AES Europe 2026

Audio synchronization across heterogeneous media playback
devices is essential for delivering immersive sound
experiences in applications such as speaker group play;
multi-room audio playback. Existing synchronization
techniques predominantly rely on tightly coupled network
infrastructures; often embed a media sequence;
timestamp information to the media packet at the
transmitting source end, which restrict flexibility of
selecting the transmitting source; also compromises
robustness under dynamic network conditions. This paper
proposes a network; source independent audio
synchronization framework that eliminates dependency on
embedding media sequence; timestamps. The proposed
system employs an audio fingerprinting-based media
sequencing algorithm amongst the media playback devices
without relying on the type of transmitting source; the
network availability. A novel audio synchronization
algorithm is proposed which first determines a common
sequence start information given a dynamic media stream
from the transmitting source; then communicates the
fingerprint; timestamp amongst the media playback
devices without modifying the original audio packet
structure. Experimental results demonstrate that the
proposed approach achieves a high audio-audio
synchronization of less than 10ms across media playback
devices in a no network environment, thereby extending the
scope of immersive audio application irrespective of the
transmitting source.

We present a spectral-like reformulation of 2D ambisonics,
enabling an alternative representation of the sound field
in terms of amplitudes; phases. We hypothesise that it
simplifies the representation; creative manipulation of
2D ambisonics, beyond encoded directional point sources.

In 2D high-order ambisonics (HOA) of order N, a sound field
can be represented as a 2π-periodic angular function as a
combination of circular harmonics (Y_m) weighted by the
coefficients (a_m) with m ∈ [-N, N]. This representation
can be reformulated in terms of N+1 amplitudes; N
phases, similarly to a Fourier decomposition.

A simple example of this representation is the ambisonic
encoder at an angle theta. Phases are then multiples of a
phase phi = theta/2π, as frequencies are multiples of a
fundamental in harmonic sounds. Therefore, the
amplitude-phase approach can draw on the field of sound
synthesis, between harmonic; inharmonic modelling.
Operations on ambisonic vectors in amplitude-phase also
rely on Fourier representation, namely the spectral
convolution of two vectors (element-wise products of the
amplitudes, element-wise sums of the phases). Spectral
convolution has vast potential in ambisonics, allowing to
represent all the usual spatial operations (geometric;
transformative) in a simple manner.

To test this approach, we are currently developing an
ambisonic synthesiser based on Faust functions running in
Max environment. We are evaluating the scope of this
representation, both theoretical; compositional,;
then attempt to expand this approach to 3D ambisonics.

Immersive audio systems are increasingly deployed in
large-scale live music contexts, yet there is limited
research addressing how immersive concerts are perceived
; experienced by audiences. This paper presents a
practice-based; ethnographically informed study of the
immersive audio design; audience experience of the band
Heilung’s concert at Roskilde Festival, staged in the Arena
Tent where a large-scale multichannel loudspeaker system
including main, surround,; overhead arrays was used.
The study combines insights in technical system design;
pre-production methods with qualitative audience research
in order to explore how immersive sound alters perception,
embodiment,; social engagement in live concerts.
Pre-production involved scaled system simulations,
reference listening positions, timing strategies,;
power-matched test environments to translate an immersive
studio mix to a festival-scale venue. During; after the
concert, audience experience was investigated through
in-depth interviews, focus group discussions, participant
observation, binaural; ambisonic recordings,;
phenomenologically inspired interview techniques.
Findings indicate that immersive audio contributes to
heightened affective engagement, bodily involvement,; a
sense of envelopment that exceeds conventional stereo
concert experiences. Audience members described the
experience as multisensory, ritualistic,; spatially
ambiguous, often lacking technical vocabulary but
emphasizing embodied; emotional responses. Importantly,
immersion was not perceived as sound alone, but as emerging
from the interaction of sound, visuals, architecture,
social presence,; narrative framing.
The paper argues that understanding immersive concerts
requires the integration of anthropological insights with
audio engineering knowledge. While technical approaches
explain how immersive sound systems operate,
anthropological perspectives are essential for
understanding how such systems are experienced,
interpreted,; given meaning by audiences. The study
contributes to the limited body of research on the effects
of immersive concert formats by examining how audiences
perceive immersion; how they ascribe meaning to
immersive sound.

