Search

Today, we are open-sourcing our core speech recognition and diarization models for non-commercial use. We are releasing both a full production pipeline for developers as well as pared-down research models for experimentation. Rev hopes that these releases will spur research and innovation in the fast-moving domain of voice technology. The speech recognition models released today outperform all existing open source speech recognition models across a variety of long-form speech recognition domains.

We consider the $k$-min-sum-radii ($k$-MSR) clustering problem with fairness constraints. The $k$-min-sum-radii problem is a mixture of the classical $k$-center and $k$-median problems. We are given a set of points $P$ in a metric space and a number $k$ and aim to partition the points into $k$ clusters, each of the clusters having one designated center. The objective to minimize is the sum of the radii of the $k$ clusters (where in $k$-center we would only consider the maximum radius and in $k$-median we would consider the sum of the individual points' costs). Various notions of fair clustering have been introduced lately, and we follow the definitions due to Chierichetti, Kumar, Lattanzi and Vassilvitskii [NeurIPS 2017] which demand that cluster compositions shall follow the proportions of the input point set with respect to some given sensitive attribute. For the easier case where the sensitive attribute only has two possible values and each is equally frequent in the input, the aim is to compute a clustering where all clusters have a 1:1 ratio with respect to this attribute. We call this the 1:1 case. There has been a surge of FPT-approximation algorithms for the $k$-MSR problem lately, solving the problem both in the unconstrained case and in several constrained problem variants. We add to this research area by designing an FPT $(6+\epsilon)$-approximation that works for $k$-MSR under the mentioned general fairness notion. For the special 1:1 case, we improve our algorithm to achieve a $(3+\epsilon)$-approximation., Comment: Full version of the paper accepted at ISAAC 2024

State symmetries play an important role in planning and generalized planning. In the first case, state symmetries can be used to reduce the size of the search; in the second, to reduce the size of the training set. In the case of general planning, however, it is also critical to distinguish non-symmetric states, i.e., states that represent non-isomorphic relational structures. However, while the language of first-order logic distinguishes non-symmetric states, the languages and architectures used to represent and learn general policies do not. In particular, recent approaches for learning general policies use state features derived from description logics or learned via graph neural networks (GNNs) that are known to be limited by the expressive power of C_2, first-order logic with two variables and counting. In this work, we address the problem of detecting symmetries in planning and generalized planning and use the results to assess the expressive requirements for learning general policies over various planning domains. For this, we map planning states to plain graphs, run off-the-shelf algorithms to determine whether two states are isomorphic with respect to the goal, and run coloring algorithms to determine if C_2 features computed logically or via GNNs distinguish non-isomorphic states. Symmetry detection results in more effective learning, while the failure to detect non-symmetries prevents general policies from being learned at all in certain domains., Comment: Accepted at the 21st International Conference on Principles of Knowledge Representation and Reasoning (KR2024) in the Reasoning, Learning, and Decision Making track

Since its introduction in 1957, Lloyd's algorithm for $k$-means clustering has been extensively studied and has undergone several improvements. While in its original form it does not guarantee any approximation factor at all, Arthur and Vassilvitskii (SODA 2007) proposed $k$-means++ which enhances Lloyd's algorithm by a seeding method which guarantees a $\mathcal{O}(\log k)$-approximation in expectation. More recently, Lattanzi and Sohler (ICML 2019) proposed LS++ which further improves the solution quality of $k$-means++ by local search techniques to obtain a $\mathcal{O}(1)$-approximation. On the practical side, the greedy variant of $k$-means++ is often used although its worst-case behaviour is provably worse than for the standard $k$-means++ variant. We investigate how to improve LS++ further in practice. We study two options for improving the practical performance: (a) Combining LS++ with greedy $k$-means++ instead of $k$-means++, and (b) Improving LS++ by better entangling it with Lloyd's algorithm. Option (a) worsens the theoretical guarantees of $k$-means++ but improves the practical quality also in combination with LS++ as we confirm in our experiments. Option (b) is our new algorithm, Foresight LS++. We experimentally show that FLS++ improves upon the solution quality of LS++. It retains its asymptotic runtime and its worst-case approximation bounds.

