Norwegian version of this page

Traditional Arab Music Is Under Threat. New Research Takes Steps to Preserve it

Today's music technology favors Western popular music, a fact that technology and music researcher Fadi Al-Ghawanmeh could not accept.

Photo collage of two pictures of females with headphones looking out of a window.

Perception experiment with participants in Amman, Jordan and Oslo, Norway.
Photos: Fadi Al-Ghawanmeh

By Silje Pileberg
Published Oct. 8, 2025 - Last modified Oct. 8, 2025

AI’s growing presence in the music industry has raised alarm bells among those seeking to preserve musical diversity.

In his research, Fadi Al-Ghawanmeh has worked to prevent maqam, the traditional Arab musical practice that is tied to improvisation, from disappearing.

“Over time, we have seen Arab music come under threat from technology. Western-centric solutions have inadvertently contributed to a production bias and, consequently, a skewed musical taste within the Arab community,” he said.

More Than Ebony and Ivory

Portrait photo of Fadi Al-Ghawanmeh
Fadi defended his thesis on September 25. More information and link to the live stream here.
Photo: Melissa J. Scott.

As a young musician in his native country Jordan, he was introduced to MIDI (Musical Instrument Digital Interface), an industry standard established in 1983. MIDI records notes in a digital format, allowing synthesizers, drum machines, and other electronic instruments to communicate.

However, it includes only Western notes, the ones we know as the black and white keys on a piano – “ebony and ivory,” as Paul McCartney and Stevie Wonder famously sang.

Maqām includes so-called microtones, tones that fall between these notes.

“Since MIDI does not readily support the microtones in maqām, people – including musicians – have started to lose them,” Al-Ghawanmeh explained.

Created a Dataset of Arab Music

Since AI entered the world of music production, the threat has grown significantly. Today’s AI models are based on datasets mainly containing Western music. 

Al-Ghawanmeh decided to create a new dataset. Together with local musicians in Amman, the capital of Jordan, he captured hours of musical improvisations and developed a tool to convert them into textual datasets. 

He also created a machine learning model to generate music based on the dataset. 

In addition, he set out to investigate listeners in Oslo and Amman’s reactions to maq?m music. He wished to gain further knowledge about how maq?m can live on – even in cultures where the genre is not well known.

Two men, one playing the keyboard while the other sings.
Dataset construction session.
Photo: Fadi Al-Ghawanmeh

Detected Subtle Motion Made by the Body  

Participants in Oslo and Amman – 60 in total – listened to an eight-minute improvisation while wearing headphones equipped with built-in accelerometers: sensors that detect body motion. These subtle movements may occur unconsciously when we listen to music. 

“Previous research has shown a link between movement and musical experience. By collecting participants’ feedback after they listened and comparing their responses with the data from their body movements, we were able to confirm this connection,” Al-Ghawanmeh said. 

In both Oslo and Amman, movement increased in response to musical tension and rhythmic percussion. However, participants in Oslo moved significantly less than in Amman. 

According to Al-Ghawanmeh, this is not surprising.  

“For people in Amman, maq?m music is familiar, which makes them more likely to engage with it physically,” he explained. 

Fadi's performance, singing with computer-responsive accompaniment on the screen in the background
Music generation: Fadi performing with the responsive computer accompanist.
Photo: Neerja Thakkar

The Familiarity of a Bell Sound

Still, the accelerometers registered pronounced momentary peaks in movement in Norway, markedly higher than in Jordan. These spikes were linked to a bell sound that was repeated several times throughout the piece.

“One of the listeners in Oslo said the bell reminded him of Christmas. It’s likely that others felt the same. It was December at the time, and the listeners were in a room with large windows overlooking a snowy forest. Recognizing certain elements in unfamiliar music can lead to enhanced engagement” Al-Ghawanmeh explained.

Our bodies tend to respond to sounds we recognize, he elaborated.

“We do not know for sure the exact reasons, but it’s likely that familiar sounds trigger memories, which in turn evoke emotions.”

According to Al-Ghawanmeh, adding familiar elements to a piece of music can increase its appeal, even if the genre or style is otherwise unfamiliar.

AI Can Adapt Music to Listeners’ Movements 

While artists can observe their audience’s reactions and adjust their music accordingly, AI tools can – by using accelerometer technology – adapt music to the listener’s movements and in this way increase its popularity. 

Already, there are apps available using such technology, for instance by adjusting the speed of workout music to listeners’ movements. 

“We may like it or not, but this is part of our future. Machines are already taking over the music industry. I have worked to protect a music tradition that is suffering under this development,” Al-Ghawanmeh said. 

“Technology Is Never Neutral”

Alexander Refsum Jensenius, professor of music technology, head of RITMO and one of Al-Ghawanmeh's supervisors, expressed enthusiasm about the creation of an open, accessible maqām dataset.

“Technology is never neutral. Every tech tool carries the cultural values and preferences of its creators. Maqām is a rich musical tradition, but because Western research dominates the field, it is underrepresented in music datasets. That is why this work is so important,” he said.

Al-Ghawanmeh’s PhD is a collaboration between the University of Lorraine in France, the University of Jordan and the University of Oslo.