Guitar-related machine listening research involves tasks like timbre transfer, performance generation, and automatic transcription. However, small datasets often limit model robustness due to insufficient acoustic diversity and musical content. To address these issues, we introduce Guitar-TECHS, a comprehensive dataset featuring a variety of guitar techniques, musical excerpts, chords, and scales. These elements are performed by diverse musicians across various recording settings. Guitar-TECHS incorporates recordings from two stereo microphones: an egocentric microphone positioned on the performer’s head and an exocentric microphone placed in front of the performer. It also includes direct input recordings and microphoned amplifier outputs, offering a wide spectrum of audio inputs and recording qualities. All signals and MIDI labels are properly synchronized. Its multi-perspective and multi-modal content makes Guitar-TECHS a valuable resource for advancing data-driven guitar research, and to develop robust guitar listening algorithms. We provide empirical data to demonstrate the dataset’s effectiveness in training robust models for Guitar Tablature Transcription.

Realistic spatial audio rendering improves immersion in virtual environments. However, the computational complexity of acoustic propagation increases linearly with the number of sources. Consequently, real-time accurate acoustic rendering becomes challenging in highly dynamic scenarios such as virtual and augmented reality (VR/AR). Exploiting the fact that human spatial sensitivity of acoustic sources is not equal at azimuth eccentricities in the horizontal plane, we introduce a perceptually-aware acoustic "foveation" guidance model to the audio rendering pipeline, which can integrate audio sources that are not spatially resolvable by human listeners. To this end, we first conduct a series of psychophysical studies to measure the minimum resolvable audible angular distance under various spatial and background conditions. We leverage this data to derive an azimuth-characterized real-time acoustic foveation algorithm. Numerical analysis and subjective user studies in VR environments demonstrate our method’s effectiveness in significantly reducing acoustic rendering workload, without compromising users’ spatial perception of audio sources. We believe that the presented research will motivate future investigation into the new frontier of modeling and leveraging human multimodal perceptual limitations — beyond the extensively studied visual acuity — for designing efficient VR/AR systems.

The concept of an intelligent augmented reality (AR) assistant has significant, wide-ranging applications, with potential uses in medicine, military, and mechanics domains. Such an assistant must be able to perceive the environment and actions, reason about the environment state in relation to a given task, and seamlessly interact with the task performer. These interactions typically involve an AR headset equipped with sensors which capture video, audio, and haptic feedback. Previous works have sought to facilitate the development of intelligent AR assistants by visualizing these sensor data streams in conjunction with the assistant's perception and reasoning model outputs. However, existing visual analytics systems do not focus on user modeling or include biometric data, and are only capable of visualizing a single task session for a single performer at a time. Moreover, they typically assume a task involves linear progression from one step to the next. We propose a visual analytics system that allows users to compare performance during multiple task sessions, focusing on non-linear tasks where different step sequences can lead to success. In particular, we design visualizations for understanding user behavior through functional near-infrared spectroscopy (fNIRS) data as a proxy for perception, attention, and memory as well as corresponding motion data (acceleration, angular velocity, and gaze). We distill these insights into embedding representations that allow users to easily select groups of sessions with similar behaviors. We provide two case studies that demonstrate how to use these visualizations to gain insights about task performance using data collected during helicopter copilot training tasks. Finally, we evaluate our approach through an in-depth examination of a think-aloud experiment with five domain experts.

Sound event localization and detection (SELD) is an important task in machine listening. Major advancements rely on simulated data with sound events in specific rooms and strong spatio-temporal labels. SELD data is simulated by convolving spatialy-localized room impulse responses (RIRs) with sound waveforms to place sound events in a soundscape. However, RIRs require manual collection in specific rooms. We present SpatialScaper, a library for SELD data simulation and augmentation. Compared to existing tools, SpatialScaper emulates virtual rooms via parameters such as size and wall absorption. This allows for parameterized placement (including movement) of foreground and background sound sources. SpatialScaper also includes data augmentation pipelines that can be applied to existing SELD data. As a case study, we use SpatialScaper to add rooms to the DCASE SELD data. Training a model with our data led to progressive performance improves as a direct function of acoustic diversity. These results show that SpatialScaper is valuable to train robust SELD models.

Direction of arrival estimation (DoAE) aims at tracking a sound in azimuth and elevation. Recent advancements include data-driven models with inputs derived from ambisonics intensity vectors or correlations between channels in a microphone array. A spherical intensity map (SIM), or acoustic image, is an alternative input representation that remains underexplored. SIMs benefit from high-resolution microphone arrays, yet most DoAE datasets use low-resolution ones. Therefore, we first propose a super-resolution method to upsample low-resolution microphones. Next, we benchmark DoAE models that use SIMs as input. We arrive to a model that uses SIMs for DoAE estimation and outperforms a baseline and a state-of-the-art model. Our study highlights the relevance of acoustic imaging for DoAE tasks.

