Search

Recent advancements in Automatic Piano Transcription (APT) have significantly improved system performance, but the impact of noisy environments on the system performance remains largely unexplored. This study investigates the impact of white noise at various Signal-to-Noise Ratio (SNR) levels on state-of-the-art APT models and evaluates the performance of the Onsets and Frames model when trained on noise-augmented data. We hope this research provides valuable insights as preliminary work toward developing transcription models that maintain consistent performance across a range of acoustic conditions., Comment: Accepted to the Late-Breaking Demo Session of the 25th International Society for Music Information Retrieval (ISMIR) Conference, 2024

In the realm of digital music, using tags to efficiently organize and retrieve music from extensive databases is crucial for music catalog owners. Human tagging by experts is labor-intensive but mostly accurate, whereas automatic tagging through supervised learning has approached satisfying accuracy but is restricted to a predefined set of training tags. Few-shot learning offers a viable solution to expand beyond this small set of predefined tags by enabling models to learn from only a few human-provided examples to understand tag meanings and subsequently apply these tags autonomously. We propose to integrate few-shot learning methodology into multi-label music auto-tagging by using features from pre-trained models as inputs to a lightweight linear classifier, also known as a linear probe. We investigate different popular pre-trained features, as well as different few-shot parametrizations with varying numbers of classes and samples per class. Our experiments demonstrate that a simple model with pre-trained features can achieve performance close to state-of-the-art models while using significantly less training data, such as 20 samples per tag. Additionally, our linear probe performs competitively with leading models when trained on the entire training dataset. The results show that this transfer learning-based few-shot approach could effectively address the issue of automatically assigning long-tail tags with only limited labeled data., Comment: Published in Audio Engineering Society NY Show 2024 as a Peer Reviewed (Category 1) paper; typos corrected

Centrifugation of erythrocytes (aka Red Blood Cells, RBCs) in a self-forming Percoll gradient is a protocol often used as a way to sort RBCs by age. However, a pattern formation of discrete bands is systematically observed along the continuous density gradient. Although early studies mentioned that aggregation between cells might modify their spatial distribution, it is debated whether a population with continuous density distribution can form discrete bands. Here, we develop a continuity equation, considering the aggregation of cells with a continuous density distribution, which describes the macroscopic evolution of the RBC volume concentration in a density gradient. The numerical solutions demonstrate that the competition between iso-density distribution and aggregation is sufficient to create band patterns. Our model reproduces the temporal evolution observed in the conventional experimental protocol, but also predicts several types of bifurcation-like behaviors for the steady-state patterns in constant gradients, when the volume fraction and aggregation energy of the cells are varied. We threrefore discovered that the competition between RBC aggregation and iso-density distribution is a novel physical mechanism leading to pattern formation.

Ensemble forecasts from numerical weather prediction models show systematic errors that require correction via post-processing. While there has been substantial progress in flexible neural network-based post-processing methods over the past years, most station-based approaches still treat every input data point separately which limits the capabilities for leveraging spatial structures in the forecast errors. In order to improve information sharing across locations, we propose a graph neural network architecture for ensemble post-processing, which represents the station locations as nodes on a graph and utilizes an attention mechanism to identify relevant predictive information from neighboring locations. In a case study on 2-m temperature forecasts over Europe, the graph neural network model shows substantial improvements over a highly competitive neural network-based post-processing method., Comment: Accepted paper at ICML 2024 - Machine Learning for Earth System Modeling Workshop (https://leap-stc.github.io/ml4esm-workshop/)

Despite significant recent progress across multiple subtasks of audio source separation, few music source separation systems support separation beyond the four-stem vocals, drums, bass, and other (VDBO) setup. Of the very few current systems that support source separation beyond this setup, most continue to rely on an inflexible decoder setup that can only support a fixed pre-defined set of stems. Increasing stem support in these inflexible systems correspondingly requires increasing computational complexity, rendering extensions of these systems computationally infeasible for long-tail instruments. In this work, we propose Banquet, a system that allows source separation of multiple stems using just one decoder. A bandsplit source separation model is extended to work in a query-based setup in tandem with a music instrument recognition PaSST model. On the MoisesDB dataset, Banquet, at only 24.9 M trainable parameters, approached the performance level of the significantly more complex 6-stem Hybrid Transformer Demucs on VDBO stems and outperformed it on guitar and piano. The query-based setup allows for the separation of narrow instrument classes such as clean acoustic guitars, and can be successfully applied to the extraction of less common stems such as reeds and organs. Implementation is available at https://github.com/kwatcharasupat/query-bandit., Comment: Accepted to the 25th International Society for Music Information Retrieval Conference (ISMIR 2024). Camera-ready version