Using the newly developed 530 MeV positron beam from the Mainz Microtron MAMI and employing a bent silicon crystal, we demonstrate the first successful manipulation with high efficiencies of the trajectories of positrons through planar channeling and volume reflection. This uncovered the presence of fine structure within the angular distribution of charged particles when they are channeled between the planes of bent crystals. The alignment of our experimental findings with simulation results not only demonstrates a deeper understanding of the interactions between charged particle beams and bent crystals but also signals a new phase in the development of innovative methodologies for slow extraction in circular accelerators operating in the GeV range, with implications for worldwide accelerators. Our results also mark a considerable progression in the generation of advanced x-ray sources through the channeling process in periodically bent crystals, rooted in a comprehensive understanding of the interactions between positron beams and such crystals.

Recently, a simple but powerful language for expressing and learning general policies and problem decompositions (sketches) has been introduced in terms of rules defined over a set of Boolean and numerical features. In this work, we consider three extensions of this language aimed at making policies and sketches more flexible and reusable: internal memory states, as in finite state controllers; indexical features, whose values are a function of the state and a number of internal registers that can be loaded with objects; and modules that wrap up policies and sketches and allow them to call each other by passing parameters. In addition, unlike general policies that select state transitions rather than ground actions, the new language allows for the selection of such actions. The expressive power of the resulting language for policies and sketches is illustrated through a number of examples., Comment: ICAPS 2024

We report the measurement of the helicity asymmetry $E$ for the $p\pi^0$ and $n\pi^+$ final states using, for the first time, an elliptically polarized photon beam in combination with a longitudinally polarized target at the Crystal Ball experiment at MAMI. The results agree very well with data that were taken with a circularly polarized photon beam, showing that it is possible to simultaneously measure polarization observables that require linearly (e.g.~$G$) and circularly polarized photons (e.g.~$E$) and a longitudinally polarized target. The new data cover a photon energy range 270 - 1400 MeV for the $p\pi^0$ final state (230 - 842 MeV for the $n\pi^+$ final state) and the full range of pion polar angles, $\theta$, providing the most precise measurement of the observable $E$. A moment analysis gives a clear observation of the $p\eta$ cusp in the $p\pi^0$ final state.

Early detection of melanoma, a potentially lethal type of skin cancer with high prevalence worldwide, improves patient prognosis. In retrospective studies, artificial intelligence (AI) has proven to be helpful for enhancing melanoma detection. However, there are few prospective studies confirming these promising results. Existing studies are limited by low sample sizes, too homogenous datasets, or lack of inclusion of rare melanoma subtypes, preventing a fair and thorough evaluation of AI and its generalizability, a crucial aspect for its application in the clinical setting. Therefore, we assessed 'All Data are Ext' (ADAE), an established open-source ensemble algorithm for detecting melanomas, by comparing its diagnostic accuracy to that of dermatologists on a prospectively collected, external, heterogeneous test set comprising eight distinct hospitals, four different camera setups, rare melanoma subtypes, and special anatomical sites. We advanced the algorithm with real test-time augmentation (R-TTA, i.e. providing real photographs of lesions taken from multiple angles and averaging the predictions), and evaluated its generalization capabilities. Overall, the AI showed higher balanced accuracy than dermatologists (0.798, 95% confidence interval (CI) 0.779-0.814 vs. 0.781, 95% CI 0.760-0.802; p<0.001), obtaining a higher sensitivity (0.921, 95% CI 0.900- 0.942 vs. 0.734, 95% CI 0.701-0.770; p<0.001) at the cost of a lower specificity (0.673, 95% CI 0.641-0.702 vs. 0.828, 95% CI 0.804-0.852; p<0.001). As the algorithm exhibited a significant performance advantage on our heterogeneous dataset exclusively comprising melanoma-suspicious lesions, AI may offer the potential to support dermatologists particularly in diagnosing challenging cases.

