ABOUT THE TEAM

In today’s music industry, over 90% of streams go to the top 1% of artists. This means that it is very difficult for 99% of artists to gain an audience, unless they are able to consistently create hit songs. Our mission is to bring equality to the music industry. We do this by training our AI with hit songs, and building songwriting tools to help artists create hit songs. Wayne Cheng is the machine learning engineer, songwriter, and audio engineer. He is the developer of the AI music technology, and uses the technology to explore the maximum potential of AI songwriting. Robert Thomas is the music producer, who takes the AI assisted compositions and produces them into music recordings. More information about our team, music, and technology can be found here:

ABOUT THE SONG

Start It Up is our demonstration of how today’s AI music technology can be used by artists to write pop songs. Specifically, songs that are intended to be competitive in the music industry. This song is our demonstration of the current capabilities of the AI music technology developed at AUDOIR. This is a fun song full of catchy hooks. A closer listen reveals a deeper message behind the lyrics. The song summons the power of positivity to overcome challenging situations. The initial effort is always difficult, so the song encourages the listeners to Start It Up! They will soon find that their situation will change for the better.

ABOUT THE HUMAN-AI CO-CREATION PROCESS

To create this song, we used “SAM,” which is our suite of AI songwriting tools, designed specifically to help artists create hit songs. We used deep learning technologies to build our AI, specifically autoregressive models. What this means is that the AI predicts a music note based on the past sequence of notes.

We used an autoencoder architecture to build our AI tools. For this song, we used “SAM Agent C” to create music from a user defined chord progression, and “SAM Agent N” to create music that is compatible with a given motif.

We first used SAM to generate a batch of music. We then evaluated each song, and selected songs with happy and catchy motifs. We manually refined the motifs, keeping some of the AI generated ideas, while adding our own ideas. The motifs were then arranged into the full song. SAM is capable of creating lyrics that best fit the generated songs. Much like the motifs, we manually refined the lyrics, and then added to the lyrics as needed.

The emotion and story of the song was inspired by both the motifs and the lyrics generated by SAM. We started with a general idea of a happy pop song, and followed to where the AI led us. After the song was written, we then brought the song to life with instrumentation. The vocalist provided her vocals, and all the elements were mixed together into the final music recording.