John Hicks

I research how machines listen to African popular music, and I make it. My work builds datasets and models for the rhythms, timbres and languages that Western-trained systems miss.

Research assistant
AIRLAB, University of Lagos
Affiliated researcher
AI Unipod, UNDP Nigeria
Artist and producer
Jotihicks

Read the researchListen

Portrait of John Hicks in a grey polo under a warm pendant light

Data scientistMachine learning research engineerMusic information retrievalMachine learning for audio

01 — Recently

Recently…

  1. 2026

    AFMGC dataset paper, under the supervision of Prof. Chika Yinka-Banjo, submitted for review to TISMIR.

    Research
  2. 2025-10

    Released “Only You”, out now on Apple Music, YouTube Music and Deezer.

    Music
  3. 2024-07

    Released “Medusa”, produced by Elbuzzi.

    Music

02 — Research

Under review · TISMIR

African Music Genre Classifier (AFMGC)

Most music-information-retrieval corpora are built around Western repertoire, so models trained on them flatten a continent of music into “world”. AFMGC is an annotated corpus of African popular music and a deep-learning pipeline for genre classification, labelled by listener judgement rather than inherited metadata.

Full write-up Dataset (opens in a new tab)GitHub (opens in a new tab)

Data
1,061 human-annotated 30-second clips, ten genres
Features
91 acoustic descriptors per clip plus aligned Mel-spectrograms
Models
Classical and convolutional baselines
Context
PGD thesis, AIRLAB, University of Lagos
  • 00Afrobeat
  • 01Afrobeats
  • 02Amapiano
  • 03Highlife
  • 04Mbalax
  • 05Kwaito
  • 06Soukous
  • 07Jùjú
  • 08Fújì
  • 09Congolese Rumba

03 — Music

04 — Videos

Performances and visuals.

  • Turn Up

    Music video

  • Medusa

    Acoustic, in the studio

  • After 7

    Lyric video

  • Acoustic session

    Guitar and vocals

05 — About

John Hicks is…

  1. 1 a musician

    Self-producing artist and audio engineer.

    Recording since 2017, trained under producers including Semzi Beats, P.Priime and Sarz. I compose, record, mix and master my own music: about 301,000 plays on Audiomack.

  2. 2 a researcher

    Music information retrieval and machine learning for audio.

    Research assistant at AIRLAB, University of Lagos, under Prof. Chika Yinka-Banjo; affiliated researcher at AI Unipod (UNDP Nigeria); teaching assistant for data science and machine learning.

  3. 3 working toward

    Representations that respect idiomatic specificity.

    Self-supervised and low-resource methods for musical traditions existing corpora underrepresent, and whether models pre-trained on Western repertoire transfer to African music at all.

Download CV (PDF) (opens in a new tab)

06 — Contact