We consider the following natural problem that generalizes min-sum-radii clustering: Given is $k\in\mathbb{N}$ as well as some metric space $(V,d)$ where $V=F\cup C$ for facilities $F$ and clients $C$. The goal is to find a clustering given by $k$ facility-radius pairs $(f_1,r_1),\dots,(f_k,r_k)\in F\times\mathbb{R}_{\geq 0}$ such that $C\subseteq B(f_1,r_1)\cup\dots\cup B(f_k,r_k)$ and $\sum_{i=1,\dots,k} g(r_i)$ is minimized for some increasing function $g:\mathbb{R}_{\geq 0}\rightarrow\mathbb{R}_{\geq 0}$. Here, $B(x,r)$ is the radius-$r$ ball centered at $x$. For the case that $(V,d)$ is the shortest-path metric of some edge-weighted graph of bounded treewidth, we present a dynamic program that is tailored to this class of problems and achieves a polynomial running time, establishing that the problem is in $\mathsf{XP}$ with parameter treewidth., Comment: updated funding information

The vast majority of ASR research uses corpora in which both the training and test data have been pre-segmented into utterances. In most real-word ASR use-cases, however, test audio is not segmented, leading to a mismatch between inference-time conditions and models trained on segmented utterances. In this paper, we re-release three standard ASR corpora - TED-LIUM 3, Gigapeech, and VoxPopuli-en - with updated transcription and alignments to enable their use for long-form ASR research. We use these reconstituted corpora to study the train-test mismatch problem for transducers and attention-based encoder-decoders (AEDs), confirming that AEDs are more susceptible to this issue. Finally, we benchmark a simple long-form training for these models, showing its efficacy for model robustness under this domain shift., Comment: Submitted to ICASSP 2024

The $k$-center problem is a classical clustering problem in which one is asked to find a partitioning of a point set $P$ into $k$ clusters such that the maximum radius of any cluster is minimized. It is well-studied. But what if we add up the radii of the clusters instead of only considering the cluster with maximum radius? This natural variant is called the $k$-min-sum-radii problem. It has become the subject of more and more interest in recent years, inspiring the development of approximation algorithms for the $k$-min-sum-radii problem in its plain version as well as in constrained settings. We study the problem for Euclidean spaces $\mathbb{R}^d$ of arbitrary dimension but assume the number $k$ of clusters to be constant. In this case, a PTAS for the problem is known (see Bandyapadhyay, Lochet and Saurabh, SoCG, 2023). Our aim is to extend the knowledge base for $k$-min-sum-radii to the domain of fair clustering. We study several group fairness constraints, such as the one introduced by Chierichetti et al. (NeurIPS, 2017). In this model, input points have an additional attribute (e.g., colors such as red and blue), and clusters have to preserve the ratio between different attribute values (e.g., have the same fraction of red and blue points as the ground set). Different variants of this general idea have been studied in the literature. To the best of our knowledge, no approximative results for the fair $k$-min-sum-radii problem are known, despite the immense amount of work on the related fair $k$-center problem. We propose a PTAS for the fair $k$-min-sum-radii problem in Euclidean spaces of arbitrary dimension for the case of constant $k$. To the best of our knowledge, this is the first PTAS for the problem. It works for different notions of group fairness., Comment: Unfortunately, there is an error in the proof. We cannot establish the general result for fair k-msr. A new version of the PTAS that solves k-msr with outliers can be found at https://katalog.ulb.hhu.de/Record/9947680789806443

Photoproduction of $\pi^0\pi^{\pm}$-pairs from quasifree nucleons bound in the deuteron has been investigated to study the helicity dependence of this reaction. Measurements with a liquid deuterium target were used to extract the unpolarized cross sections for reactions on protons and neutrons. A deuterated, longitudinally polarized solid-butanol target, together with a circularly polarized photon beam, determined the double polarization observable $E$. From these results the spin-dependent cross sections $\sigma_{1/2}$ and $\sigma_{3/2}$, corresponding to the anti-parallel and parallel spin configurations of the beam photon and target nucleon, have been derived. The measurements were performed at the Mainz MAMI accelerator with tagged, circularly-polarized photon beams produced via bremsstrahlung from longitudinally polarized electron beams. The reaction products were detected with an almost $4\pi$ solid-angle covering calorimeter composed of the Crystal Ball and TAPS detectors, supplemented by plastic scintillation detectors for charged particle identification. The results are sensitive to sequential decays of nucleon resonances via intermediate states and also to the decay of nucleon resonances by emission of charged $\rho$ mesons, and are compared to recent model results., Comment: 9 pages, 6 figures

