arXiv subjects

Christoph Hoog Antink

Publications and source records attributed to Christoph Hoog Antink.

7 recordsLinked to original sources

arXiv2026

DNN-Based Frequency-Dependent Estimation of Speech, Music, and Noise Power in Acoustic Mixtures for Hearing-Aid Scene Analysis

Acoustic scene analysis is essential for adapting hearing-aid signal processing algorithms to the current listening environment. However, state-of-the-art (SOTA) systems typically rely on multiple independent estimators for tasks such as scene classification, Voice Activity Detection (VAD), or Signal-to-Noise Ratio estimation, which increases computational complexity and fails to exploit dependencies between related tasks. To address this problem, we propose a unified and interpretable acoustic scene representation by decomposing the observed mixture spectrum into speech, music, and noise power components. This is motivated by the typical listening targets of hearing-aid users. In particular, we estimate time- and frequency-dependent power proportions by a causal low-complexity Deep Neural Network, from which multiple downstream acoustic scene analysis measures can in principle be derived by simple post-processing. In this work, we validate the proposed representation using VAD as a representative downstream task and show performance comparable to a SOTA estimator while providing a substantially richer scene description.

eess.AS↗

arXiv2026

A Novel Binaural Cue Preservation Loss for DNN-Based Binaural Speech Enhancement

Binaural speech enhancement for hearing aids aims to reduce noise while preserving the interaural cues needed for spatial localization. Although deep neural network-based methods achieve strong noise reduction, they often distort the rela- tionship between the left and right signals. In this paper, we propose two novel binaural cue preservation losses. First, a binaural reconstruction error loss that directly penalizes masking-induced distortion in the relationship between the left and right spectra, providing a more direct measure of the binaural consistency than conventional separate interaural level differences (ILD) and interaural phase differences (IPD) errors as in prior work. Second, a binaural cue loss that jointly models ILD and IPD to better preserve the binaural structure. Experimental results show that both proposed losses maintain strong noise reduction performance and reduce masking- induced distortion compared to the state-of-the-art baseline cue loss, while the second proposed joint binaural cue loss also outperforms the baseline in ILD preservation.

eess.AS↗

arXiv2026

Task- and Metric-Specific Signal Quality Indices for Medical Time Series

Medical time series such as electrocardiograms (ECGs) and photoplethysmograms (PPGs) are frequently affected by measurement artifacts due to challenging acquisition environments, such as in ambulances and during routine daily activities. Since automated algorithms for analyzing such signals increasingly inform clinically relevant decisions, identifying signal segments on which these algorithms may produce unreliable outputs is of critical importance. Signal quality indices (SQIs) are commonly used for this purpose. However, most existing SQIs are task agnostic and do not account for the specific algorithm and performance metric used downstream. In this work, we formalize signal quality as a task- and metric-dependent concept and propose a perturbation-based SQI (pSQI) that aims to detect an algorithm's performance degradation on an input signal with respect to a metric. The pSQI is defined as the worst-case value of the performance metric under an additive, colored Gaussian noise perturbation with a lower-bounded signal-to-noise ratio. We introduce formal requirements for task- and metric-specific SQIs, including monotonicity of the metric in expectation and maximal separation under thresholding. Experiments on R-peak detection and atrial fibrillation classification benchmarks demonstrate that the proposed pSQI consistently outperforms existing feature- and deep learning-based SQIs in identifying unreliable inputs without requiring training.

eess.SP↗

arXiv2026

An AI dose engine for fast carbon ion treatment planning

Monte Carlo (MC) simulations provide gold-standard accuracy for carbon ion therapy dose calculations but are computationally intensive. Analytical pencil beam algorithms offer speed but reduced accuracy in heterogeneous tissues. We developed the first AI-based dose engine capable of predicting absorbed dose, the alpha and beta parameters for relative biological effectiveness (RBE)- weighted optimisation in carbon ion therapy, delivering MC-level accuracy with drastically reduced computation time. We extended the transformer-based DoTA model to predict absorbed dose (C-DoTA-d), alpha (C-DoTA-alpha), and beta (C-DoTA-beta), introducing a cross-attention mechanism for alpha and beta to combine dose and energy inputs. The training dataset consisted of ~70,000 pencil beams from 187 head-and-neck patients, with ground-truth values obtained using the GPU-accelerated MC toolkit FRED. Performance was evaluated on an independent test set using gamma pass rate (1%/1 mm), depth-dose, and isodose contour Dice coefficients. MC dropout-based uncertainty analysis was performed. Median gamma pass rates exceeded 98% for all predictions (99.76% for dose, 99.14% for alpha, and 98.74% for beta), with minima above 85% in the most heterogeneous anatomies. The Dice coefficient was 0.95 for 1% isodose contours, with slightly reduced agreement in high-gradient regions. Compared to MC FRED, inference was over 400x faster (0.032 s vs. 14 s per pencil beam) while maintaining accuracy. Uncertainty analysis showed high stability, with mean standard deviations below 0.5% for all models. C-DoTA achieves MC-quality predictions of absorbed dose and RBE model parameters in ~30 milliseconds per beam. Its speed and accuracy support online adaptive planning, paving the way for more effective carbon ion therapy workflows. Future work will expand to additional anatomical sites, beam geometries, and clinical beamlines.