Exploration requires that robots reason about numerous ways to cover a space in response to dynamically changing conditions. However, in continuous domains there are potentially infinitely many options for robots to explore which can prove computationally challenging. How then should a robot efficiently optimize and choose exploration strategies to adopt? In this work, we explore this question through the use of variational inference to efficiently solve for distributions of coverage trajectories. Our approach leverages ergodic search methods to optimize coverage trajectories in continuous time and space. In order to reason about distributions of trajectories, we formulate ergodic search as a probabilistic inference problem. We propose to leverage Stein variational methods to approximate a posterior distribution over ergodic trajectories through parallel computation. As a result, it becomes possible to efficiently optimize distributions of feasible coverage trajectories for which robots can adapt exploration. We demonstrate that the proposed Stein variational ergodic search approach facilitates efficient identification of multiple coverage strategies and show online adaptation in a model-predictive control formulation. Simulated and physical experiments demonstrate adaptability and diversity in exploration strategies online., Comment: 16 pages, 12 figures, accepted to Robotics: Science and Systems 2024

While various sensors have been deployed to monitor vehicular flows, sensing pedestrian movement is still nascent. Yet walking is a significant mode of travel in many cities, especially those in Europe, Africa, and Asia. Understanding pedestrian volumes and flows is essential for designing safer and more attractive pedestrian infrastructure and for controlling periodic overcrowding. This study discusses a new approach to scale up urban sensing of people with the help of novel audio-based technology. It assesses the benefits and limitations of microphone-based sensors as compared to other forms of pedestrian sensing. A large-scale dataset called ASPED is presented, which includes high-quality audio recordings along with video recordings used for labeling the pedestrian count data. The baseline analyses highlight the promise of using audio sensors for pedestrian tracking, although algorithmic and technological improvements to make the sensors practically usable continue. This study also demonstrates how the data can be leveraged to predict pedestrian trajectories. Finally, it discusses the use cases and scenarios where audio-based pedestrian sensing can support better urban and transportation planning., Comment: submitted to Urban Informatics

Weather forecasts from numerical weather prediction models play a central role in solar energy forecasting, where a cascade of physics-based models is used in a model chain approach to convert forecasts of solar irradiance to solar power production, using additional weather variables as auxiliary information. Ensemble weather forecasts aim to quantify uncertainty in the future development of the weather, and can be used to propagate this uncertainty through the model chain to generate probabilistic solar energy predictions. However, ensemble prediction systems are known to exhibit systematic errors, and thus require post-processing to obtain accurate and reliable probabilistic forecasts. The overarching aim of our study is to systematically evaluate different strategies to apply post-processing methods in model chain approaches: Not applying any post-processing at all; post-processing only the irradiance predictions before the conversion; post-processing only the solar power predictions obtained from the model chain; or applying post-processing in both steps. In a case study based on a benchmark dataset for the Jacumba solar plant in the U.S., we develop statistical and machine learning methods for post-processing ensemble predictions of global horizontal irradiance and solar power generation. Further, we propose a neural network-based model for direct solar power forecasting that bypasses the model chain. Our results indicate that post-processing substantially improves the solar power generation forecasts, in particular when post-processing is applied to the power predictions. The machine learning methods for post-processing yield slightly better probabilistic forecasts, and the direct forecasting approach performs comparable to the post-processing strategies.

We revisit the magnetic properties of the hexagonal ferrite PbFe$_{12-x}$Ga$_x$O$_{19}$. Recent experiments have reported puzzling dependencies of the ordering temperature and the saturation magnetization on the Ga concentration $x$. To explain these observations, we perform large-scale Monte Carlo simulations, focusing on the effects of an unequal distribution of the Ga impurities over the five distinct Fe sublattices. Ab-initio density-functional calculations predict that the Ga ions preferably occupy the $12k$ sublattice and (to a lesser extent) the $2a$ sublattice. We incorporate this insight into a nonuniform model of the Ga distribution. Monte Carlo simulations using this model lead to an excellent agreement between the theoretical and experimental values of the ordering temperature and saturation magnetization, indicating that the unequal distribution of the Ga impurities is the main reason for the unusual magnetic properties of PbFe$_{12-x}$Ga$_x$O$_{19}$. We also compute the temperature and concentration dependencies of the sublattice magnetizations, and we study the character of the zero-temperature transition that takes place when the ordering temperature is tuned to zero., Comment: 11 pages, 12 figures, final version as published

