| Wed, 16 Jul 2014 12:46:18 +0100 |
Chris Cannam |
Add piano-evaluation script; fix one of the piano groundtruth files (was a variable-tempo file which naive conversion script couldn't handle); fix the conversion script to fail when such a file is encountered
|
| Wed, 16 Jul 2014 08:11:08 +0100 |
Chris Cannam |
MIDI and .lab format groundtruth files for small piano dataset
|
| Tue, 15 Jul 2014 17:18:04 +0100 |
Chris Cannam |
Add piano and viola (for string quartet) to instruments, update RDF
|
| Tue, 15 Jul 2014 16:40:58 +0100 |
Chris Cannam |
Give RWC piano same range as other pianos
|
| Tue, 15 Jul 2014 16:39:30 +0100 |
Chris Cannam |
Add viola, RWC piano headers
|
| Tue, 15 Jul 2014 16:34:49 +0100 |
Chris Cannam |
Add RWC-derived piano template, and viola
|
| Tue, 15 Jul 2014 14:11:44 +0100 |
Chris Cannam |
Update subrepo
|
| Tue, 15 Jul 2014 13:32:27 +0100 |
Chris Cannam |
Normalise samples to cumulative maximum (experimentally)
norm
|
| Tue, 15 Jul 2014 13:28:52 +0100 |
Chris Cannam |
Use all three piano templates
|
| Tue, 15 Jul 2014 13:28:25 +0100 |
Chris Cannam |
Make source sparsity configurable in instrument pack as well as pitch sparsity; make both equal to 1 for piano templates
|
| Tue, 15 Jul 2014 13:26:56 +0100 |
Chris Cannam |
Some doc tweaks
|
| Mon, 30 Jun 2014 11:38:33 +0100 |
Chris Cannam |
Merge from default branch
noteagent
|
| Mon, 30 Jun 2014 11:38:12 +0100 |
Chris Cannam |
Some single-instrument tests
|
| Fri, 20 Jun 2014 10:30:04 +0100 |
Chris Cannam |
More RDF data
|
| Wed, 04 Jun 2014 13:03:56 +0100 |
Chris Cannam |
Agent test output. Much worse!
noteagent
|
| Wed, 04 Jun 2014 12:50:46 +0100 |
Chris Cannam |
Restore more theoretically agent-friendly instrument settings
noteagent
|
| Wed, 04 Jun 2014 12:48:52 +0100 |
Chris Cannam |
Merge from default branch; remove previous test run (I'm pretty sure it was re-running the previous code and had not rebuilt it!)
noteagent
|
| Wed, 04 Jun 2014 12:48:06 +0100 |
Chris Cannam |
New test run
|
| Wed, 04 Jun 2014 12:24:47 +0100 |
Chris Cannam |
Translate saxophone instrument to tenorsax; call make before running!
|
| Wed, 04 Jun 2014 12:12:56 +0100 |
Chris Cannam |
Rename file, add labels
noteagent
|
| Wed, 04 Jun 2014 12:11:25 +0100 |
Chris Cannam |
Merge from default branch
noteagent
|
| Wed, 04 Jun 2014 12:11:07 +0100 |
Chris Cannam |
Print out instrument alongside main arrow; add a new test run output
|
| Wed, 04 Jun 2014 12:00:55 +0100 |
Chris Cannam |
Use same polyphony/threshold settings for all single instruments as for unknown/multiple instruments (for comparative evaluation)
|
| Wed, 04 Jun 2014 11:53:32 +0100 |
Chris Cannam |
Evaluation output
noteagent
|
| Wed, 04 Jun 2014 11:46:01 +0100 |
Chris Cannam |
Merge from the default branch
noteagent
|
| Wed, 04 Jun 2014 11:45:42 +0100 |
Chris Cannam |
Run again with parameter settings for instruments. I see the results are worse!