Join us to hear the finalists selected for this category of
the Student Recording Competition. We will hear their
presentations and recordings, and comments and feedback
from the judges. Award and prize placements will be
announced on the last day of the convention.

As spatial audio moves to a consumer standard, the demand
for sophisticated design frameworks has never been higher.
This panel brings together key contributors from the
recently published "Immersive Sound Volume II: The Design
and Practice of Binaural and Multi-Channel Experiences" to
bridge the gap between theoretical research and real-world
production. The session will explore the recent and
developing trends and practices of immersive audio,
focusing on the core design principles that define modern
binaural and multi-channel workflows. Panelists will
discuss themes from the text, including current guiding
principles and system design, and the creative practice of
building immersive sound experiences. Through a mix of case
studies and technical perspectives, the authors will
provide insights into a roadmap for engineers and creators
looking to master the immersive soundstage.

Loudspeaker monitoring is the reference when audio
professionals evaluate content. Headphones are also
important quality-checking tools; and many consumers enjoy
music using “close-fitting listening devices”, as all
different flavours of headphones are known in recent
standards writing.

We discuss the two reproduction methods from perceptual,
recording and mastering perspectives; especially
differences in timbre, imaging and auditory envelopment
when listening to stereo. Applications of headphones in
recording, when setting up and trimming stereo or 3D
microphone arrays, are also practically detailed.

In the last part of the workshop, attendees are invited to
personally compare the two domains on the qualities and
applications discussed; with guided listening to audio
examples between a pair of precision nearfield monitors,
Genelec 8351B, and a pair of excellent headphones, Audeze
CRBN2.

Generating 4pi acoustical atmosphere of a target space is
important for creating an immersive sound content. A
SBA-based reverb is a useful tool for this purpose. We
developed VSVerb, a SBA reverb that generates 4pi
reverberation from the virtual sound sources detected from
three orthogonal x-y-z sound intensities measured at the
target space. A virtual sound source, also known as a
mirror source, is an acoustic concept in geometrical
acoustics. According to this theory, many virtual sound
sources are considered to be located outside the room;
provide reflection sounds inside the room. Since the
spatial information of virtual sound sources is a kind of
fingerprint of a room’s reverberant characteristics,
correctly sampled virtual sound sources enables us to
recreate room's reverberation precisely.
Several methods have been proposed for detecting virtual
sound sources of a room, i.e., dominant reflection sounds
in a room, by using the spatial room impulse responses
(SRIRs). However, these methods have the disadvantage of
failing to detect small virtual sound sources that provide
late reflections, because they detect sources by focusing
on the peak amplitude values in SRIRs. It is difficult to
distinguish if a small peak in the latter part of SRIR
indicates the reflection or noise component. Additionally,
in low-band analysis, side robes of the band pass filter
add many large peaks to the SRIRs,; they make it
difficult to detect true reflection peaks.
To overcome these disadvantages of the conventional
methods, we developed a method that detects virtual sound
sources without using the amplitude characteristics of
SRIRs. We call this method “Speed Detection.” This method
detects virtual sound sources based on the spatial moving
speed of the sound intensity. Instead of measuring SRIRs of
the sound pressure, we measure SRIRs of x-y-z instantaneous
sound intensities. Since we can assume that the reflection
sound comes from a “certain-sized” virtual sound source
over a “certain period,” the sound intensity provided by
the virtual sound source is considered to remain within a
small area; move slowly while the source emits the
reflection sound. We focused on this behavior of sound
intensities; developed the new detection method.
First, we identify the portions of the sound intensity that
move slowly; isolate them as the “Source intensity.”
Then, we calculate the positions, strengths,; phase
characteristics of the virtual sound sources from these
Source intensities of the x, y,; z directions. We
examined Speed Detection method by generating several types
of 4pi reverbs from the virtual sound sources detected
using this method,; verified that it works well in many
cases. However, we have also found that it does not always
work well. We have realized the necessity of improving the
threshold value for classifying sound intensity into the
source intensity or other.
We have used to classify sound intensities into source
intensities; others by referring a threshold value,
vt=40(1000t+10)^1.5 [m/s], where t indicates the arrival
time [s] of the sound intensity. This equation is based on
our practical experience, rather than scientific facts. It
works well in most cases, but some adjustments are required
in very rare cases. To apply the threshold value to various
acoustical conditions of the target spaces, we propose
switching the threshold value from our conventional
equation to an averaged value using a time-varying time
window. To examine the newly proposed threshold value, we
conducted experiments on detecting virtual sound sources of
a simple rectangular room. The results demonstrated the
validity of the new threshold value. We expect this new
threshold value to improve the sound quality of VSVerb;
V2MA as well.

