ΑΙhub.org
 

Yaboi Hanoi wins the 2022 AI Song Contest


by
08 July 2022



share this:
AI song contest logo

On 6 July, the organisers of the AI Song Contest revealed the winner of this year’s competition. The accolade goes to…

Team | Yaboi Hanoi
Song | อสุระเทวะชุมนุม (“Asura Deva Choom Noom”) – Enter Demons & Gods
Team member | Lamtharn “Hanoi” Hantrakul

You can listen to the winning song below:
https://soundcloud.com/user-458660217/enter-demons-and-gods?utm_source=clipboard&utm_campaign=wtshare&utm_medium=widget&utm_content=https%253A%252F%252Fsoundcloud.com%252Fuser-458660217%252Fenter-demons-and-gods

What makes this song stand out is that it uses Thai tuning. Most AI models are rooted in Western definitions of melody, harmony and tuning. This means that models can only output notes on the 12-note Western scale, making it very difficult to apply machine learning to music from many musical cultures around the world. In his submission, Lamtharn aimed to demonstrate “how advancements in realtime audio machine learning enable unprecedented audio synthesis with respect to a culture’s native tuning”.

As part of his submission to the contest, Lamtharn wrote a process document describing how he went about using AI methods to aid his composition. He also gives a case study on how he modelled the unique sound of the Phi, a double-reeded instrument integral to Thai culture. You can read more here.

You can also watch a short video where Lamtharn talks about the composition of his song:

You can listen to the submissions from the other entrants here.



tags:


Lucy Smith is Senior Managing Editor for AIhub.
Lucy Smith is Senior Managing Editor for AIhub.




            AIhub is supported by:


Related posts :



Interview with Yuki Mitsufuji: Improving AI image generation

  23 Jan 2025
Find out about two pieces of research tackling different aspects of image generation.

The Good Robot podcast: Using feminist chatbots to fight trolls with Sarah Ciston

  22 Jan 2025
Eleanor and Kerry chat to Sarah Ciston about the difficult labor of content moderation, chatbots to combat trolls, and more.

An open-source training framework to advance multimodal AI

  22 Jan 2025
EPFL researchers have developed 4M, a next-generation, framework for training versatile and scalable multimodal foundation models.

Optimizing LLM test-time compute involves solving a meta-RL problem

  20 Jan 2025
By altering the LLM training objective, we can reuse existing data along with more test-time compute to train models to do better.

Generating a biomedical knowledge graph question answering dataset

  17 Jan 2025
Introducing PrimeKGQA - a scalable approach to dataset generation, harnessing the power of large language models.

The Machine Ethics podcast: 2024 in review with Karin Rudolph and Ben Byford

Karin Rudolph and Ben Byford talk about 2024 touching on the EU AI Act, agent-based AI and advertising, AI search and access to information, conflicting goals of many AI agents, and much more.

Playbook released with guidance on creating images of AI

  15 Jan 2025
Archival Images of AI project enables the creation of meaningful and compelling images of AI.




AIhub is supported by:






©2024 - Association for the Understanding of Artificial Intelligence


 












©2021 - ROBOTS Association