|
| Wed, 04 Jun 2014 11:30:21 +0100 |
Chris Cannam |
Add category file
|
| Wed, 04 Jun 2014 11:26:59 +0100 |
Chris Cannam |
More adjustments, and an output file
|
| Wed, 04 Jun 2014 11:07:34 +0100 |
Chris Cannam |
Fixes to script
|
| Wed, 04 Jun 2014 10:57:54 +0100 |
Chris Cannam |
Converted data for evaluation runs
|
| Wed, 04 Jun 2014 10:16:22 +0100 |
Chris Cannam |
Move MIDI files of mixdowns to subdirs, start adding single-instrument groundtruth
|
| Wed, 04 Jun 2014 09:55:31 +0100 |
Chris Cannam |
RDF file, and some copyright etc updates
|
| Thu, 29 May 2014 15:18:14 +0100 |
Chris Cannam |
Debug out
noteagent
|
| Thu, 29 May 2014 10:30:08 +0100 |
Chris Cannam |
Fixes to mono feeder; use it for monophonic instruments
noteagent
|
| Thu, 29 May 2014 09:21:15 +0100 |
Chris Cannam |
Emit "MIDI-compatible" frequencies only, unless in fine tuning mode
noteagent
|
| Wed, 28 May 2014 15:16:00 +0100 |
Chris Cannam |
Don't retain returned hypotheses -- to avoid having to test whether we've seen them before
noteagent
|
| Wed, 28 May 2014 15:05:43 +0100 |
Chris Cannam |
Tidy column counting
noteagent
|
| Wed, 28 May 2014 14:56:01 +0100 |
Chris Cannam |
Merge from default branch
noteagent
|
| Wed, 28 May 2014 14:54:01 +0100 |
Chris Cannam |
Wire up note agent code -- results are not very good, so far
noteagent
|
| Fri, 23 May 2014 18:17:59 +0100 |
Chris Cannam |
Add some further parameters to the instrument pack
|
| Fri, 23 May 2014 17:03:27 +0100 |
Chris Cannam |
Remove some irrelevant code
noteagent
|
| Fri, 23 May 2014 12:40:18 +0100 |
Chris Cannam |
Experimental branch toward note-agent stuff (not actually plumbed in yet)
noteagent
|
| Thu, 22 May 2014 16:59:12 +0100 |
Chris Cannam |
Have a first go at reporting f0
f0
|
| Thu, 22 May 2014 15:06:37 +0100 |
Chris Cannam |
Fix incorrect use of int for non-integer shift weights
|
| Thu, 22 May 2014 12:11:33 +0100 |
Chris Cannam |
Restore (and fix) the time-frequency distribution output (filtered CQ); tidy up the bottom-octave handling in draft mode
|
| Wed, 21 May 2014 15:19:02 +0100 |
Chris Cannam |
Comment
|
| Wed, 21 May 2014 15:03:12 +0100 |
Chris Cannam |
Add some ensemble instrument packs
|
| Wed, 21 May 2014 14:42:00 +0100 |
Chris Cannam |
Emit cents offset in note name too
|
| Wed, 21 May 2014 14:41:53 +0100 |
Chris Cannam |
Introduce shift sparsity
|
| Wed, 21 May 2014 12:15:29 +0100 |
Chris Cannam |
In draft mode, make the CQ transform one octave shorter (bottom octave empty)
|
| Wed, 21 May 2014 12:10:02 +0100 |
Chris Cannam |
Remove comment (quick test suggests this makes little difference either way)
|
| Wed, 21 May 2014 11:53:54 +0100 |
Chris Cannam |
Merge from branch finetune
|
| Wed, 21 May 2014 11:53:31 +0100 |
Chris Cannam |
Refactor to avoid allocating 300 EM objects at a time!
finetune
|
| Wed, 21 May 2014 11:15:53 +0100 |
Chris Cannam |
More work on returning sensibly-shifted notes with fine tuning
finetune
|
| Wed, 21 May 2014 09:11:49 +0100 |
Chris Cannam |
Store active shifts separately from active pitches
finetune
|
| Tue, 20 May 2014 17:49:07 +0100 |
Chris Cannam |
More on returning fine tuning (but we're treating different shifts of the same pitch as different notes at the moment which is not right)
finetune
|
| Tue, 20 May 2014 17:34:49 +0100 |
Chris Cannam |
Start working on returning fine-tuning pitches
finetune
|
| Tue, 20 May 2014 16:48:33 +0100 |
Chris Cannam |
Use 20ms resolution in hq mode, 40ms only in draft mode
|
| Tue, 20 May 2014 16:21:33 +0100 |
Chris Cannam |
Some measurements suggest we get slightly better results with more iterations, but not drastically worse with fewer -- so go lower for draft and higher for hq mode
|
| Tue, 20 May 2014 15:56:57 +0100 |
Chris Cannam |
Minor tidy
|