Reliable forecasts of quasi-stationary, recurrent, and persistent large-scale atmospheric circulation patterns (weather regimes) are crucial for various socio-economic sectors. Despite steady progress, probabilistic weather regime predictions still exhibit biases in the exact timing and amplitude of weather regimes. This study thus aims at advancing probabilistic weather regime predictions in the North Atlantic-European region through ensemble post-processing. Here, we focus on the representation of seven year-round weather regimes in the sub-seasonal to seasonal reforecasts of the European Centre for Medium-Range Weather Forecasts. The manifestation of each of the seven regimes can be expressed by a continuous weather regime index, representing the projection of the instantaneous 500-hPa geopotential height anomalies (Z500A) onto the respective mean regime pattern. We apply a two-step ensemble post-processing involving first univariate ensemble model output statistics and second ensemble copula coupling, which restores the multivariate dependency structure. Compared to current forecast calibration practices, which rely on correcting the Z500 field by the lead time dependent mean bias, our approach extends the forecast skill horizon for daily/instantaneous regime forecasts moderately by 1.2 days to 14.5 days. Additionally, to our knowledge our study is the first to systematically evaluate the multivariate aspects of forecast quality for weather regime forecasts. Our method outperforms current practices in the multivariate aspect, as measured by the energy and variogram score. Still our study shows, that even with advanced post-processing weather regime prediction becomes difficult beyond 14 days, which likely points towards intrinsic limits of predictability for daily/instantaneous regime forecasts. The proposed method can easily be applied to operational weather regime forecasts., Comment: submitted to Quarterly Journal of the Royal Meteorological Society (QJRMS)

Artificial intelligence (AI)-based data-driven weather forecasting models have experienced rapid progress over the last years. Recent studies, with models trained on reanalysis data, achieve impressive results and demonstrate substantial improvements over state-of-the-art physics-based numerical weather prediction models across a range of variables and evaluation metrics. Beyond improved predictions, the main advantages of data-driven weather models are their substantially lower computational costs and the faster generation of forecasts, once a model has been trained. However, most efforts in data-driven weather forecasting have been limited to deterministic, point-valued predictions, making it impossible to quantify forecast uncertainties, which is crucial in research and for optimal decision making in applications. Our overarching aim is to systematically study and compare uncertainty quantification methods to generate probabilistic weather forecasts from a state-of-the-art deterministic data-driven weather model, Pangu-Weather. Specifically, we compare approaches for quantifying forecast uncertainty based on generating ensemble forecasts via perturbations to the initial conditions, with the use of statistical and machine learning methods for post-hoc uncertainty quantification. In a case study on medium-range forecasts of selected weather variables over Europe, the probabilistic forecasts obtained by using the Pangu-Weather model in concert with uncertainty quantification methods show promising results and provide improvements over ensemble forecasts from the physics-based ensemble weather model of the European Centre for Medium-Range Weather Forecasts for lead times of up to 5 days.

We discuss a class of linear representations of the product poset of totally ordered sets $P= T_1 \times \cdots \times T_n$ which decompose into interval representations for block intervals. These can be characterised in terms of a homological property which is called middle exactness., Comment: This paper has been merged with arXiv:2402.16624

Local conditions for the direct summands of a persistence module to belong to a certain class of indecomposables have been proposed in the 2-parameter setting, notably for the class of indecomposables called block modules, which plays a prominent role in levelset persistence. Here we generalize the local condition for decomposability into block modules to the n-parameter setting, and prove a corresponding structure theorem. Our result holds in the generality of pointwise finite-dimensional modules over finite products of arbitrary totally ordered sets. Our proof extends the one by Botnan and Crawley-Boevey from 2 to n parameters, which requires some crucial adaptations at places where their proof is fundamentally tied to the 2-parameter setting., Comment: This paper has been merged with arXiv:2402.19228. The overall exposition has been restructured and improved along the way

Common knowledge distillation methods require the teacher model and the student model to be trained on the same task. However, the usage of embeddings as teachers has also been proposed for different source tasks and target tasks. Prior work that uses embeddings as teachers ignores the fact that the teacher embeddings are likely to contain irrelevant knowledge for the target task. To address this problem, we propose to use an embedding compression module with a trainable teacher transformation to obtain a compact teacher embedding. Results show that adding the embedding compression module improves the classification performance, especially for unsupervised teacher embeddings. Moreover, student models trained with the guidance of embeddings show stronger generalizability., Comment: 5+1 pages. In ICASSP 2024 Satellite Workshop Deep Neural Network Model Compression

Wind gust prediction plays an important role in warning strategies of national meteorological services due to the high impact of its extreme values. However, forecasting wind gusts is challenging because they are influenced by small-scale processes and local characteristics. To account for the different sources of uncertainty, meteorological centers run ensembles of forecasts and derive probabilities of wind gusts exceeding a threshold. These probabilities often exhibit systematic errors and require postprocessing. Model Output Statistics (MOS) is a common operational postprocessing technique, although more modern methods such as neural network-bases approaches have shown promising results in research studies. The transition from research to operations requires an exhaustive comparison of both techniques. Taking a first step into this direction, our study presents a comparison of a postprocessing technique based on linear and logistic regression approaches with different neural network methods proposed in the literature to improve wind gust predictions, specifically distributional regression networks and Bernstein quantile networks. We further contribute to investigating optimal design choices for neural network-based postprocessing methods regarding changes of the numerical model in the training period, the use of persistence predictors, and the temporal composition of training datasets. The performance of the different techniques is compared in terms of calibration, accuracy, reliability and resolution based on case studies of wind gust forecasts from the operational weather model of the German weather service and observations from 170 weather stations.

In the contemporary security landscape, the incorporation of photonics has emerged as a transformative force, unlocking a spectrum of possibilities to enhance the resilience and effectiveness of security primitives. This integration represents more than a mere technological augmentation; it signifies a paradigm shift towards innovative approaches capable of delivering security primitives with key properties for low-power systems. This not only augments the robustness of security frameworks, but also paves the way for novel strategies that adapt to the evolving challenges of the digital age. This paper discusses the security layers and related services that will be developed, modeled, and evaluated within the Horizon Europe NEUROPULS project. These layers will exploit novel implementations for security primitives based on physical unclonable functions (PUFs) using integrated photonics technology. Their objective is to provide a series of services to support the secure operation of a neuromorphic photonic accelerator for edge computing applications., Comment: 6 pages, 4 figures

Recent advancements in Neural Audio Synthesis (NAS) have outpaced the development of standardized evaluation methodologies and tools. To bridge this gap, we introduce AquaTk, an open-source Python library specifically designed to simplify and standardize the evaluation of NAS systems. AquaTk offers a range of audio quality metrics, including a unique Python implementation of the basic PEAQ algorithm, and operates in multiple modes to accommodate various user needs.

Continuous exploration without interruption is important in scenarios such as search and rescue and precision agriculture, where consistent presence is needed to detect events over large areas. Ergodic search already derives continuous trajectories in these scenarios so that a robot spends more time in areas with high information density. However, existing literature on ergodic search does not consider the robot's energy constraints, limiting how long a robot can explore. In fact, if the robots are battery-powered, it is physically not possible to continuously explore on a single battery charge. Our paper tackles this challenge, integrating ergodic search methods with energy-aware coverage. We trade off battery usage and coverage quality, maintaining uninterrupted exploration by at least one agent. Our approach derives an abstract battery model for future state-of-charge estimation and extends canonical ergodic search to ergodic search under battery constraints. Empirical data from simulations and real-world experiments demonstrate the effectiveness of our energy-aware ergodic search, which ensures continuous exploration and guarantees spatial coverage., Comment: 7 pages, 7 figures, ICRA'24

We introduce the new audio analysis task of pedestrian detection and present a new large-scale dataset for this task. While the preliminary results prove the viability of using audio approaches for pedestrian detection, they also show that this challenging task cannot be easily solved with standard approaches., Comment: 4+1 pages, ICASSP 2024