Recent advances in large-scale multichannel loudspeaker
systems have enabled immersive concert formats that extend
spatial control beyond conventional stereo; small
multichannel configurations. High-density loudspeaker
arrays (HDLAs) allow sound to be distributed across complex
architectural spaces, challenging established distinctions
between composition, performance,; live sound practice.
In live contexts, however, the realization of spatial
attributes is often constrained by system complexity,
limited rehearsal time,; the lack of artist-facing
spatial control interfaces. As a result, spatial
realization; sound diffusion are frequently delegated to
sound engineers, who translate artistic material to the
acoustic; architectural conditions of the venue in real
time.

This paper examines three immersive concerts presented
during Sonic Days 2025 in Denmark, realized on both
large-scale; small-scale multichannel loudspeaker
systems. The concerts represent contrasting production
contexts, including a site-specific spatial composition
conceived explicitly for a high-density loudspeaker array
; performances by artists whose practices are typically
oriented toward stereo or small multichannel formats.
Across these cases, spatialization functioned variously as
compositional material, interpretive layer,; adaptive
live-mixing practice.

The paper analyzes how control over spatial attributes is
negotiated between artists; sound engineers in live
immersive concert settings,; how this negotiation
affects the interpretation of artistic intent; audience
experience. Particular attention is given to the role of
sound engineers as active mediators whose decisions shape
spatial form, listening perspective,; the relationship
between sound; architecture. The findings suggest that
immersive concert formats redistribute creative agency
across artists, technicians,; technological
infrastructures,; point toward the need for revised
conceptual frameworks for authorship, performance,;
listening in large-scale spatial audio environments.

Virtual acoustics and active acoustic systems are
increasingly used in architectural acoustics to extend the
acoustic response of performance spaces. While these
technologies have traditionally been associated with
concert halls, theaters, and multipurpose venues, their
application has recently expanded to more controlled
environments such as recording studios and music production
spaces.

This tutorial introduces the fundamental principles of
virtual acoustics implemented through active acoustic
systems, starting from their role in architectural
acoustics and room acoustics enhancement. Basic concepts
such as room impulse responses, acoustical parameters,
system architectures, and feedback control strategies are
presented at an introductory level, with emphasis on common
practices and practical limitations. The discussion then
progressively narrows to the specific case of recording
studios, where virtual acoustics are used not only to
simulate performance spaces, but also to influence musical
performance, comfort, and interaction during recording
sessions, including the use of immersive microphone
techniques.

Through practical examples and listening demonstrations
developed at the Immersive Medial Laboratory in the
Department of Music Research of McGill University, the
tutorial illustrates how different virtual acoustic
conditions can be designed and applied in studio contexts,
highlighting their perceptual effects and implications for
musicians, recording engineers, and producers. The tutorial
aims to provide attendees with a clear conceptual framework
and practical insight into how virtual acoustics and active
sound reinforcement systems can be effectively employed
across architectural and studio applications, preparing the
audience for more advanced technical discussions on these
topics.

