We introduce SoundVista, a method to generate the ambient sound of an arbitrary scene at novel viewpoints. Given a pre-acquired recording of the scene from sparsely distributed microphones, SoundVista can synthesize the sound of that scene from an unseen target viewpoint. The method learns the underlying acoustic transfer function that relates the signals acquired at the distributed microphones to the signal at the target viewpoint, using a limited number of known recordings. Unlike existing works, our method does not require constraints or prior knowledge of sound source details. Moreover, our method efficiently adapts to diverse room layouts, reference microphone configurations and unseen environments. To enable this, we introduce a visual-acoustic binding module that learns visual embeddings linked with local acoustic properties from panoramic RGB and depth data. We first leverage these embeddings to optimize the placement of reference microphones in any given scene. During synthesis, we leverage multiple embeddings extracted from reference locations to get adaptive weights for their contribution, conditioned on target viewpoint. We benchmark the task on both publicly available data and real-world settings. We demonstrate significant improvements over existing methods.

In mixed reality applications, a realistic acoustic experience in spatial environments is as crucial as the visual experience for achieving true immersion. Despite recent advances in neural approaches for Room Impulse Response (RIR) estimation, most existing methods are limited to the single environment on which they are trained, lacking the ability to generalize to new rooms with different geometries and surface materials. We aim to develop a unified model capable of reconstructing the spatial acoustic experience of any environment with minimum additional measurements. To this end, we present xRIR, a framework for cross-room RIR prediction. The core of our generalizable approach lies in combining a geometric feature extractor, which captures spatial context from panorama depth images, with a RIR encoder that extracts detailed acoustic features from only a few reference RIR samples. To evaluate our method, we introduce AcousticRooms, a new dataset featuring high-fidelity simulation of over 300,000 RIRs from 260 rooms. Experiments show that our method strongly outperforms a series of baselines. Furthermore, we successfully perform sim-to-real transfer by evaluating our model on four real-world environments, demonstrating the generalizability of our approach and the realism of our dataset.

Modern perception models, particularly those designed for multisensory egocentric tasks, have achieved remarkable performance but often come with substantial computational costs. These high demands pose challenges for real-world deployment, especially in resource-constrained environments. In this paper, we introduce EgoAdapt, a framework that adaptively performs cross-modal distillation and policy learning to enable efficient inference across different egocentric perception tasks, including egocentric action recognition, active speaker localization, and behavior anticipation. Our proposed policy module is adaptable to task-specific action spaces, making it broadly applicable. Experimental results on three challenging egocentric datasets EPIC-Kitchens, EasyCom, and Aria Everyday Activities demonstrate that our method significantly enhances efficiency, reducing GMACs by up to 89.09%, parameters up to 82.02%, and energy up to 9.6x, while still on-par and in many cases outperforming, the performance of corresponding state-of-the-art models.

In recent years, the thriving development of research related to egocentric videos has provided a unique perspective for the study of conversational interactions, where both visual and audio signals play a crucial role. While most prior work focus on learning about behaviors that directly involve the camera wearer, we introduce the Ego-Exocentric Conversational Graph Prediction problem, marking the first attempt to infer exocentric conversational interactions from egocentric videos. We propose a unified multi-modal framework-Audio- Visual Conversational Attention (AV-CONV), for the joint prediction of conversation behaviors-speaking and listening-for both the camera wearer as well as all other social partners present in the egocentric video. Specifically, we adopt the self-attention mechanism to model the representations across-time, across-subjects, and across-modalities. To validate our method, we conduct experiments on a challenging egocentric video dataset that includes multi-speaker and multi-conversation scenarios. Our results demonstrate the superior performance of our method compared to a series of baselines. We also present detailed ablation studies to assess the contribution of each component in our model. Check our Project Page.

Individuals with impaired hearing experience difficulty in conversations, especially in noisy environments. This difficulty often manifests as a change in behavior and may be captured via facial expressions, such as the expression of discomfort or fatigue. In this work, we build on this idea and introduce the problem of detecting hearing loss from an individual’s facial expressions during a conversation. Building machine learning models that can represent hearing-related facial expression changes is a challenge. In addition, models need to disentangle spurious age-related correlations from hearing-driven expressions. To this end, we propose a self-supervised pre-training strategy tailored for the modeling of expression variations. We also use adversarial representation learning to mitigate the age bias. We evaluate our approach on a large-scale egocentric dataset with realworld conversational scenarios involving subjects with hearing loss and show that our method for hearing loss detection achieves superior performance over baselines.

