fix(align): calibrated fit (precision, lift, beat-shift check, baseline) and aligner guards (A7, A8)

Fit flags on precision (<0.6) and chance-corrected lift (<0.25), null with <8
recording onsets; old match rate kept as audibleRate (info). Symbolic-chroma
beat/bar-shift check per window. Constant-offset baseline (-2..+2 s) replaces
DTW without manual anchors unless DTW precision is better by >=0.02. Stretch
warning counts in the fit summary. DTW: slope-limited steps, open begin/end
options; per-bar outlier rejection (1/4 beat, Theil-Sen-transported +-3 bar
median); no anchor in the final partial bar. bench real: saved/computed
source, baseline + method, corrupt alignment.json skipped. Parabolic onset
interpolation; warp extrapolation documented; spec amended.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
Lucas WintherandClaude Opus 5.5 committed 2026-10-30 19:50:48 +01:00
1 parent 3b002059e9
commit 3db87c0317
19 files changed
+1016 -252

No files matched your search

+125 -16
View File
@@ -1,5 +1,5 @@
import { test, expect, beforeAll } from "bun:test";
import { alignmentFit, autoAlign, bandedWithRetry, barTimes, fitFromOnsets, recordingOnsets } from "../../src/align/auto.ts";
import { alignmentFit, autoAlign, bandedWithRetry, barTimes, beatTimes, constantOffsetBaseline, fitFromCues, meterGrid, recordingCues, rejectOffsetOutliers } from "../../src/align/auto.ts";
import { makeWarp, type Anchor, type Warp } from "../../src/align/warp.ts";
import type { RefTrack, Smf } from "../../src/align/smf.ts";
import type { Audio, Role, TruthTrack } from "../../src/core/types.ts";
@@ -49,18 +49,22 @@ function recoveryErrors(smf: Smf, got: Anchor[], trueMidiToAudio: (m: number) =>
.map((m) => Math.abs(w.toAudio(m) - trueMidiToAudio(m)));
}
test("recovers a known piecewise warp: median error < 40 ms, fit match rate > 0.7", () => {
test("recovers a known piecewise warp: median error < 40 ms, fit precision ≥ 0.8, DTW beats the constant baseline", () => {
const D = distortion(song.song.bpm);
const smf = smfFrom(song.truth.tracks, song.song.tracks.map((t) => t.program), song.song.bpm, D.toAudio);
const t0 = performance.now();
const { anchors, fit } = autoAlign(song.mix, smf, rolesOf(song.truth.tracks), [], SF2);
const { anchors, fit, baseline, chosen } = autoAlign(song.mix, smf, rolesOf(song.truth.tracks), [], SF2);
const ms = performance.now() - t0;
const err = recoveryErrors(smf, anchors, D.toMidi, durOf(song.mix));
debug(`synthetic warp: ${anchors.length} anchors, median err ${(median(err) * 1000).toFixed(1)} ms, p90 ${(p90(err) * 1000).toFixed(1)} ms, fit ${fit.matchRate?.toFixed(3)} / ${fit.medianResidualMs?.toFixed(1)} ms, ${ms.toFixed(0)} ms`);
debug(`synthetic warp: ${anchors.length} anchors, median err ${(median(err) * 1000).toFixed(1)} ms, p90 ${(p90(err) * 1000).toFixed(1)} ms, fit ${fit.precision?.toFixed(3)} lift ${fit.lift?.toFixed(3)} / ${fit.medianResidualMs?.toFixed(1)} ms, baseline ${baseline.offsetSec} s ${baseline.precision?.toFixed(3)}, ${ms.toFixed(0)} ms`);
expect(chosen).toBe("dtw");
expect(anchors.every((a) => a.kind === "auto")).toBe(true);
expect(median(err)).toBeLessThan(0.04);
expect(p90(err)).toBeLessThan(0.08);
expect(fit.matchRate!).toBeGreaterThan(0.7);
expect(fit.precision!).toBeGreaterThanOrEqual(0.8);
expect(fit.precision!).toBeGreaterThanOrEqual(baseline.precision! + 0.02);
expect(fit.windows.some((w) => w.flagged)).toBe(false);
expect(fit.stretches!.total).toBe(anchors.length + 1);
expect(fit.windows.length).toBe(2);
expect(anchors.every((a) => a.audioSec > 0 || a.midiSec === 0)).toBe(true);
}, BIG);
@@ -86,7 +90,7 @@ test("a silent intro in the recording does not drag the path", () => {
const { anchors, fit } = autoAlign(mix, smf, rolesOf(song.truth.tracks), [], SF2);
const err = recoveryErrors(smf, anchors, (m) => m + 4, durOf(mix));