The acoustic characterisation of indoor spaces is crucial
for a wide range of applications. While global metrics
provide convenient descriptors of a room's overall
behaviour, a more spatially detailed analysis offers deeper
insight into the spatio-temporal structure of the sound
field, albeit at a higher experimental cost. This paper
proposes a methodology that leverages the predictive
capabilities of sound field reconstruction methods to
estimate room acoustic parameters as a function of
position. The approach is experimentally evaluated in an
auditorium, where it achieves accurate estimation of
temporal; energetic room acoustic parameters across the
entire audience area. In addition, the reconstructed field
yields higher intelligibility indices compared to the raw
measurements. Overall, these results highlight the
potential of sound field reconstruction techniques as a
practical tool for room acoustic characterisation; for
supporting assistive listening technologies.

This presentation develops a conceptual framework for
understanding how visitors cognize sound in museum
exhibitions. While sound increasingly features in museum
practice, research has focused primarily on measuring
visitor enjoyment; engagement rather than examining the
specific meanings sound generates. This gap reflects the
absence of a framework conceptualizing sound's
meaning-making capacities to guide empirical investigation.
Drawing on scholarship from music studies, semiotics,
phenomenology,; embodied cognition, I propose a
seven-component spectrum identifying distinct yet
interrelated meanings that sound can convey in museums:
aesthetic, representational, emotional, sensorial,
imaginative, social,; political. These meanings can be
apprehended independently or in combination, typically
through emergent, pre-conscious perception rather than
deliberate awareness.
The spectrum builds on the premise that museum sound
meaning-making unfolds through dynamics internalized from
early childhood as we attune to the world sonically. It
draws on the notion of sound as a "sonic aggregate"
(Grimshaw; Garner 2015)—encompassing social, contextual,
temporal,; embodied experiences—rather than reducing
sound to wave phenomena. Visitors actively co-produce
meanings by drawing on their moods, memories, knowledge,
; imagination during exhibition encounters.
Each meaning category is illustrated with exhibition case
studies, demonstrating the spectrum's applicability across
diverse sound-based multimodal museum practices—from
popular music exhibitions to sound art installations. The
spectrum aims to catalyze research through varied
methodological approaches; establish analytical
standards for studying sound in museums, with potential
adoption by international standardization bodies.

Join leaders in immersive audio who work with affinity
groups: women and miniorities who are building social
capital in audio in unexpected ways. Following the
"Credibilitizing" framework proposed by Dr Leslie
Gaston-Bird, the panel discussions how role models,
networking, and the right kind of mentoring opportunities
are helping people from underrepresented groups upskill,
innovate, and find new purpose and career pathways in
immersive audio.

Binaural audio delivered over headphones is currently the
most widely used method for experiencing immersive sound.
However, significant challenges remain in achieving the
highest possible quality of immersive listening through
current binaural delivery systems. Numerous technical
factors influence the listening experience, including the
personalisation of head-related transfer functions (HRTFs),
room simulation, head tracking, headphone type,
equalisation, etc. Beyond these technical considerations,
however, content types, production practices, and user
expectations and preferences also play critical roles in
shaping perceptual outcomes. Binaural audio is often
treated primarily as a post-processing technique for
simulating loudspeaker reproduction. Yet binaural
approaches also offer substantial creative opportunities
when considered from the earliest stages of content
production. This panel workshop will discuss these topics,
bringing together perspectives from creative practice,
research and development. The session will explore how
immersive listening experiences can be more effectively
designed, produced, and evaluated using binaural audio
technologies.

Prof. Li Dakang is a preeminent recording engineer and
pioneer of 3D recording of Chinese traditional music,
ancient instruments and spaces. Attendees are treated to a
selection of unique 3D recordings, including a new and
glorious version of China’s National Anthem. Prof. Li
describes the LDK-Cube for capturing the envelopment of an
acoustic space, and questions reliable reproduction of this
important quality.

This masterclass series, featuring remarkable recording
artists, is a chance to hear 3D audio at its best; as we
discuss qualities that make it truly worth the effort.

In each masterclass, we explore the new spatial
possibilities in recording and production, detailing also
this specific listening room, regarding ITU-R BS.1116
compliance and auditory envelopment (AEV) transparency.
Seats are limited to keep playback variation at bay.

