Andrew C. Singer

Adapting pretrained deep learning models to new and unknown environments remains a major challenge in underwater acoustic localization. We show that although the performance of pretrained models suffers from mismatch between the training and test data, they generally exhibit a higher uncertainty in environments where there is more mismatch. In addition, in the presence of environmental mismatch, spurious peaks can appear in the output of classification-based localization approaches, which inspires us to define and use a method to quantify the “implied uncertainty” based on the number of model output peaks. Leveraging this notion of implied uncertainty, we partition the test samples into sets with more certain and less certain samples, and implement a method to adapt the model to new environments by using the certain samples to improve the labeling for uncertain samples. Thus, using this efficient method for model uncertainty quantification, we showcase an innovative approach to adapt a pretrained model to unseen underwater environments at test time. This eliminates the need for labeled data from the target environment or the original training data. This adaptation is enhanced by integrating an independent estimate based on the received signal energy. We validate the approach extensively using real experimental data, as well as synthetic data consisting of model-generated signals with real ocean noise. The results demonstrate significant improvements in model prediction accuracy, underscoring the potential of the method to enhance underwater acoustic localization in diverse, noisy, and unknown environments.

In this paper, we propose a method to adapt a pre-trained deep-learning-based model for underwater acoustic localization to a new environment. We use unsupervised domain adaptation to improve the generalization performance of the model, i.e., using an unsupervised loss, fine-tune the pre-trained network parameters without access to any labels of the target environment or any data used to pre-train the model. This method improves the pre-trained model prediction by coupling that with an almost independent estimation based on the received signal energy (that depends on the source). We show the effectiveness of this approach on Bellhop generated data in an environment similar to that of the SWellEx-96 experiment contaminated with real ocean noise from the KAM11 experiment.

In this paper, we study the underwater acoustic localization in the presence of environmental mismatch. Especially, we exploit a pre-trained neural network for the acoustic wave propagation in a gradient-based optimization framework to estimate the source location. To alleviate the effect of mismatch between the training data and the test data, we simultaneously optimize over the network weights at the inference time, and provide conditions under which this method is effective. Moreover, we introduce a physics-inspired modularity in the forward model that enables us to learn the path lengths of the multipath structure in an end-to-end training manner without access to the specific path labels. We investigate the validity of the assumptions in a simple yet illustrative environment model.

Environment estimation is a challenging task in reverberant settings such as the underwater and indoor acoustic domains. The locations of reflective boundaries, for example, can be estimated using acoustic echoes and leveraged for subsequent, more accurate localization and mapping. Current boundary estimation methods are constrained to high signal-to-noise ratios or are customized to specific environments. Existing methods also often require a correct assignment of echoes to boundaries, which is difficult if spurious echoes are detected. To evade these limitations, a convolutional neural network (NN) method is developed for robust two-dimensional boundary estimation, given known emitter and receiver locations. A Hough transform-inspired algorithm is leveraged to transform echo times of arrival into images, which are amenable to multi-resolution regression by NNs. The same architecture is trained on transform images of different resolutions to obtain diverse NNs, deployed sequentially for increasingly refined boundary estimation. A correct echo labeling solution is not required, and the method is robust to reverberation. The proposed method is tested in simulation and for real data from a water tank, where it outperforms state-of-the-art alternatives. These results are encouraging for the future development of data-driven three-dimensional environment estimation with high practical value in underwater acoustic detection and tracking.

Wireless assistive listening devices (ALDs), such as induction loops, radio-frequency transmitters, and digital streaming systems, improve accessibility for people with hearing loss by transmitting from a venue’s sound system directly to the listener. Today, ALDs are used primarily for lectures and performances. When paired with advanced hearing devices, however, they could form part of an augmented listening system that lets users "remix" sounds in their environment, including from loudspeakers in public spaces. For example, users could amplify public announcements or suppress background music while having a conversation. In the proposed system, a binaural adaptive filter uses the ALD signal to estimate the loudspeaker sound at the ears. The hearing device can then either enhance or remove the loudspeaker sound in the hearing device output while preserving other nearby sounds. We demonstrate the proposed system using several commercial ALDs and assess the effects of delay, bandwidth, distortion, and noise on real-world system performance.

Underwater communication signals typically suffer from distortion due to motion-induced Doppler. Especially in shallow water environments, recovering the signal is challenging due to the time-varying Doppler effects distorting each path differently. However, conventional Doppler estimation algorithms typically model uniform Doppler across all paths and often fail to provide robust Doppler tracking in multipath environments. In this paper, we propose a dynamic programming-inspired method, called online segmented recursive least-squares (OSRLS) to sequentially estimate the time-varying non-uniform Doppler across different multipath arrivals. By approximating the non-linear time distortion as a piece-wise-linear Markov model, we formulate the problem in a dynamic programming framework known as segmented least-squares (SLS). In order to circumvent an ill-conditioned formulation, perturbations are added to the Doppler model during the linearization process. The successful operation of the algorithm is demonstrated in a simulation on a synthetic channel with time-varying non-uniform Doppler.

Some of my favorite homework problems are not homework problems at all, but, rather, more open-ended project-based assignments that elevate students' thinking toward the top of Bloom's Taxonomy. While some students may have the background to jump into a project-based assignment, most benefit from an increasing level of scaffolding. This not only brings all students to a common level from which they can develop a more coherent project, but it also provides multiple opportunities for them to solidify their understanding and build on curated, worked examples. This talk will explore two different types of courses, one theory-based and one experiential, each benefiting from a scaffolded framing for a more open-ended signal processing or data analysis project.

Modern listening devices come equipped with bone-conducted microphones (e.g.accelerometers) and conventional air-conducted microphones. With numerous active sound sources, the air-conducted microphones pick up the target sources alongside unwanted noise sources, while the contact microphones are robust to external noise. A drawback of contact microphones is that they are bandlimited. When a talker of interest has such a listening device then we can use its accelerometer to derive a spatio-temporal filter (beamformer) that estimates the desired source using a microphone array. However, different beamformers have varied performance across the frequency range of interest. If we have access to the output of multiple beamformers, then we would like to be able to combine them in a constructive manner. In this article, we present a frame-by-frame energy based method to combine multiple beamformers. The proposed method is evaluated in a real world environment with human talkers.

In underwater acoustic localization via matched-field-processing, given a propagation model and a suitable environmental parameterization, one searches for the

Passive localization and tracking of a mobile emitter, and joint learning of its reverberant three-dimensional (3D) acoustic environment, where critical structural features are unknown, is a key open problem. Unaccounted-for occluders are potentially present, so that the emitter can lose line-of-sight to the receivers, and can only be observed through its reflected raypaths. The locations of reflective boundaries must therefore be jointly estimated with the emitter's position. A multistage global optimization and tracking architecture is developed to solve this problem with a relatively unconstrained model. Each stage of this architecture establishes domain knowledge such as synchronization and initial environment estimation, which are inputs for the following stages of more refined algorithms. This approach is generalizable to different physical scales and modalities and improves on methods that do not exploit the motion of the emitter. In one stage of this architecture, particle swarm optimization is used to simultaneously estimate the environment and the emitter location. In another stage, a Hough transform-inspired boundary localization algorithm is extended to 3D settings, to establish an initial estimate of the environment. The performance of this holistic approach is analyzed and its reliability is demonstrated in a reverberant watertank testbed, which models the shallow-water underwater acoustic setting.