What data do you use to train the AI?
Why are there different AI’s for each genre?
How do I use the three workspace views?
Key metrics and definitions
Send us other questions
We two sources of listener data: public online comments and an in-house listening group. First, we compile comments listeners leave on sites like Youtube, Last.fm, and Soundcloud that use a frisson word (e.g. chills, goosebumps, eargasm, etc.) and have a timestamp. Second, we organize these comments to see which songs and moments appear most frequently. Third, our in-house group listens to the most frequently appearing songs and records where they experience chills. This is what we then use to train our algorithms.
II. Why are there different AI's for each genre?
The short answer is: taste. We all have a preference for the genres of music that we grew up with (especially during our teenage years). This creates a tricky problem for frisson: there may be a great chills moment that works for me, but doesn’t for you because you hate the genre or the artist. To solve this, we trained algorithms with data from one genre. With this approach, each AI can serve as a representative for a listener that likes that genre and help to show what moments would give that listener chills.
This feature enables users to upload files and receive analyses from the Qbrio AI.
FRISSON HEATMAP: The core visualization of the AI’s analysis of a song. When you upload a file, the AI scores each second of the upload displays these scores as color intensities on the waveform.
SONG VIEW: This is the default view for analyzing one song. You can make edits and re-upload the song to see whether your scores improve and where frisson is likely to occur for listeners.
MIX VIEW: This features lets you compare up to four mixes and supports synced play and toggling just like a DAW. Creative teams use this view to help avoid the common problem of “going past” the best mix of a song.
A&R VIEW: This feature enables users to compare up to 20 songs at a time. A&R teams use this view to assess albums and decide which tracks to cut as singles.
IV. Key Metrics and Definitions
Frisson Analytics: The set of metrics outlined below that together provides a new way to assess and compare mixes, songs, and albums.
Overall Song Ranking: A composite metric composed of the Chills, Streamability, and Novelty scores. This composite is calculated for each upload and then compared to every song the AI has previously scored. The metric is meant to provide an overall view of how moving and effective a song will be.
Chills Score: A measure of the emotional intensity and engagement of a song, as measured by the amount of “strength” of chills moments throughout the pieece.
Streamability Score: A measure of how commerically optimized a song is, as measured by the distribution of peak frisson moments in a song and how well it aligns with previous high-streamed songs.
Novelty score: A measure of how innovative a song is, as measured by which of the nine frisson patterns it uses and how it combines these patterns in key chills moments.