This paper presents the perceptual evaluation of the Open Binaural Renderer (OBR), an open-source librarydeveloped for headphone-based rendering of Immersive Audio Model and Formats (IAMF) content. The evaluationfollowed an iterative framework in which findings from a pilot listening study informed the tuning of renderingprofiles, and the resulting renderer was benchmarked against established proprietary solutions. In the pilot study,19 expert listeners rated the Overall Listening Experience (OLE) of the initial prototype (OBRv1) and five externalrenderers across diverse audio content. Qualitative feedback was analysed using inductive coding to identify salientperceptual dimensions. The pilot revealed content-dependent performance and showed that a single default profilewas inadequate, yielding mixed responses in both the numerical scale and in the qualitative feedback and motivatingthe development of multiple rendering profiles in OBRv2. The main study evaluated two OBRv2 profiles targetingdifferent reverberation characteristics (Direct and Ambient) alongside three top-performing external renderers. Atotal of 39 participants, divided into expert and non-expert groups, rated five perceptual attributes: Voice Quality,Envelopment, Externalisation, Overall Listening Experience, and Timbral Balance. Mixed-design ANOVA revealedsignificant main effects of renderer condition on all attributes. Pairwise comparisons showed that OBRv2,Ambientachieved significantly higher OLE ratings than one proprietary renderer and reached statistical parity with theremaining two, representing a measurable improvement over the prototype. A trade-off between Voice Qualityand Externalisation was observed, driven by the level of reverberation in each renderer. The results demonstratethat iterative, perceptually informed tuning can yield competitive binaural rendering quality in an open-sourceframework.

Morten describes his excellent recording techniques, and
attendees are treated to
a unique selection of high resolution 3D music listening
examples.

This masterclass series, featuring remarkable recording
artists, is a chance to hear 3D audio at its best; as we
discuss qualities that make it truly worth the effort.

In each masterclass, we explore the new spatial
possibilities in recording and production, detailing also
this specific listening room, regarding ITU-R BS.1116
compliance and auditory envelopment (AEV) transparency.

Individualized head-related transfer functions (HRTFs)
require accurate pinna geometry, yet commodity multi-view
captures leave the ear region self-occluded; weakly
textured. We present a practical pipeline that couples
ear-centric acquisition with 3D Gaussian splatting (3DGS)
; the boundary element method (BEM) for complete HRTF
computation. The protocol augments horizontal views with
per-ear elevated captures under directional lighting; 3DGS
training with depth-distortion regularization yields
watertight meshes via truncated signed distance function
(TSDF) fusion. Standardized head coordinates; ear-canal
annotations interface the mesh with BEM. Experimental
evaluations demonstrate that our method achieves lower
ear-region geometric error; lower full-band spectral
distortion compared to existing image-based personalized
reconstruction baselines including AudioEar, NeuS,;
Metashape MVS.

This paper proposes a psychoacoustic-based audio-visual
mapping framework for intelligent vehicle cabins to enhance
immersion; stabilize spatial auditory perception. By
establishing mappings between auditory descriptors—such as
Direction of Arrival (DOA), spectral centroid,; temporal
envelope—and ambient lighting parameters, the framework
leverages "ambient vision" to augment the perceptual
experience without increasing the driver's cognitive load.
Theoretical analysis based on Stevens’ Power Law indicates
that the proposed mapping strategies effectively
synchronize audio-visual intensities; mitigate
perceptual fatigue, providing a conceptual reference for
future multisensory HMI design.

This paper presents a multichannel adaptive filtering
algorithm for real-time full-band adaptive transaural
reproduction on general-purpose hardware. It is based on a
multichannel frequency-domain FxLMS algorithm using an
overlap-save framework for both filtering; adaptation,
; is extended with (i) online plant identification for
fully adaptive operation, (ii) frequency-dependent
normalization for faster convergence,; (iii)
frequency-dependent regularization to stabilize adaptation.
The proposed algorithm is implemented in C language on a
standard desktop PC; evaluated on a 4x2 transaural
configuration running in real time at 48 kHz with 2048-tap
control filters. Two evaluation tests are conducted. The
first test consists of reproducing two uncorrelated
white-noise signals at the ears of a manikin using
crosstalk cancellation as the performance metric. An
average crosstalk cancellation of 32 dB over 100 Hz–20 kHz
is demonstrated. The second experiment considers binaural
signal reproduction as a more realistic use case of the
algorithm. In both cases, performance is assessed for both
a static listener; a moving listener scenario,
demonstrating the algorithm’s ability to rapidly re-adapt.