Quantitative tissue information, like the light scattering properties, is considered as a key player in the detection of cancerous cells in medical diagnosis. A promising method to obtain these data is optical coherence tomography (OCT). In this article, we will therefore discuss the refractive index reconstruction from OCT data, employing a Gaussian beam based forward model. We consider in particular samples with a layered structure, meaning that the refractive index as a function of depth is well approximated by a piece-wise constant function. For the reconstruction, we present a layer-by-layer method where in every step the refractive index is obtained via a discretized least squares minimization. For an approximated form of the minimization problem, we present an existence and uniqueness result. The applicability of the proposed method is then verified by reconstructing refractive indices of layered media from both simulated and experimental OCT data., Comment: 27 pages, 12 figures, 4 tables

Non-invasive imaging plays a crucial role in diagnosing and studying eye diseases. However, existing photoacoustic ophthalmoscopy (PAOM) techniques in mice have limitations due to handling restrictions, suboptimal optical properties, limited availability of light sources and permissible light fluence at the retina. This study introduces an innovative approach that utilizes Rose Bengal, a contrast agent, to enhance PAOM contrast. This enables visualization of deeper structures like the choroidal microvasculature and sclera in the mouse eye using visible light. The integration of near-infrared-II optical coherence tomography (NIR-II OCT) provides additional tissue contrast and insights into potential NIR-II PAOM capabilities. To optimize imaging, we developed a cost-effective 3D printable mouse eye phantom and a fully 3D printable tip/tilt mouse platform. This solution elevates PAOM to a user-friendly technology, which can be used to address pressing research questions concerning several ocular diseases such as myopia, glaucoma and/or age-related macular degeneration in the future., Comment: 14 pages, 4 figures

Background: Convolutional neural network (CNN)-based melanoma classifiers face several challenges that limit their usefulness in clinical practice. Objective: To investigate the impact of multiple real-world dermoscopic views of a single lesion of interest on a CNN-based melanoma classifier. Methods: This study evaluated 656 suspected melanoma lesions. Classifier performance was measured using area under the receiver operating characteristic curve (AUROC), expected calibration error (ECE) and maximum confidence change (MCC) for (I) a single-view scenario, (II) a multiview scenario using multiple artificially modified images per lesion and (III) a multiview scenario with multiple real-world images per lesion. Results: The multiview approach with real-world images significantly increased the AUROC from 0.905 (95% CI, 0.879-0.929) in the single-view approach to 0.930 (95% CI, 0.909-0.951). ECE and MCC also improved significantly from 0.131 (95% CI, 0.105-0.159) to 0.072 (95% CI: 0.052-0.093) and from 0.149 (95% CI, 0.125-0.171) to 0.115 (95% CI: 0.099-0.131), respectively. Comparing multiview real-world to artificially modified images showed comparable diagnostic accuracy and uncertainty estimation, but significantly worse robustness for the latter. Conclusion: Using multiple real-world images is an inexpensive method to positively impact the performance of a CNN-based melanoma classifier.

Although artificial intelligence (AI) systems have been shown to improve the accuracy of initial melanoma diagnosis, the lack of transparency in how these systems identify melanoma poses severe obstacles to user acceptance. Explainable artificial intelligence (XAI) methods can help to increase transparency, but most XAI methods are unable to produce precisely located domain-specific explanations, making the explanations difficult to interpret. Moreover, the impact of XAI methods on dermatologists has not yet been evaluated. Extending on two existing classifiers, we developed an XAI system that produces text and region based explanations that are easily interpretable by dermatologists alongside its differential diagnoses of melanomas and nevi. To evaluate this system, we conducted a three-part reader study to assess its impact on clinicians' diagnostic accuracy, confidence, and trust in the XAI-support. We showed that our XAI's explanations were highly aligned with clinicians' explanations and that both the clinicians' trust in the support system and their confidence in their diagnoses were significantly increased when using our XAI compared to using a conventional AI system. The clinicians' diagnostic accuracy was numerically, albeit not significantly, increased. This work demonstrates that clinicians are willing to adopt such an XAI system, motivating their future use in the clinic.

