EventOwner An Exact Marginal Pilot of Audio Visual Source Ownership

Two audio-visual pairs can contain the same global event inventory while assigning sounds to different visible sources. We construct a small procedural test that makes this relationship necessary for classification. Two event schedules drive rendered rotating objects and four-channel waveforms. Crossing video and audio ownership assignments gives four pairs per scene; every exact video and waveform occurs under both labels. A frozen confirmation study contains 120 scenes and 480 dependent pairs in held-out procedural families. A frequency-resolved joint diagnostic obtains balanced accuracy 0.806, compared with 0.771 for a broadband joint diagnostic, 0.500 for temporal synchrony, and 0.510 for pooled spatial coverage. Scene-cluster intervals preserve the repeated-pair structure. Both joint methods have identical paired-ranking accuracy of 0.996, and performance weakens under overlapping activity and near-colocation. An exploratory 72-window real-recording comparison is inconclusive and favors a simpler spatial reference. The result supports controlled joint construction and evaluation feasibility. It does not establish realistic acoustics, learned source understanding, or real transfer.

Authors

Publication Details

Journal
Preprints.org
Published
2026-11-03
DOI
https://doi.org/10.20944/preprints202611.0190.v1
Primary Topic
Music and Audio Processing
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
preprint

EventOwner An Exact Marginal Pilot of Audio Visual Source Ownership

Saurav Keshari Aryal
Preprints.org
Music and Audio Processing
preprint

EventOwner An Exact Marginal Pilot of Audio Visual Source Ownership

Saurav Keshari Aryal
preprint en

Abstract

Two audio-visual pairs can contain the same global event inventory while assigning sounds to different visible sources. We construct a small procedural test that makes this relationship necessary for classification. Two event schedules drive rendered rotating objects and four-channel waveforms. Crossing video and audio ownership assignments gives four pairs per scene; every exact video and waveform occurs under both labels. A frozen confirmation study contains 120 scenes and 480 dependent pairs in held-out procedural families. A frequency-resolved joint diagnostic obtains balanced accuracy 0.806, compared with 0.771 for a broadband joint diagnostic, 0.500 for temporal synchrony, and 0.510 for pooled spatial coverage. Scene-cluster intervals preserve the repeated-pair structure. Both joint methods have identical paired-ranking accuracy of 0.996, and performance weakens under overlapping activity and near-colocation. An exploratory 72-window real-recording comparison is inconclusive and favors a simpler spatial reference. The result supports controlled joint construction and evaluation feasibility. It does not establish realistic acoustics, learned source understanding, or real transfer.

Preprints.org
Music and Audio Processing
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon
EventOwner An Exact Marginal Pilot of Audio Visual Source Ownership — Saurav Keshari Aryal · Preprints.org (2026) | TGRS Research Map | TGRS