On the Usefulness of Diffusion-Based Room Impulse Response Interpolation to Microphone Array Processing

Sagi Della Torre; Mirco Pezzoli; Fabio Antonacci; Sharon Gannot

cs.SDMar 30, 2026

On the Usefulness of Diffusion-Based Room Impulse Response Interpolation to Microphone Array Processing

Authors: Sagi Della Torre, Mirco Pezzoli, Fabio Antonacci, Sharon Gannot

Organizations: Bar-Ilan University, Israel · Politecnico di Milano, Italy

Abstract

Room Impulse Responses estimation is a fundamental problem in spatial audio processing and speech enhancement. In this paper, we build upon our previously introduced diffusion-based inpainting framework for Room Impulse Response interpolation and demonstrate its applicability to enhancing the performance of practical multi-microphone array processing tasks. Furthermore, we validate the robustness of this method in interpolating real-world Room Impulse Responses.

Figures & tables

Fig. 1 : System block diagram: Diffusion-based RIR reconstruction followed by beamforming for speech enhancement.

Fig. 2 : Measured (blue) and missing (orange) microphones.

	Directional noise			Diffuse noise
Method	SIR [dB] $\uparrow$	SI-SDR [dB] $\uparrow$	STOI $\uparrow$	SIR [dB] $\uparrow$	SI-SDR [dB] $\uparrow$	STOI $\uparrow$
Mics	0	-4	0.59	0	-4	0.58
Full	12.2	9	0.88	6.2	10.2	0.79
Mask 0 - Missing	11	6	0.80	4.8	7	0.70
Mask 0 - Inpainted	12.3	8.8	0.88	6.2	10.1	0.79
Mask 1 - Missing	9.5	4.3	0.78	3.4	6	0.68

TABLE I : MVDR results averaged over all SNRs under directional and diffuse noise.

Dist( $\mathbf{h}$ , $\mathbf{\hat{h}}$ ) $\downarrow$	Mask 0	Mask 1	Mask 2	Mask 3
Inpainted (Ours)	0.02	0.05	0.19	0.52
Interpolated (SCI)	0.1	0.17	0.4	0.63

TABLE II : Alignment between interpolated and gound-truth RIR for proposed and baseline methods (best results in bold).

Fig. 3 : Geometric setup of the room with a source and the microphone array, taken from the MeshRIR dataset.

Panel of Figure 6 — Fig. 4 : NMSE and CD vs. mask ratio for Three Rows configuration.

Panel of Figure 7 — Fig. 5 : NMSE and CD vs. mask ratio for Frame configuration.

Fig. 6 : Three Rows array configuration: Measured (blue) and missing (orange) microphones.

Panel of Figure 9 — Fig. 7 : Comparison between reconstructed and ground-truth impulse responses and EDC for microphone #7.

Microphone Array Processing

See all 17 papers

Ambisonics Encoding of Room Impulse Responses using a Device-Agnostic Diffusion Model
Aug 14, 2026Eloi Moliner, Christoph Hold, Juan Azcarreta Ortiz +5Spatial Audio Room Acoustics
Reality Labs Research, Meta · Acoustics Lab, DICE, Aalto University, Espoo, Finland
Room Impulse Response Embeddings for Speech Enhancement in Noisy and Reverberant Environments
Sep 25, 2026Adrian Meise, Reinhold Haeb-UmbachRepresentation Learning Speech Enhancement
Paderborn University, Germany
Spherical Harmonic Sliced Wasserstein Displacement Interpolation for Acoustic Source and Reflection Density Modeling
Sep 18, 2026Yuancheng LuoSpatial Audio Sliced Wasserstein Distance
NuSpace Audio Cambridge, MA, USA

Aug 14, 2026J/K move · Enter open · S save

Ambisonics Encoding of Room Impulse Responses using a Device-Agnostic Diffusion Model

Eloi Moliner, Christoph Hold, Juan Azcarreta Ortiz, Sebastian Prepelita+4

Reality Labs Research, Meta · Acoustics Lab, DICE, Aalto University, Espoo, Finland

Spatial Audio Room Acoustics Inverse Problems Diffusion-Based Inverse Problems

Open paper AskPDF arXiv

We address the problem of encoding room impulse responses (RIRs) into high-order Ambisonics (HOA) representations from arbitrary and potentially insufficient or incomplete microphone array measurements. This task is fundamentally ill-posed for microphone arrays with limited spatial capture capabilities, such as irregular or sparse arrays, as classical linear methods fail to reconstruct high-order spatial detail. We introduce a diffusion-based generative framework that models the statistical properties of HOA RIRs. This enables device-agnostic encoding from arbitrary microphone arrays, potentially unseen during data measurement. Our approach incorporates a posterior sampling procedure that enforces consistency between the estimated signals and the measurements while plausibly reconstructing spatial information that is unobservable from the limited measurements alone. Experiments on simulated data demonstrate that our method outperforms linear and neural baselines, achieving accurate HOA RIR estimation up to 12th order. A listening test with binaural renderings, including both simulated and measured RIRs, further confirms that the proposed method yields higher perceptual similarity to reference Ambisonics RIRs than all baselines. The flexibility and accuracy of the proposed framework opens new possibilities for scalable acoustics simulations.

Abstract

Microphone Array Processing

Explore similar work

Ambisonics Encoding of Room Impulse Responses using a Device-Agnostic Diffusion Model

Room Impulse Response Embeddings for Speech Enhancement in Noisy and Reverberant Environments

Spherical Harmonic Sliced Wasserstein Displacement Interpolation for Acoustic Source and Reflection Density Modeling