Statistical postprocessing is used to translate ensembles of raw numerical weather forecasts into reliable probabilistic forecast distributions. In this study, we examine the use of permutation-invariant neural networks for this task. In contrast to previous approaches, which often operate on ensemble summary statistics and dismiss details of the ensemble distribution, we propose networks that treat forecast ensembles as a set of unordered member forecasts and learn link functions that are by design invariant to permutations of the member ordering. We evaluate the quality of the obtained forecast distributions in terms of calibration and sharpness and compare the models against classical and neural network-based benchmark methods. In case studies addressing the postprocessing of surface temperature and wind gust forecasts, we demonstrate state-of-the-art prediction quality. To deepen the understanding of the learned inference process, we further propose a permutation-based importance analysis for ensemble-valued predictors, which highlights specific aspects of the ensemble forecast that are considered important by the trained postprocessing models. Our results suggest that most of the relevant information is contained in a few ensemble-internal degrees of freedom, which may impact the design of future ensemble forecasting and postprocessing systems., Comment: in press

Cinematic audio source separation is a relatively new subtask of audio source separation, with the aim of extracting the dialogue, music, and effects stems from their mixture. In this work, we developed a model generalizing the Bandsplit RNN for any complete or overcomplete partitions of the frequency axis. Psychoacoustically motivated frequency scales were used to inform the band definitions which are now defined with redundancy for more reliable feature extraction. A loss function motivated by the signal-to-noise ratio and the sparsity-promoting property of the 1-norm was proposed. We additionally exploit the information-sharing property of a common-encoder setup to reduce computational complexity during both training and inference, improve separation performance for hard-to-generalize classes of sounds, and allow flexibility during inference time with detachable decoders. Our best model sets the state of the art on the Divide and Remaster dataset with performance above the ideal ratio mask for the dialogue stem., Comment: Accepted to the IEEE Open Journal of Signal Processing (ICASSP 2024 Track)

Music classification has been one of the most popular tasks in the field of music information retrieval. With the development of deep learning models, the last decade has seen impressive improvements in a wide range of classification tasks. However, the increasing model complexity makes both training and inference computationally expensive. In this paper, we integrate the ideas of transfer learning and feature-based knowledge distillation and systematically investigate using pre-trained audio embeddings as teachers to guide the training of low-complexity student networks. By regularizing the feature space of the student networks with the pre-trained embeddings, the knowledge in the teacher embeddings can be transferred to the students. We use various pre-trained audio embeddings and test the effectiveness of the method on the tasks of musical instrument classification and music auto-tagging. Results show that our method significantly improves the results in comparison to the identical model trained without the teacher's knowledge. This technique can also be combined with classical knowledge distillation approaches to further improve the model's performance., Comment: Accepted at the 24th International Society for Music Information Retrieval Conference (ISMIR 2023), 9 pages, 2 figures

Sub-seasonal weather forecasts are becoming increasingly important for a range of socio-economic activities. However, the predictive ability of physical weather models is very limited on these time scales. We propose several post-processing methods based on convolutional neural networks to improve sub-seasonal forecasts by correcting systematic errors of numerical weather prediction models. Our post-processing models operate directly on spatial input fields and are therefore able to retain spatial relationships and to generate spatially homogeneous predictions. They produce global probabilistic tercile forecasts for biweekly aggregates of temperature and precipitation for weeks 3-4 and 5-6. In a case study based on a public forecasting challenge organized by the World Meteorological Organization, our post-processing models outperform recalibrated forecasts from the European Centre for Medium-Range Weather Forecasts (ECMWF), and achieve improvements over climatological forecasts for all considered variables and lead times. We compare several model architectures and training modes and demonstrate that all approaches lead to skillful and well-calibrated probabilistic forecasts. The good calibration of the post-processed forecasts emphasizes that our post-processing models reliably quantify the forecast uncertainty based on deterministic input information in form of the ECMWF ensemble mean forecast fields only.

Spatial audio quality is a highly multifaceted concept, with many interactions between environmental, geometrical, anatomical, psychological, and contextual considerations. Methods for characterization or evaluation of the geometrical components of spatial audio quality, however, remain scarce, despite being perhaps the least subjective aspect of spatial audio quality to quantify. By considering interchannel time and level differences relative to a reference signal, it is possible to construct a signal model to isolate some of the spatial distortion. By using a combination of least-square optimization and heuristics, we propose a signal decomposition method to isolate the spatial error from a processed signal, in terms of interchannel gain leakages and changes in relative delays. This allows the computation of simple energy-ratio metrics, providing objective measures of spatial and non-spatial signal qualities, with minimal assumptions and no dataset dependency. Experiments demonstrate the robustness of the method against common spatial signal degradation introduced by, e.g., audio compression and music source separation. Implementation is available at https://github.com/karnwatcharasupat/spauq., Comment: Accepted to the 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)