The concept of augmented reality (AR) assistants has captured the human imagination for decades, becoming a staple of modern science fiction. To pursue this goal, it is necessary to develop artificial intelligence (AI)-based methods that simultaneously perceive the 3D environment, reason about physical tasks, and model the performer, all in real-time. Within this framework, a wide variety of sensors are needed to generate data across different modalities, such as audio, video, depth, speech, and time-of-flight. The required sensors are typically part of the AR headset, providing performer sensing and interaction through visual, audio, and haptic feedback. AI assistants not only record the performer as they perform activities, but also require machine learning (ML) models to understand and assist the performer as they interact with the physical world. Therefore, developing such assistants is a challenging task. We propose ARGUS, a visual analytics system to support the development of intelligent AR assistants. Our system was designed as part of a multi-year-long collaboration between visualization researchers and ML and AR experts. This co-design process has led to advances in the visualization of ML in AR. Our system allows for online visualization of object, action, and step detection as well as offline analysis of previously recorded AR sessions. It visualizes not only the multimodal sensor data streams but also the output of the ML models. This allows developers to gain insights into the performer activities as well as the ML models, helping them troubleshoot, improve, and fine-tune the components of the AR assistant.

Automatic Synthesizer Programming is the task of transforming an audio signal that was generated from a virtual instrument, into the parameters of a sound synthesizer that would generate this signal. In the past, this could only be done for one virtual instrument. In this paper, we expand the current literature by exploring approaches to automatic synthesizer programming for multiple virtual instruments. Two different approaches to multi-task automatic synthesizer programming are presented. We find that the joint-decoder approach performs best. We also evaluate the performance of this model for different timbre instruments and different latent dimension sizes.

A musician's spontaneous rate of movement, called spontaneous motor tempo (SMT), can be measured while spontaneously playing a simple melody. Data shows that the SMT influences the musician's tempo and synchronization. In this study we present a model that captures these phenomena. We review the results from three previously-published studies: solo musical performance with a pacing metronome tempo that is different from the SMT, solo musical performance without a metronome at a tempo that is faster or slower than the SMT, and duet musical performance between musicians with matching or mismatching SMTs. These studies showed, respectively, that the asynchrony between the pacing metronome and the musician's tempo grew as a function of the difference between the metronome tempo and the musician's SMT, musicians drifted away from the initial tempo toward the SMT, and the absolute asynchronies were smaller if musicians had matching SMTs. We hypothesize that the SMT constantly acts as a pulling force affecting musical actions at a tempo different from a musician's SMT. To test our hypothesis, we developed a model consisting of a non-linear oscillator with Hebbian tempo learning and a pulling force to the model's spontaneous frequency. While the model's spontaneous frequency emulates the SMT, elastic Hebbian learning allows for frequency learning to match a stimulus' frequency. To test our hypothesis, we first fit model parameters to match the data in the first of the three studies and asked whether this same model would explain the data the remaining two studies without further tuning. Results showed that the model's dynamics allowed it to explain all three experiments with the same set of parameters. Our theory offers a dynamical-systems explanation of how an individual's SMT affects synchronization in realistic music performance settings, and the model also enables predictions about performance settings not yet tested.

Dancing and playing music require people to coordinate actions with auditory rhythms. In laboratory perception-action coordination tasks, people are asked to synchronize taps with a metronome. When synchronizing with a metronome, people tend to anticipate stimulus onsets, tapping slightly before the stimulus. The anticipation tendency increases with longer stimulus periods of up to 3500ms, but is less pronounced in trained individuals like musicians compared to non-musicians. Furthermore, external factors influence the timing of tapping. These factors include the presence of auditory feedback from one's own taps, the presence of a partner performing coordinated joint tapping, and transmission latencies (TLs) between coordinating partners. Phenomena like the anticipation tendency can be explained by delay-coupled systems, which may be inherent to the sensorimotor system during perception-action coordination. Here we tested whether a dynamical systems model based on this hypothesis reproduces observed patterns of human synchronization. We simulated behavior with a model consisting of an oscillator receiving its own delayed activity as input. Three simulation experiments were conducted using previously-published behavioral data from 1) simple tapping, 2) two-person alternating beat-tapping, and 3) two-person alternating rhythm-clapping in the presence of a range of constant auditory TLs. In Experiment 1, our model replicated the larger anticipation observed for longer stimulus intervals and adjusting the amplitude of the delayed feedback reproduced the difference between musicians and non-musicians. In Experiment 2, by connecting two models we replicated the smaller anticipation observed in human joint tapping with bi-directional auditory feedback compared to joint tapping without feedback. In Experiment 3, we varied TLs between two models alternately receiving signals from one another. Results showed reciprocal lags at points of alternation, consistent with behavioral patterns. Overall, our model explains various anticipatory behaviors, and has potential to inform theories of adaptive human synchronization.