Search for: All records

Variability in speech pronunciation is widely observed across different linguistic backgrounds, which impacts modern automatic speech recognition performance. Here, we evaluate the performance of a self-supervised speech model in phoneme recognition using direct articulatory evidence. Findings indicate significant differences in phoneme recognition, especially in front vowels, between American English and Indian English speakers. To gain a deeper understanding of these differences, we conduct real-time MRI-based articulatory analysis, revealing distinct velar region patterns during the production of specific front vowels. This underscores the need to deepen the scientific understanding of self-supervised speech model variances to advance robust and inclusive speech technology. 

This paper proposes a modified method for training tool segmentation networks for endoscopic images by parsing training images into two disjoint sets: one for rectangular representations of endoscopic images and one for polar. Previous work [1], [2] demonstrated that certain endoscopic images may be better segmented by a U-Net network trained on the original rectangular representation of images alone, and others performed better with polar representations. This work extends that observation to the training images and seeks to intelligently decompose the aggregate training data into disjoint image sets — one ideal for training a network to segment original, rectangular endoscopic images and the other for training a polar segmentation network. The training set decomposition consists of three stages: (1) initial data split and models, (2) image reallocation and transition mechanisms with retraining, and (3) evaluation. In (2), two separate frameworks for parsing polar vs. rectangular training images were investigated, with three switching metrics utilized in both. Experiments comparatively evaluated the segmentation performance (via Sørenson Dice coefficient) of the in-group and out-of-group images between the set-decomposed models. Results are encouraging, showing improved aggregate in-group Dice scores as well as image sets trending towards convergence. 

This paper proposes a low-cost interface and refined digital twin for the Raven-II surgical robot. Previous simulations of the Raven-II, e.g. via the Asynchronous Multibody Framework (AMBF), presented salient drawbacks, including control inputs inconsistent with Raven-II software, and lack of stable, high-fidelity physical contact simulations. This work bridges both of these gaps, both (1) enabling robust, simulated contact mechanics for dynamic physical interactions with the Raven-II, and (2) developing a universal input format for both simulated and physical platforms. The method furthermore proposes a low cost, commodity game-controller interface for controlling both virtual and real realizations of Raven-II, thus greatly reducing the barrier to access for Raven-II research and collaboration. Overall, this work aims to eliminate the inconsistencies between simulated and real representations of the Raven-II. Such a development can expand the reach of surgical robotics research. Namely, providing end-to-end transparency between the simulated AMBF and physical Raven-II platforms enables a software testbed previously unavailable, e.g. for training real surgeons, for creating digital synthetic datasets, or for prototyping novel architectures like shared control strategies. Experiments validate this transparency by comparing joint trajectories between digital twin and physical testbed given identical inputs. This work may be extended and incorporated into recent efforts in developing modular or common software infrastructures for both simulation and control of real robotic devices, such as the Collaborative Robotics Toolkit (CRTK). 

ABSTRACT Cochlear hair cell stereocilia bundles are key organelles required for normal hearing. Often, deafness mutations cause aberrant stereocilia heights or morphology that are visually apparent but challenging to quantify. Actin-based structures, stereocilia are easily and most often labeled with phalloidin then imaged with 3D confocal microscopy. Unfortunately, phalloidin non-specifically labels all the actin in the tissue and cells and therefore results in a challenging segmentation task wherein the stereocilia phalloidin signal must be separated from the rest of the tissue. This can require many hours of manual human effort for each 3D confocal image stack. Currently, there are no existing software pipelines that provide an end-to-end automated solution for 3D stereocilia bundle instance segmentation. Here we introduce VASCilia, a Napari plugin designed to automatically generate 3D instance segmentation and analysis of 3D confocal images of cochlear hair cell stereocilia bundles stained with phalloidin. This plugin combines user-friendly manual controls with advanced deep learning-based features to streamline analyses. With VASCilia, users can begin their analysis by loading image stacks. The software automatically preprocesses these samples and displays them in Napari. At this stage, users can select their desired range of z-slices, adjust their orientation, and initiate 3D instance segmentation. After segmentation, users can remove any undesired regions and obtain measurements including volume, centroids, and surface area. VASCilia introduces unique features that measures bundle heights, determines their orientation with respect to planar polarity axis, and quantifies the fluorescence intensity within each bundle. The plugin is also equipped with trained deep learning models that differentiate between inner hair cells and outer hair cells and predicts their tonotopic position within the cochlea spiral. Additionally, the plugin includes a training section that allows other laboratories to fine-tune our model with their own data, provides responsive mechanisms for manual corrections through event-handlers that check user actions, and allows users to share their analyses by uploading a pickle file containing all intermediate results. We believe this software will become a valuable resource for the cochlea research community, which has traditionally lacked specialized deep learning-based tools for obtaining high-throughput image quantitation. Furthermore, we plan to release our code along with a manually annotated dataset that includes approximately 55 3D stacks featuring instance segmentation. This dataset comprises a total of 1,870 instances of hair cells, distributed between 410 inner hair cells and 1,460 outer hair cells, all annotated in 3D. As the first open-source dataset of its kind, we aim to establish a foundational resource for constructing a comprehensive atlas of cochlea hair cell images. Together, this open-source tool will greatly accelerate the analysis of stereocilia bundles and demonstrates the power of deep learning-based algorithms for challenging segmentation tasks in biological imaging research. Ultimately, this initiative will support the development of foundational models adaptable to various species, markers, and imaging scales to advance and accelerate research within the cochlea research community. 

Abstract Bio-inspired flying robots (BIFRs) which fly by flapping their wings experience continuously oscillating aerodynamic forces. These oscillations in the driving force cause vibrations in the motion of the body around the mean trajectory. In other words, a hovering BIFR does not remain fixed in space; instead, it undergoes oscillatory motion in almost all directions around the stationary point. These oscillations affect the aerodynamic performance of the flier. Assessing the effect of these oscillations, particularly on thrust generation in two-winged and four-winged BIFRs, is the main objective of this work. To achieve such a goal, two experimental setups were considered to measure the average thrust for the two BIFRs. The average thrust is measured over the flapping cycle of the BIFRs. In the first experimental setup, the BIFR is installed at the end of a pendulum rod, in place of the pendulum mass. While flapping, the model creates a thrust force that raises the model along the circular trajectory of the pendulum mass to a certain angular position, which is an equilibrium point and is also stable. Measuring the weight of the BIFR and the equilibrium angle it obtains, it is straightforward to estimate the average thrust, by moment balance about the pendulum hinge. This pendulum setup allows the BIFR model to freely oscillate back and forth along the circular trajectory about the equilibrium position. As such, the estimated average thrust includes the effects of these self-induced vibrations. In contrast, we use another setup with a load cell to measure thrust where the model is completely fixed. The thrust measurement revealed that the load cell or the fixed test leads to a higher thrust than the pendulum or the oscillatory test for the two-winged model, showing the opposite behavior for the four-winged model. That is, self-induced vibrations have different effects on the two BIFR models. We felt that this observation is worth further investigation. It is important to mention that aerodynamic mechanisms for thrust generation in the two and four-winged models are different. A two-winged BIFR generates thrust through traditional flapping mechanisms whereas a four-winged model enjoys a clapping effect, which results from wing-wing interaction. In the present work, we use a motion capture system, aerodynamic modeling, and flow visualization to study the underlying physics of the observed different behaviors of the two flapping models. The study revealed that the interaction of the vortices with the flapping wing robots may play a role in the observed aerodynamic behavior of the two BIFRs.