physics.med-ph↗

arXiv2025

3D Blood Pulsation Maps

We present Pulse3DFace, the first dataset of its kind for estimating 3D blood pulsation maps. These maps can be used to develop models of dynamic facial blood pulsation, enabling the creation of synthetic video data to improve and validate remote pulse estimation methods via photoplethysmography imaging. Additionally, the dataset facilitates research into novel multi-view-based approaches for mitigating illumination effects in blood pulsation analysis. Pulse3DFace consists of raw videos from 15 subjects recorded at 30 Hz with an RGB camera from 23 viewpoints, blood pulse reference measurements, and facial 3D scans generated using monocular structure-from-motion techniques. It also includes processed 3D pulsation maps compatible with the texture space of the 3D head model FLAME. These maps provide signal-to-noise ratio, local pulse amplitude, phase information, and supplementary data. We offer a comprehensive evaluation of the dataset's illumination conditions, map consistency, and its ability to capture physiologically meaningful features in the facial and neck skin regions.

cs.CV↗

arXiv2023

Automatic Generation of Labeled Data for Video-Based Human Pose Analysis via NLP applied to YouTube Subtitles

With recent advancements in computer vision as well as machine learning (ML), video-based at-home exercise evaluation systems have become a popular topic of current research. However, performance depends heavily on the amount of available training data. Since labeled datasets specific to exercising are rare, we propose a method that makes use of the abundance of fitness videos available online. Specifically, we utilize the advantage that videos often not only show the exercises, but also provide language as an additional source of information. With push-ups as an example, we show that through the analysis of subtitle data using natural language processing (NLP), it is possible to create a labeled (irrelevant, relevant correct, relevant incorrect) dataset containing relevant information for pose analysis. In particular, we show that irrelevant clips ($n=332$) have significantly different joint visibility values compared to relevant clips ($n=298$). Inspecting cluster centroids also show different poses for the different classes.

cs.CV↗

arXiv2022

Signal-to-noise ratio is more important than sampling rate in beat-to-beat interval estimation from optical sensors

Photoplethysmographic Imaging (PPGI) allows the determination of pulse rate variability from sequential beat-to-beat intervals (BBI) and pulse wave velocity from spatially resolved recorded pulse waves. In either case, sufficient temporal accuracy is essential. The presented work investigates the temporal accuracy of BBI estimation from photoplethysmographic signals. Within comprehensive numerical simulation, we systematically assess the impact of sampling rate, signal-to-noise ratio (SNR), and beat-to-beat shape variations on the root mean square error (RMSE) between real and estimated BBI. Our results show that at sampling rates beyond 14 Hz only small errors exist when interpolation is used. For example, the average RMSE is 3 ms for a sampling rate of 14 Hz and an SNR of 18 dB. Further increasing the sampling rate only results in marginal improvements, e.g. more than tripling the sampling rate to 50 Hz reduces the error by approx. 14%. The most important finding relates to the SNR, which is shown to have a much stronger influence on the error than the sampling rate. For example, increasing the SNR from 18 dB to 24 dB at 14 Hz sampling rate reduced the error by almost 50% to 1.5 ms. Subtle beat-to-beat shape variations, moreover, increase the error decisively by up to 800%. Our results are highly relevant in three regards: first, they partially explain different results in the literature on minimum sampling rates. Second, they emphasize the importance to consider SNR and possibly shape variation in investigations on the minimal sampling rate. Third, they underline the importance of appropriate processing techniques to increase SNR. Importantly, though our motivation is PPGI, the presented work immediately applies to contact PPG and PPG in other settings such as wearables. To enable further investigations, we make the scripts used in modelling and simulation freely available.

eess.SP↗