# Blind Estimation of Sub-band Acoustic Parameters from Ambisonics Recordings using Spectro-Spatial Covariance Features

arXiv: https://arxiv.org/abs/2411.03172 · HTML: https://mlsanity.com/paper/2411.03172/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 32 references that are in the map.
- First posted on arXiv 5 Nov 2024.

## Builds on (most cited first, 10 of 10)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Overview and Evaluation of Sound Event Localization and Detection in DCASE 2019](https://mlsanity.com/paper/2009.02792/) (2020)
- [Spatial LibriSpeech: An Augmented Dataset for Spatial Audio Learning](https://mlsanity.com/paper/2308.09514/) (2023)
- [A Universal Deep Room Acoustics Estimator](https://mlsanity.com/paper/2109.14436/) (2021)
- [Direction of Arrival Estimation of Noisy Speech Using Convolutional Recurrent Neural Networks with Higher-Order Ambisonics Signals](https://mlsanity.com/paper/2102.09853/) (2021)
- [Blind Room Parameter Estimation Using Multiple-Multichannel Speech Recordings](https://mlsanity.com/paper/2107.13832/) (2021)
- [Blind Acoustic Room Parameter Estimation Using Phase Features](https://mlsanity.com/paper/2303.07449/) (2023)
- [Binaural Selective Attention Model for Target Speaker Extraction](https://mlsanity.com/paper/2406.12236/) (2024)
- [Signal-Aware Direction-of-Arrival Estimation Using Attention Mechanisms](https://mlsanity.com/paper/2201.00503/) (2022)

## Built on by (most cited first, 1 of 1)

- [SPUR: A Plug-and-Play Framework for Integrating Spatial Audio Understanding and Reasoning into Large Audio-Language Models](https://mlsanity.com/paper/2511.06606/) (2025)

## Abstract (arXiv)

Estimating frequency-varying acoustic parameters is essential for enhancing immersive perception in realistic spatial audio creation. In this paper, we propose a unified framework that blindly estimates reverberation time (T60), direct-to-reverberant ratio (DRR), and clarity (C50) across 10 frequency bands using first-order Ambisonics (FOA) speech recordings as inputs. The proposed framework utilizes a novel feature named Spectro-Spatial Covariance Vector (SSCV), efficiently representing temporal, spectral as well as spatial information of the FOA signal. Our models significantly outperform existing single-channel methods with only spectral information, reducing estimation errors by more than half for all three acoustic parameters. Additionally, we introduce FOA-Conv3D, a novel back-end network for effectively utilising the SSCV feature with a 3D convolutional encoder. FOA-Conv3D outperforms the convolutional neural network (CNN) and recurrent convolutional neural network (CRNN) backends, achieving lower estimation errors and accounting for a higher proportion of variance (PoV) for all 3 acoustic parameters.