Piano Evaluation for Level Normalisation » History » Version 2

Chris Cannam, 2014-07-16 06:33 PM

1 1 Chris Cannam
h1. Piano Evaluation for Level Normalisation
2 1 Chris Cannam
3 1 Chris Cannam
Lack of normalisation for Vamp plugin inputs is a problem when analysing quiet recordings (see #1028).
4 1 Chris Cannam
5 1 Chris Cannam
Testing using a small set of piano recordings, quickly evaluating performance across the first 30 seconds under a number of different normalisation / level management regimes.
6 1 Chris Cannam
7 1 Chris Cannam
Recording files:
8 1 Chris Cannam
9 1 Chris Cannam
|Filename|Signal max approx|
10 1 Chris Cannam
|31.wav|0.57|
11 1 Chris Cannam
|MAPS_MUS-bach_846_AkPnBcht.wav|0.12|
12 1 Chris Cannam
|MAPS_MUS-chpn_op7_1_ENSTDkAm.wav|0.33|
13 1 Chris Cannam
|MAPS_MUS-scn15_7_SptkBGAm.wav|0.13|
14 1 Chris Cannam
|mz_333_1MINp_align.wav|0.10|
15 2 Chris Cannam
16 2 Chris Cannam
The plugin has one internal threshold parameter, which can be lowered to find quieter notes (at the expense of course of more false positives). We don't really want to expose this (or any continuous controls) as a parameter. But we need to have approximately predictable input levels, for this threshold to be meaningful.
17 2 Chris Cannam
18 2 Chris Cannam
Methods:
19 2 Chris Cannam
20 2 Chris Cannam
|Name|Hg revision|Description|
21 2 Chris Cannam
|as-is|d721a17f3e14|No normalisation|
22 2 Chris Cannam
|norm|d721a17f3e14|Normalise to 0.50 max before running plugin (can't do this in plugin)|
23 2 Chris Cannam
|to-date|d9b688700819|Track max signal level _so far_, adjust each sample so that max is at 0.50|
24 2 Chris Cannam
25 2 Chris Cannam
Results: