Daniel Levi | Searcharxiv

arXiv2024

peerRTF: Robust MVDR Beamforming Using Graph Convolutional Network

Accurate and reliable identification of the relative transfer functions (RTFs) between microphones with respect to a desired source is an essential component in the design of microphone array beamformers, specifically when applying the minimum variance distortionless response (MVDR) criterion. Since an accurate estimation of the RTF in a noisy and reverberant environment is a cumbersome task, we aim at leveraging prior knowledge of the acoustic enclosure to robustify the RTFs estimation by learning the RTF manifold. In this paper, we present a novel robust RTF identification method, tested and trained using both real recordings and simulated scenarios, which relies on learning the RTF manifold using a graph convolutional network (GCN) to infer a robust representation of the RTFs in a confined area, and consequently enhance the beamformers performance.

eess.AS↗

arXiv2024

RevRIR: Joint Reverberant Speech and Room Impulse Response Embedding using Contrastive Learning with Application to Room Shape Classification

This paper focuses on room fingerprinting, a task involving the analysis of an audio recording to determine the specific volume and shape of the room in which it was captured. While it is relatively straightforward to determine the basic room parameters from the Room Impulse Responses (RIR), doing so from a speech signal is a cumbersome task. To address this challenge, we introduce a dual-encoder architecture that facilitates the estimation of room parameters directly from speech utterances. During pre-training, one encoder receives the RIR while the other processes the reverberant speech signal. A contrastive loss function is employed to embed the speech and the acoustic response jointly. In the fine-tuning stage, the specific classification task is trained. In the test phase, only the reverberant utterance is available, and its embedding is used for the task of room shape classification. The proposed scheme is extensively evaluated using simulated acoustic environments.

eess.AS↗