High fidelity spatial audio often performs better when produced using a personalized head-related transfer function (HRTF). However, the direct acquisition of HRTFs is cumbersome and requires specialized equipment. Thus, many personalization methods estimate HRTF features from easily obtained anthropometric features of the pinna, head, and torso. The first HRTF notch frequency (N1) is known to be a dominant feature in elevation localization, and thus a useful feature for HRTF personalization. This paper describes the prediction of N1 frequency from pinna anthropometry using a neural model. Prediction is performed separately on three databases, both simulated and measured, and then by domain mixing in-between the databases. The model successfully predicts N1 frequency for individual databases and by domain mixing between some databases. Prediction errors are better or comparable to those previously reported, showing significant improvement when acquired over a large database and with a larger output range.

Sound source localization is a key requirement for many assistive applications of augmented reality, such as speech enhancement. In conversational settings, potential sources of interest may be approximated by active speaker detection. However, localizing speakers in crowded, noisy environments is challenging, particularly without extensive ground truth annotations. Still, people are often able to communicate effectively in these scenarios through orienting behavioral responses, such as head motion and eye gaze, which have been shown to correlate with directions of auditory sources. In the absence of ground truth annotations, we propose joint training of egocentric audiovisual localization with behavioral pseudolabels to relate audiovisual stimuli with directional information extracted from future behavior. We evaluate this method as a technique for unsupervised egocentric active speaker localization and compare pseudolabels derived from head and gaze directions against fully-supervised alternatives.

We propose a novel approach for blind room impulse response (RIR) estimation systems in the context of a downstream application scenario, far-field automatic speech recognition (ASR). We first draw the connection between improved RIR estimation and improved ASR performance, as a means of evaluating neural RIR estimators. We then propose a generative adversarial network (GAN) based architecture that encodes RIR features from reverberant speech and constructs an RIR from the encoded features, and uses a novel energy decay relief loss to optimize for capturing energy-based properties of the input reverberant speech. We show that our model outperforms the state-of-the-art baselines on acoustic benchmarks (by 17% on the energy decay relief and 22% on an early-reflection energy metric), as well as in an ASR evaluation task (by 6.9% in word error rate).

A growing need for on-device machine learning has led to an increased interest in light-weight neural networks that lower model complexity while retaining performance. While a variety of general-purpose techniques exist in this context, very few approaches exploit domain-specific properties to further improve upon the capacity-performance trade-off. In this paper, extending our prior work [1], we train a network to emulate the behaviour of an audio codec and use this network to construct a loss. By approximating the psychoacoustic model underlying the codec, our approach enables light-weight neural networks to focus on perceptually relevant properties without wasting their limited capacity on imperceptible signal components. We adapt our method to two audio source separation tasks, demonstrate an improvement in performance for small-scale networks via listening tests, characterize the behaviour of the loss network in detail, and quantify the relationship between performance gain and model capacity. Our work illustrates the potential for incorporating perceptual principles into objective functions for neural networks.

The way we perceive a sound depends on many aspects- its ecological frequency, acoustic features, typicality, and most notably, its identified source. In this paper, we present the HCU400: a dataset of 402 sounds ranging from easily identifiable everyday sounds to intentionally obscured artificial ones. It aims to lower the barrier for the study of aural phenomenology as the largest available audio dataset to include an analysis of causal attribution. Each sample has been annotated with crowd-sourced descriptions, as well as familiarity, imageability, arousal, and valence ratings. We extend existing calculations of causal uncertainty, automating and generalizing them with word embeddings. Upon analysis we find that individuals will provide less polarized emotion ratings as a sound's source becomes increasingly ambiguous; individual ratings of familiarity and imageability, on the other hand, diverge as uncertainty increases despite a clear negative trend on average.

Generative audio models based on neural networks have led to considerable improvements across fields including speech enhancement, source separation, and text-to-speech synthesis. These systems are typically trained in a supervised fashion using simple element-wise l1 or l2 losses. However, because they do not capture properties of the human auditory system, such losses encourage modelling perceptually meaningless aspects of the output, wasting capacity and limiting performance. Additionally, while adversarial models have been employed to encourage outputs that are statistically indistinguishable from ground truth and have resulted in improvements in this regard, such losses do not need to explicitly model perception as their task; furthermore, training adversarial networks remains an unstable and slow process. In this work, we investigate an idea fundamentally rooted in psychoacoustics. We train a neural network to emulate an MP3 codec as a differentiable function. Feeding the output of a generative model through this MP3 function, we remove signal components that are perceptually irrelevant before computing a loss. To further stabilize gradient propagation, we employ intermediate layer outputs to define our loss, as found useful in image domain methods. Our experiments using an autoencoding task show an improvement over standard losses in listening tests, indicating the potential of psychoacoustically motivated models for audio generation.