diff --git a/index.md b/index.md index f11d71e..7a058d1 100644 --- a/index.md +++ b/index.md @@ -90,37 +90,37 @@ Diff-A-Riff allows the generation of accompaniments based on an audio reference. - 1 - - - + 1 + + + - - - + + + - 2 - - - + 2 + + + - - - + + + - 3 - - - + 3 + + + - - - + + + @@ -148,26 +148,26 @@ Diff-A-Riff also allows to specify the accompaniment using a text prompt. This r - 3 + 3 "A solo ukulele delivering a cheerful and sunny accompaniment." - - + + "A mellow synthesizer playing ethereal pads." - - + + - 4 + 4 "Drums with reverb and a lot of toms." - - + + "Drums with reverb and a lot of hats/cymbals." - - + + @@ -194,33 +194,33 @@ The model can generate accompaniments from a context only, without the need for - - - - - + + + + + - - - - - + + + + + - - - - - - + + + + + + - - - - - + + + + + @@ -235,25 +235,25 @@ Despite Diff-A-Riff generating only solo instrumental tracks, we are able to gen - - - + + + - - - + + + - - - + + + - - - + + + @@ -280,22 +280,22 @@ Diff-A-Riff also allows the generation of solo instrument tracks conditioned on - - - - + + + + - - - - + + + + - - - - + + + +
@@ -318,23 +318,23 @@ In this section, you can hear single instrument tracks generated solely from a t "Guitar played folk style." - - + + "Slow evolving pad synth." - - + + "A vibrant, funky bassline characterized by the electrifying slap technique, where each note pops with a distinct rhythmic snap and sizzle." - - + + "A pulsating techno drum beat, where a deep bass kick thunders every quarter note, creating a relentless and hypnotic pulse." - - + + @@ -350,29 +350,29 @@ In this section, we show single instrument tracks generated without context or C - - - + + + - - - + + + - - - + + + - - - + + + - - - + + + @@ -403,48 +403,48 @@ In the following examples, all tracks are inpainted from second 5 to 8. - - - - + + + + - - + + - - + + - - - - + + + + - - + + - - + + - - - - + + + + - - + + - - + + @@ -460,53 +460,53 @@ We can interpolate between different references in the CLAP space. Here, we demo - - - - + + + + - - - - + + + + - - - - + + + + - - - - + + + + - - - - + + + + - - - - + + + + - - - - + + + + @@ -537,28 +537,28 @@ Given an audio file, we can encode it in the CAE latent space and get the corres - - - - + + + + - - - - + + + + - - - - + + + + - - - - + + + + @@ -583,22 +583,22 @@ Following the same principle as for variations, for any mono signal, we can crea - - - - + + + + - - - - + + + + - - - - + + + +
Audio Reference
$$ r = 0 $$
$$ r = 0.2 $$
$$ r = 0.4 $$
$$ r = 0.6 $$
$$ r = 0.8 $$
$$ r = 1 $$
Text Prompt
@@ -620,40 +620,40 @@ By repeating a portion of the data being denoised, we can enforce repetitions in 2 0.5 - - - + + + 0.8 - - - + + + 1 - - - + + + 4 0.5 - - - + + + 0.8 - - - + + + 1 - - - + + +