Zobrazeno 1 - 10
of 6 567
pro vyhledávání: '"Schuller, P"'
Curriculum learning (CL) describes a machine learning training strategy in which samples are gradually introduced into the training process based on their difficulty. Despite a partially contradictory body of evidence in the literature, CL finds popu
Externí odkaz:
http://arxiv.org/abs/2411.00973
Audio-based kinship verification (AKV) is important in many domains, such as home security monitoring, forensic identification, and social network analysis. A key challenge in the task arises from differences in age across samples from different indi
Externí odkaz:
http://arxiv.org/abs/2410.11120
The increasing success of audio foundation models across various tasks has led to a growing need for improved interpretability to understand their intricate decision-making processes better. Existing methods primarily focus on explaining these models
Externí odkaz:
http://arxiv.org/abs/2410.07530
Autor:
Körber, Nikolai, Kromer, Eduard, Siebert, Andreas, Hauke, Sascha, Mueller-Gritschneder, Daniel, Schuller, Björn
We introduce PerCo (SD), a perceptual image compression method based on Stable Diffusion v2.1, targeting the ultra-low bit range. PerCo (SD) serves as an open and competitive alternative to the state-of-the-art method PerCo, which relies on a proprie
Externí odkaz:
http://arxiv.org/abs/2409.20255
Autor:
Ye, Zhengxin Joseph, Schuller, Bjoern
Earnings release is a key economic event in the financial markets and crucial for predicting stock movements. Earnings data gives a glimpse into how a company is doing financially and can hint at where its stock might go next. However, the irregulari
Externí odkaz:
http://arxiv.org/abs/2409.17392
Autor:
Herron, Connor W., Schuller, Robert, Beiter, Benjamin C., Griffin, Robert J., Leonessa, Alexander, Englsberger, Johannes
In this work, the Divergent Component of Motion (DCM) method is expanded to include angular coordinates for the first time. This work introduces the idea of spatial DCM, which adds an angular objective to the existing linear DCM theory. To incorporat
Externí odkaz:
http://arxiv.org/abs/2409.12796
Autor:
Schuller, Björn, Mallol-Ragolta, Adria, Almansa, Alejandro Peña, Tsangko, Iosif, Amin, Mostafa M., Semertzidou, Anastasia, Christ, Lukas, Amiriparian, Shahin
The dawn of Foundation Models has on the one hand revolutionised a wide range of research problems, and, on the other hand, democratised the access and use of AI-based tools by the general public. We even observe an incursion of these models into dis
Externí odkaz:
http://arxiv.org/abs/2409.08907
While current emotional text-to-speech (TTS) systems can generate highly intelligible emotional speech, achieving fine control over emotion rendering of the output speech still remains a significant challenge. In this paper, we introduce ParaEVITS, a
Externí odkaz:
http://arxiv.org/abs/2409.06451
Foundational Large Language Models (LLMs) have changed the way we perceive technology. They have been shown to excel in tasks ranging from poem writing and coding to essay generation and puzzle solving. With the incorporation of image generation capa
Externí odkaz:
http://arxiv.org/abs/2409.00105
Autor:
Kounadis-Bastian, Dionyssos, Schrüfer, Oliver, Derington, Anna, Wierstorf, Hagen, Eyben, Florian, Burkhardt, Felix, Schuller, Björn
Speech Emotion Recognition (SER) needs high computational resources to overcome the challenge of substantial annotator disagreement. Today SER is shifting towards dimensional annotations of arousal, dominance, and valence (A/D/V). Universal metrics a
Externí odkaz:
http://arxiv.org/abs/2408.13920