tanja
Visual Grounding (VG) in VQA refers to a model's proclivity to infer answers based on question-relevant image regions. Conceptually, VG identifies as an axiomatic requirement of the VQA task. In practice, however, DNN-based VQA models are notorious f
Externí odkaz:
http://arxiv.org/abs/2406.18253
Autor:
Chang, Yi, Ren, Zhao, Zhao, Zhonghao, Nguyen, Thanh Tam, Qian, Kun, Schultz, Tanja, Schuller, Björn W.
Speech emotion recognition (SER) plays a crucial role in human-computer interaction. The emergence of edge devices in the Internet of Things (IoT) presents challenges in constructing intricate deep learning models due to constraints in memory and com
Externí odkaz:
http://arxiv.org/abs/2406.15119
Electromyography-to-Speech (ETS) conversion has demonstrated its potential for silent speech interfaces by generating audible speech from Electromyography (EMG) signals during silent articulations. ETS models usually consist of an EMG encoder which c
Externí odkaz:
http://arxiv.org/abs/2405.08021
Autor:
Chang, Yi, Ren, Zhao, Zhang, Zixing, Jing, Xin, Qian, Kun, Shao, Xi, Hu, Bin, Schultz, Tanja, Schuller, Björn W.
Speech contains rich information on the emotions of humans, and Speech Emotion Recognition (SER) has been an important topic in the area of human-computer interaction. The robustness of SER models is crucial, particularly in privacy-sensitive and rel
Externí odkaz:
http://arxiv.org/abs/2402.01227
Autor:
Reich, Daniel, Schultz, Tanja
Visual Grounding (VG) methods in Visual Question Answering (VQA) attempt to improve VQA performance by strengthening a model's reliance on question-relevant visual information. The presence of such relevant information in the visual input is typicall
Externí odkaz:
http://arxiv.org/abs/2401.07803
Autor:
Doneit Wolfgang, Lohse Jana, Glesing Kristina, Simon Clarissa, Fischer Monika, Depner Anamaria, Kruse Andreas, Franz Ingo, Schultz Tanja, Putze Felix, Schulze Timo, Engels Marc Aurel, Gaerte Philipp, Bothe Dietmar, Ziegler Christof, Maucher Irene, Ricken Michael, Dimitrov Todor, Herzig Joachim, Bernardin Keni, Gehrig Tobias, Mikut Ralf
Publikováno v:
Current Directions in Biomedical Engineering, Vol 3, Iss 2, Pp 735-738 (2017)
In the project I-CARE a technical system for tablet devices is developed that captures the personal needs and skills of people with dementia. The system provides activation content such as music videos, biographical photographs and quizzes on various
Externí odkaz:
https://doaj.org/article/338d53376e224c9cb2b949ba6acbb5f4
Humans possess the remarkable ability to selectively attend to a single speaker amidst competing voices and background noise, known as selective auditory attention. Recent studies in auditory neuroscience indicate a strong correlation between the att
Externí odkaz:
http://arxiv.org/abs/2307.14303
Publikováno v:
EMNLP 2023 Findings
Metrics for Visual Grounding (VG) in Visual Question Answering (VQA) systems primarily aim to measure a system's reliance on relevant parts of the image when inferring an answer to the given question. Lack of VG has been a common problem among state-
Externí odkaz:
http://arxiv.org/abs/2305.15015