English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Room geometry is important prior information for implementing realistic 3Daudio rendering. For this reason, various room geometry inference (RGI) methodshave been developed by utilizing the time of arrival (TOA) or time differenceof arrival (TDOA) information in room impulse responses. However, theconventional RGI technique poses several assumptions, such as convex roomshapes, the number of walls known in priori, and the visibility of first-orderreflections. In this work, we introduce the deep neural network (DNN), RGI-Net,which can estimate room geometries without the aforementioned assumptions.RGI-Net learns and exploits complex relationships between high-orderreflections in room impulse responses (RIRs) and, thus, can estimate roomshapes even when the shape is non-convex or first-order reflections are missingin the RIRs. The network takes RIRs measured from a compact audio deviceequipped with a circular microphone array and a single loudspeaker, whichgreatly improves its practical applicability. RGI-Net includes the evaluationnetwork that separately evaluates the presence probability of walls, so thegeometry inference is possible without prior knowledge of the number of walls.

RGI-Net: 3D Room Geometry Inference from Room Impulse Responses in the Absence of First-order Echoes