# Deep Learning Based Relative Transfer Matrix Estimation for Multiple Sources and Multiple Microphones

arXiv: https://arxiv.org/abs/2608.11627 · HTML: https://mlsanity.com/paper/2608.11627/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 38 references that are in the map.
- First posted on arXiv 12 Aug 2026.

## Builds on (most cited first, 7 of 7)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [McNet: Fuse Multiple Cues for Multichannel Speech Enhancement](https://mlsanity.com/paper/2211.08872/) (2022)
- [Learning Deep Direct-Path Relative Transfer Function for Binaural Sound Source Localization](https://mlsanity.com/paper/2202.07841/) (2022)
- [Manifold learning-supported estimation of relative transfer functions for spatial filtering](https://mlsanity.com/paper/2110.02189/) (2021)
- [Relative Transfer Function Vector Estimation for Acoustic Sensor Networks Exploiting Covariance Matrix Structure](https://mlsanity.com/paper/2310.18199/) (2023)
- [peerRTF: Robust MVDR Beamforming Using Graph Convolutional Network](https://mlsanity.com/paper/2407.01779/) (2024)
- [Relative Transfer Matrix Estimator using Covariance Subtraction](https://mlsanity.com/paper/2510.19439/) (2025)

## Abstract (arXiv)

The Relative Transfer Matrix (ReTM), recently introduced as a generalization of the relative transfer function for multiple receivers and sources, shows promising performance when applied to speech enhancement in noisy environments. Estimating the ReTM of sound sources by exploiting the covariance matrices of multichannel recordings is highly beneficial for practical applications and, to date, remains the only proposed approach. This paper investigates deep learning-based ReTM estimation. We propose three novel supervised learning frameworks using time and short-time frequency transform domain convolutional networks, and a Long Short-Term Memory-based recurrent neural network. Experimental results demonstrate that the proposed models achieve more accurate estimation of the ReTM using five objective metrics compared to the covariance-based method. We also show the effectiveness of the proposed frameworks for speech enhancement, achieving performance on par with the baseline method.