We report a first measurement of the double-polarisation observable, $C_{x'}$, in $\pi^+$ photoproduction off the proton. The $C_{x'}$ double-polarisation observable represents the transfer of polarisation from a circularly polarised photon beam to the recoiling neutron. The MAMI circularly polarised photon beam impinged on a liquid deuterium target cell, with reaction products detected in the Crystal Ball calorimeter. Ancillary apparatus surrounding the target provided tracking, particle identification and determination of recoil nucleon polarisation. The $C_{x'}$ observable is determined for photon energies 800-1400 MeV, providing new constraints on models aiming to elucidate the spectrum and properties of nucleon resonances. This is the first determination of any polarisation observable from the beam-recoil group of observables for this reaction, providing a valuable constraint and systematic check of the current solutions of partial wave analysis based theoretical models.

Motivated by an application from geodesy, we introduce a novel clustering problem which is a $k$-center (or k-diameter) problem with a side constraint. For the side constraint, we are given an undirected connectivity graph $G$ on the input points, and a clustering is now only feasible if every cluster induces a connected subgraph in $G$. We call the resulting problems the connected $k$-center problem and the connected $k$-diameter problem. We prove several results on the complexity and approximability of these problems. Our main result is an $O(\log^2{k})$-approximation algorithm for the connected $k$-center and the connected $k$-diameter problem. For Euclidean metrics and metrics with constant doubling dimension, the approximation factor of this algorithm improves to $O(1)$. We also consider the special cases that the connectivity graph is a line or a tree. For the line we give optimal polynomial-time algorithms and for the case that the connectivity graph is a tree, we either give an optimal polynomial-time algorithm or a $2$-approximation algorithm for all variants of our model. We complement our upper bounds by several lower bounds.

Contextual ASR, which takes a list of bias terms as input along with audio, has drawn recent interest as ASR use becomes more widespread. We are releasing contextual biasing lists to accompany the Earnings21 dataset, creating a public benchmark for this task. We present baseline results on this benchmark using a pretrained end-to-end ASR model from the WeNet toolkit. We show results for shallow fusion contextual biasing applied to two different decoding algorithms. Our baseline results confirm observations that end-to-end models struggle in particular with words that are rarely or never seen during training, and that existing shallow fusion techniques do not adequately address this problem. We propose an alternate spelling prediction model that improves recall of rare words by 34.7% relative and of out-of-vocabulary words by 97.2% relative, compared to contextual biasing without alternate spellings. This model is conceptually similar to ones used in prior work, but is simpler to implement as it does not rely on either a pronunciation dictionary or an existing text-to-speech system.

The automatic detection and localization of anatomical features in retinal imaging data are relevant for many aspects. In this work, we follow a data-centric approach to optimize classifier training for optic nerve head detection and localization in optical coherence tomography en face images of the retina. We examine the effect of domain knowledge driven spatial complexity reduction on the resulting optic nerve head segmentation and localization performance. We present a machine learning approach for segmenting optic nerve head in 2D en face projections of 3D widefield swept source optical coherence tomography scans that enables the automated assessment of large amounts of data. Evaluation on manually annotated 2D en face images of the retina demonstrates that training of a standard U-Net can yield improved optic nerve head segmentation and localization performance when the underlying pixel-level binary classification task is spatially relaxed through domain knowledge., Comment: 12 pages, 2 figures

Background: Photoproduction of pion pairs allows to study sequential decays of nucleon resonances via excited intermediate states. Such decays are important e.g. for states which in the quark model have both oscillators excited and de-excite them in a two-step process. However, analyses of multi-meson final states is difficult and requires more than unpolarized cross section measurements. Purpose: Experimental study and model analysis in view of resonant contributions of target and beam-target polarization observables for the reaction $\gamma p \to \pi^0 \pi^0 p$. Methods: Investigated were target (single) and beam-target (double) polarization asymmetries in dependence of several parameters. The experiments were performed at the Mainz Microtron (MAMI) using circularly polarized photon beams and transversally polarized solid-state butanol targets. The reaction products were analyzed with the Crystal Ball and TAPS detectors. Results: Studied were the polarization observables Py (unpolarized beam, target polarized in y direction) and Px (circularly polarized beam, target polarized in x direction), which are similar to T (target asymmetry) and F (beam-target asymmetry) for single pion production. The asymmetries were analyzed with three independent methods, revealing systematic uncertainties., Comment: 16 pages, 12 figures, 5 tables