Binaural rendering is typically assessed via timbre;
localization accuracy, while its intrinsic spatial
resolution remains rarely quantified. This paper proposes a
perceptual evaluation method based on Minimum Audible Angle
(MAA) measurements to estimate the azimuthal
just-noticeable difference (JND) introduced by binaural
rendering algorithms. We systematically compared several
rendering algorithms across eight reference azimuths using
two participant-allocation paradigms. The results show that
spatial resolution is significantly influenced by Ambisonic
order; choice of the rendering alrorithm, with MAA
thresholds systematically decreasing as the truncation
order increases. Furthermore, the propsed method
successfully captures physiological spatial characteristics
; identifies resolution limits imposed by reference
angles. While both participant-allocation paradigms yield
consistent qualitative trends, the repeated-measures design
provides superior data stability. These findings
demonstrate that the proposed MAA-based method is an
effective tool for quantifying the spatial resolution of
binaural rendering algorithms.

Richard is a multiple Grammy Award–winning recording
engineer and a specialist in acoustic music recording. His
work is focused primarily on classical, jazz, and film
score music. A selection of his immersive recordings will
be presented, accompanied by a discussion of the microphone
configurations and mixing decisions employed in each
example.

This masterclass series, featuring remarkable recording
artists, is a chance to hear 3D audio at its best; as we
discuss qualities that make it truly worth the effort.

In each masterclass, we explore the new spatial
possibilities in recording and production, detailing also
this specific listening room, regarding ITU-R BS.1116
compliance and auditory envelopment (AEV) transparency.
Seats are limited to keep playback variation at bay.

The evaluation of audio quality is important in the
development of immersive audio algorithms; reproduction
systems,; binaural models are often used for this as a
quick alternative to listening tests. Coloration (i.e.,
perceived loudness differences integrated across ears;
frequency) is one key quality aspect; however, the majority
of models used to predict coloration are often
oversimplified or are missing a dedicated binaural stage to
consider the relative contribution of the left; right
ear signals. A binaural coloration model is presented that
builds upon previous work; tests three different
approaches for its binaural stage. The proposed model is
evaluated in comparison with nine models that are
frequently used to predict coloration by using data from
five listening tests totaling 252 stimuli with various
audio contents; source positions. The proposed model
performed best with 85% of explained variance, followed by
predictions based on ISO 532-1 loudness, yielding 78%
explained variance. The commonly used log-spectral distance
performed worst, with only 44% explained variance. The
three tested binaural stages had little influence on the
performance of the proposed model. The model is made freely
available to download.

This study evaluates three Next-Generation Audio (NGA)
rendering systems through listening tests using real-life
audio content. The testing paradigm prioritized subjective
preference over adherence to a ground-truth reference.
Participants assessed perceptual spatial audio attributes
in both 5.1; 7.1.4 loudspeaker setups. The findings
suggest that strict adherence to the rendering algorithm
used during content creation is not mandatory in terms of
listener preference. While not advocating disregarding
artistic intent without consideration, this study proposes
that such flexibility in reproduction can be an acceptable
compromise.

Immersive audio continues to expand beyond traditional
studio; terrestrial field-recording environments, yet
underwater soundscapes—particularly those involving marine
mammals—remain largely documented in mono or stereo
formats. This paper presents a practical; low-cost
approach for capturing immersive underwater audio using a
newly developed wideband hydrophone; a multichannel
array optimized for marine environments. The hydrophones,
designed by the author, feature a low noise floor, extended
frequency response exceeding 100 kHz,; direct
compatibility with standard P48 phantom-powered audio
recorders, enabling deployment without specialized
underwater preamplifiers or power systems.

