Case Study: Figaro Metadata Management + Audiomachine
Case Study: Figaro Metadata Management + Audiomachine
“Audiomachine have always been pioneers in both music and technology, and it's exciting to be at the forefront of this new technology with Figaro. Our goal for years has been to provide metadata so track discovery for our clients is both accurate and fast. Our early findings have already shown that implementing Figaro has made substantial improvements in this essential workflow.” - Marc D’Amour, Head of Operations

Audiomachine is one of the leading production music companies for film and tv music; their tracks have been featured in thousands of feature film and video game trailers, tv promos, brand advertisements, and social/digital content spots.

Since 2005, Audiomachine has been meticulous about crafting a taxonomy of subjective metadata to allow users of their online search platform to find the perfect track for their projects in the shortest amount of time possible. As their number of annual album releases grew, so did the need for resources to maintain this important eye on accurate and detailed metadata.

Using machine learning, Figaro has learned their taxonomy and analysed how their tags relate to the music. Figaro is then able to predict tags from the existing Audiomachine taxonomy for new tracks, using the same historical musical meaning the Audiomachine team applied when previously implementing those tags.

The Audiomachine team started incorporating Figaro into their workflow in early 2020. The simple process requires uploading new, untagged files to Figaro in order to receive applicable tags from their current taxonomy for their new music.

Figaro is a collaborative tool that takes feedback from their team and improves over time. Figaro has already analysed feedback on thousands of tracks to improve its future performance. The Audiomachine team find that working with Figaro speeds up the process of applying accurate subjective metadata to tracks ahead of release.

Front Page
AudioMachine