Tract: ramps at phone boundaries, 12 ms stop release, smoothers starting at their input; Meta's tract-weak-spots-1 verdict and analysis #52
Loading…
Reference in a new issue
No description provided.
Delete branch "aqua/tract-coarticulation"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Meta's tract-weak-spots-1 listening verdict (2 keep, 12 fix; data and analysis in docs/listening/) with every formant on target. Causes found by measuring the clips she heard: a step in the merged control curve at every phone boundary (nibu clicks, 0.40 and 0.49 peaks at 95 and 275 ms),
si.smoostarting every control at 0 (each clip a 100 ms climb from silence), and a stop opening over 33 ms (a burst the length of a fricative).Changes: 30 ms ramps at phone boundaries (
PatchScript.WithPhoneTransition), a 12 ms stop release,smoo_initon control-surface sliders, a 12 ms vocal attack on the word scaffold,tools/formant-check/ear_metrics.pyandphone_probe.py. Soul pass 1 found real regressions caused by this PR (closing-ramp hiss from the burst term, a voice bar 12 dB loud,smoo_inittime constant 5 ms vssi.smoo22.7 ms, stale Ding fixtures, stale 0.65 release windows, spline handles folded unlike the Faust lowering); fixed in20aec42and3e54428. Soul pass 2 then found the velar test blind to leaks, /d/ closing noise untested and thesmoo_fromcomment wrong; fixed in 96e6166..267a772 (the relaxed velar test is gone).Nothing here has been heard by Meta. Every claim about sound is a measurement, not a listening.
Verified (head
7a72915; suite run at267a772, one test host per class)267a772only three classes fail, all failing on main71cf9catoo:FaustLoaderPlatformTests.FindLibraryLooksUnderLibForThePlatformName,ZynReferenceParityTests,SpeechDistributedTrainingTests. Every other class and everyStressAndReleaseRenderTestscase, run singly, exited 0 (s52/pr3/exits.txtin the Aqua workspace).7a72915(two tests only) was then built and its two edited tests run alone: closing-noise 5/5 pass, velar closure 1/1 pass. The full suite was not rerun on7a72915.aqua-body:verdict:cut-tract-coarticulation-pr52-fix2.s3, 3 Low findings, no Medium): the velar leak-injection test fails on every leak and closure-source mutant; the closing-noise test, source silent, fails on the burst-through-ramp mutants (p b t d k) with a -30 dB bound about 22 dB from each side; thesmoo_fromstep form reproduces the old PlaceTable pins byte for byte; the glottal alias test passes at -43.4 dB and fails with the pitch smoother started at 0; freq/gain/note sliders stillsi.smoofrom 0. Its Low findings:/g/is not inTryIpaDescriptorso the closing-noise case could not fail (dropped in7a72915); the velar seal bound was not the binding guard (now -15.5,7a72915); the/k/closure at or under/p/criterion is unmet and has no ruling (follow-up). Not rechecked by a fourth Soul pass:7a72915is the two edits Soul prescribed, checked by the runs above.Not verified
phone_probe.py) not re-run after the fixes (no torch on this host);weak_spots.pynot run./k/closure with the source on is louder than/p/(-16.5 vs about -20 dB re vowels; it was on main too). Whether that is acceptable is unruled.🤖 Generated with Claude Code