To translate established immersive recording techniques
into the ocean environment, an array architecture was
developed based on a compact eight-element cube geometry.
Two array variants were constructed to account for the
significantly higher speed of sound in water compared to
air, allowing the spatial characteristics of underwater
sources to be captured with appropriate inter-element
spacing. Field recordings were conducted off the coast of
Hawaii in January during the peak season for humpback whale
song. Recordings were made at multiple depths; positions
to explore variations in reverberation, propagation,;
ambient biological activity.

Preliminary results indicate that the system captures
detailed spatial cues from humpback whale vocalizations
while simultaneously preserving the rich ambient marine
soundscape. The extended ultrasonic response further allows
slowed or pitch-shifted playback to reveal fine temporal
structures not typically audible. This work demonstrates a
feasible method for immersive underwater recording;
provides a foundation for both scientific research;
creative content production.

‘Nexus Sonance’ is a unique sonic space that is dependent
on time, place, and the people interacting with the
installation. At its core, the concept is a sonic portal
where the Cosmos, Earth, and Humans are unified through
sound in a single location. For this iteration of this
project, we decided to focus on real-time satellite data
sonification and put it as the core concept as our network
makes it possible to collaborate with ESA (European Space
Agency) therefore by sonifying real-time satellite data, we
create an evolving spatial environment where cosmic events
are felt and heard in the present moment.

This installation applies innovative machine-learning based
synthesis techniques with immersive spatial audio to embody
the experience of these unstoppable physical forces,
harnessing real-time satellite and geomagnetic data
provided by the European Space Agency (ESA), by simulating
neural network model corruption via cosmic radiation
following real-time patterns transmitted by the L1
satellite cluster.

While the cosmos is traditionally conceptualized through
heavily processed and "colorized" visual imagery, this
installation shifts the lens to a sonic perspective. Here,
the positioning and synthesis of sound are governed by
live-data streams from orbital satellites and global
geomagnetic stations, creating an immersive environment
where the listener experiences a unique, time-bound sonic
representation of our solar system. As our lives are
increasingly dependent on machine learning and neural
networks whose fundamentals are based on binary forms of
data, introducing the concept of cosmic radiation and data
corruption (based on a Single Event Upset phenomenon)
throughout the duration of the work references the idea of
Entropy as ever changing and expanding state.

Using an ESA-provided data from satellites that measure
specific states of solar weather, namely the Interplanetary
Magnetic Field (IMF) measurements including such variables
as Bt (the total induction of the IMF) which are assigned
to parameters such as intensity, saturation and amount of
the created sonic particles. Other variables include Bx,
By, Bz that compose a 3D magnetic force field measurements
are translatable to positioning, velocity of travel, and
direction of travel. In case ESA could not provide such
data, a backup plan is to use publicly available data from
https://norlys.live/rtsw. Furthermore, with data from L1
ESA-operated satellites, the readings regarding cosmic
radiation flux in space could be used to train a model
predicting the Single Event Upsets (SEU) and simulate
events that impacts the way that RAVE (Ircam) outputs
audio. This creates a metaphorical and literal decay of the
machine-learning output, mirroring the impact of radiation
on digital infrastructure

The earth and human layers that sit as a canvas background,
are a pre-sculpted soundscapes in combination with RAVEs
generative output that is trained on a private collection
of earth recordings (using geophones) and spatial audio
recordings of Georgian Polyphonic Choir “Adilei” which
symbolises the earth and human element within the
spatial-sonic setting. Furthermore, using publicly
available data on geomagnetic changes across the globe
through an intermagnet.org website with a MagPy package, we
are able to influence the textural output of the RAVE where
the changes are related to the positioning of the actual
reading stations. This way achieving a multi-layered sonic
representation of earth’s constantly changing geomagnetic
field, which in combination with real-time space weather
sonification in spatial audio creates a complex and
innovative spatial soundscape that is driven predominantly
by real-time data, meaning, that every time the work is
presented, the outcome is unique, depending on the
circumstances under which it is played.