Nirupam Roy

Harshvardhan C. Takawale, Nirupam Roy, Phil Brown

Accurate modeling of spatial acoustics is critical for immersive and intelligible audio in confined, resonant environments such as car cabins. Current tuning methods are manual, hardware-intensive, and static, failing to account for frequency selective behaviors and dynamic changes like passenger presence or seat adjustments. To address this issue, we propose INFER: Implicit Neural Frequency Response fields, a frequency-domain neural framework that is jointly conditioned on source and receiver positions, orientations to directly learn complex-valued frequency response fields inside confined, resonant environments like car cabins. We introduce three key innovations over current neural acoustic modeling methods: (1) novel end-to-end frequency-domain forward model that directly learns the frequency response field and frequency-specific attenuation in 3D space; (2) perceptual and hardware-aware spectral supervision that emphasizes critical auditory frequency bands and deemphasizes unstable crossover regions; and (3) a physics-based Kramers-Kronig consistency constraint that regularizes frequency-dependent attenuation and delay. We evaluate our method over real-world data collected in multiple car cabins. Our approach significantly outperforms time- and hybrid-domain baselines on both simulated and real-world automotive datasets, cutting average magnitude and phase reconstruction errors by over 39% and 51%, respectively. INFER sets a new state-of-the-art for neural acoustic modeling in automotive spaces

Ayushi Mishra, Yang Bai, Priyadarshan Narayanasamy et al.

Integrating spatial context into large language models (LLMs) has the potential to revolutionize human-computer interaction, particularly in wearable devices. In this work, we present a novel system architecture that incorporates spatial speech understanding into LLMs, enabling contextually aware and adaptive applications for wearable technologies. Our approach leverages microstructure-based spatial sensing to extract precise Direction of Arrival (DoA) information using a monaural microphone. To address the lack of existing dataset for microstructure-assisted speech recordings, we synthetically create a dataset called OmniTalk by using the LibriSpeech dataset. This spatial information is fused with linguistic embeddings from OpenAI's Whisper model, allowing each modality to learn complementary contextual representations. The fused embeddings are aligned with the input space of LLaMA-3.2 3B model and fine-tuned with lightweight adaptation technique LoRA to optimize for on-device processing. SING supports spatially-aware automatic speech recognition (ASR), achieving a mean error of $25.72^\circ$-a substantial improvement compared to the 88.52$^\circ$ median error in existing work-with a word error rate (WER) of 5.3. SING also supports soundscaping, for example, inference how many people were talking and their directions, with up to 5 people and a median DoA error of 16$^\circ$. Our system demonstrates superior performance in spatial speech understanding while addressing the challenges of power efficiency, privacy, and hardware constraints, paving the way for advanced applications in augmented reality, accessibility, and immersive experiences.

Harshvardhan Takawale, Nirupam Roy

In this paper, we introduce SpINR, a novel framework for volumetric reconstruction using Frequency-Modulated Continuous-Wave (FMCW) radar data. Traditional radar imaging techniques, such as backprojection, often assume ideal signal models and require dense aperture sampling, leading to limitations in resolution and generalization. To address these challenges, SpINR integrates a fully differentiable forward model that operates natively in the frequency domain with implicit neural representations (INRs). This integration leverages the linear relationship between beat frequency and scatterer distance inherent in FMCW radar systems, facilitating more efficient and accurate learning of scene geometry. Additionally, by computing outputs for only the relevant frequency bins, our forward model achieves greater computational efficiency compared to time-domain approaches that process the entire signal before transformation. Through extensive experiments, we demonstrate that SpINR significantly outperforms classical backprojection methods and existing learning-based approaches, achieving higher resolution and more accurate reconstructions of complex scenes. This work represents the first application of neural volumetic reconstruction in the radar domain, offering a promising direction for future research in radar-based imaging and perception systems.

Harshvardhan Takawale, Nirupam Roy

We present SpINRv2, a neural framework for high-fidelity volumetric reconstruction using Frequency-Modulated Continuous-Wave (FMCW) radar. Extending our prior work (SpINR), this version introduces enhancements that allow accurate learning under high start frequencies-where phase aliasing and sub-bin ambiguity become prominent. Our core contribution is a fully differentiable frequency-domain forward model that captures the complex radar response using closed-form synthesis, paired with an implicit neural representation (INR) for continuous volumetric scene modeling. Unlike time-domain baselines, SpINRv2 directly supervises the complex frequency spectrum, preserving spectral fidelity while drastically reducing computational overhead. Additionally, we introduce sparsity and smoothness regularization to disambiguate sub-bin ambiguities that arise at fine range resolutions. Experimental results show that SpINRv2 significantly outperforms both classical and learning-based baselines, especially under high-frequency regimes, establishing a new benchmark for neural radar-based 3D imaging.