Urgent.News

What's breaking now, across thousands of outlets.

AI

AI is struggling to hear the Gulf’s music

When I arrived in Abu Dhabi 13 years ago, I had an idea. As a composer, I had previously worked in Portugal on developing computer programmes capable of generating music, including jazz. I wanted to explore whether similar technology could be used to create music inspired by the traditions of the Gulf. There was just one problem – I couldn’t find the recordings. Everyone I spoke to described the…

AI is struggling to hear the Gulf’s music

Thirteen years ago, I embarked on a mission to explore AI's role in documenting Gulf music traditions. As a composer in Abu Dhabi, I aimed to create music inspired by the region's rich cultural heritage. However, finding existing recordings proved challenging, so I began documenting local musicians myself. This experience highlighted a paradox: while the internet offers an abundance of music, AI's algorithms are better at recognizing certain traditions than others.

Music recommendation systems excel at suggesting songs based on personal tastes, yet they struggle to distinguish between cultural traditions like Al Ayyala, a traditional Emirati performing art. This imbalance in data availability poses a challenge for Music Information Retrieval, a field that combines musical knowledge, engineering, computer science, and AI to analyze and organize music digitally.

Existing technology has been developed primarily for musical traditions with extensive recordings, which often come from the West. For instance, Arabic music incorporates melodic systems like maqam, which can include intervals outside western equal-tempered tuning, making it harder for algorithms to identify. In our research at NYU Abu Dhabi, we're addressing this by combining computational methods with the expertise of musicians and researchers.

Our work on Carnatic music from southern India involves developing techniques to distinguish the 13 different types of strokes played on a mridangam, a double-headed drum, a challenge that existing systems struggle with. Beyond identifying instruments or styles, AI could also reveal connections between musical traditions across the Indian Ocean, such as the similarities between Gulf pearl-diving songs and those from Ghana and Brazil.

However, interpreting these findings requires the combined knowledge of musicians, historians, and ethnomusicologists alongside computer scientists. This month, NYU Abu Dhabi will host the International Society for Music Information Retrieval Conference in the Arab world, an event aimed at encouraging greater interest in the region's musical heritage and expanding the research community studying it.

Written by urgent.news from The National UAE's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

This story

This is one outlet's version. Read the fullest account.

Read the original at thenationalnews.com →

More in AI

More from Tuesday 10 November →