FMP / HCI / NAMAN MEHRAA CAMERA THAT LISTENS

Soundscene®

A physical study in
machine listening.

Scroll to listen
SOUNDSCENE / PROTOTYPE INTERPRETATION / 2026
[ 01 / THE QUESTION ]

We photograph
what we see.
What about what
we hear?

Wind. A passing bus. Someone laughing. A place has a sound, but the usual souvenir leaves it behind.

Soundscene explores how machine listening turns that atmosphere into an image. Sound Polaroid gives the question a physical form: an object that listens, interprets and prints.

Project
Final major project
Discipline
Human-computer interaction
My role
Concept, interaction & prototyping
Output
A listening-to-print prototype
[ 02 / THE TRANSLATION ]THREE ACTS. ONE SOUVENIR.
01 / CAPTURE

A place.

Ambient sound becomes the starting point. Traffic, voices, wind and footsteps: the parts of a place a photograph leaves out.

Sound Polaroid prototype held during the documented Westminster field session
[ OUTPUT / IN THE FIELD ]

Press play.
Keep listening.

One button, ten seconds, one interpreted souvenir.

[ 03 / FIELD NOTES ]

Behind the souvenir.

01

A camera that listens

A place is not only remembered through images. It is remembered through voices, birds, traffic, footsteps, wind, water, echo and silence.

Sound Polaroid is a handheld device that photographs a place by listening to it. Press one button: it records ten seconds of ambient sound, works out what it thinks it heard, turns those detections into a readable prompt, generates an image from that prompt, and prints the result on thermal paper.

It is the physical form of Soundscene, my final major project — which asks what happens when a machine listens to a place, simplifies it, interprets it, and makes something visual from that listening.

02

The HCI question behind the object

Sound Polaroid is the physical part of Soundscene, my final major project. The research question is not simply whether sound can generate an image. It is how a person understands, questions and relates to the interpretation a machine makes of a place.

The device makes that translation tangible. Sound becomes labels, labels become a prompt, and the prompt becomes a souvenir. Each step introduces choices and loses information. Showing those steps gives the person something to inspect rather than presenting the final picture as a faithful record.

03

The problem with the default souvenir

The usual way to keep a moment is to raise a phone, frame it, retake it and check the screen — and the result looks like everyone else's photograph of the same spot.

I wanted a capture device that records atmosphere rather than appearance. And I wanted to do it without quietly shipping people's private ambient audio to a black box that hands back a polished picture with no explanation.

Abstract artwork for the project: listening rendered as image.
Abstract artwork for the project: listening rendered as image.
04

The translation chain

Place → ambient sound → detected labels → authored visual mapping → prompt → generated image → print.

Every stage changes the original moment. Most systems hide that; this one shows it. A dense soundscape collapses into three words — traffic, speech, birds — and that collapse is the interesting part of the project, not the embarrassing part.

[ KEY INTERFACE SCREENS ]
Sound Polaroid interface flow
Sound Polaroid interface flow
Sound Polaroid screen during capture
Sound Polaroid screen during capture
Sound Polaroid print layout
Sound Polaroid print layout