expect(median(err)).toBeLessThan(0.04);
expect(fit.matchRate!).toBeGreaterThan(0.7);
expect(fit.precision!).toBeGreaterThanOrEqual(0.8);
}, BIG);
test("5-minute input aligns in < 15 s", () => {
@@ -94,12 +98,18 @@ test("5-minute input aligns in < 15 s", () => {
const mix: Audio = { sampleRate: song.mix.sampleRate, channels: song.mix.channels.map((c) => { const o = new Float32Array(c.length * reps); for (let r = 0; r < reps; r++) o.set(c, r * c.length); return o; }) };
const smf = smfFrom(song.truth.tracks, song.song.tracks.map((t) => t.program), song.song.bpm, (t) => t + 0.3, reps, period);
const t0 = performance.now();
const { anchors, fit } = autoAlign(mix, smf, rolesOf(song.truth.tracks), [], SF2);
const { anchors, fit, baseline, chosen } = autoAlign(mix, smf, rolesOf(song.truth.tracks), [], SF2);
const sec = (performance.now() - t0) / 1000;
debug(`5-min (${durOf(mix).toFixed(0)} s) input: ${sec.toFixed(2)} s, ${anchors.length} anchors, fit ${fit.matchRate?.toFixed(3)}`);
debug(`5-min (${durOf(mix).toFixed(0)} s) input: ${sec.toFixed(2)} s, ${anchors.length} anchors, fit ${fit.precision?.toFixed(3)}, ${chosen}, baseline ${baseline.offsetSec} ${baseline.precision?.toFixed(3)}`);
expect(durOf(mix)).toBeGreaterThan(290);
expect(sec).toBeLessThan(15);
expect(fit.windows.length).toBe(10);
// a constant offset: DTW cannot beat the baseline by 0.02, so the single-anchor baseline is returned
expect(baseline.offsetSec).toBeCloseTo(-0.3, 1);
expect(chosen).toBe("baseline");
expect(anchors).toHaveLength(1);
expect(anchors[0]!.kind).toBe("auto");
expect(anchors[0]!.audioSec - anchors[0]!.midiSec).toBeCloseTo(baseline.offsetSec, 6);
}, BIG);
test("barTimes follows tempo and time-signature changes", () => {
@@ -130,13 +140,13 @@ test("fit exposes a bad alignment instead of hiding it", () => {
const smf = smfFrom(song.truth.tracks, song.song.tracks.map((t) => t.program), song.song.bpm, D.toAudio);
const roles = rolesOf(song.truth.tracks);
const bad = alignmentFit(song.mix, smf, roles, []); // identity: off by 0.4–0.8 s throughout
expect(bad.matchRate!).toBeLessThan(0.5);
expect(bad.precision!).toBeLessThan(0.6);
// the −0.8 s section is exposed; the +0.4 s section is not, as 0.4 s is ≈ 40 ms from two 16ths at 68 bpm (grid alias)
expect(bad.windows[1]!.flagged).toBe(true);
const good = alignmentFit(song.mix, smf, roles, autoAlign(song.mix, smf, roles, [], SF2).anchors);
expect(good.windows.some((w) => w.flagged)).toBe(false);
// unmapped tracks are excluded: with no scored roles there is nothing to measure
expect(alignmentFit(song.mix, smf, Object.fromEntries(Object.keys(roles).map((k) => [k, null])), []).matchRate).toBeNull();
expect(alignmentFit(song.mix, smf, Object.fromEntries(Object.keys(roles).map((k) => [k, null])), []).precision).toBeNull();
}, BIG);
test("a deliberately wrong manual anchor (+0.3 s) is kept exactly and the result stays monotonic", () => {
@@ -158,23 +168,122 @@ test("when every fine band fails, the coarse-path fallback still yields auto anc
const D = distortion(song.song.bpm);
const smf = smfFrom(song.truth.tracks, song.song.tracks.map((t) => t.program), song.song.bpm, D.toAudio);
const manual: Anchor = { midiSec: D.toAudio(30), audioSec: 30, kind: "manual" };
const { anchors, fit } = autoAlign(song.mix, smf, rolesOf(song.truth.tracks), [manual], SF2, { fineBandsSec: [] });
const { anchors, fit, chosen } = autoAlign(song.mix, smf, rolesOf(song.truth.tracks), [manual], SF2, { fineBandsSec: [] });
expect(chosen).toBe("dtw"); // manual anchors present: never substituted by the baseline
const autos = anchors.filter((a) => a.kind === "auto");
// both segments (before and after the manual anchor) get anchors
expect(autos.filter((a) => a.audioSec < 30).length).toBeGreaterThan(3);
expect(autos.filter((a) => a.audioSec > 30).length).toBeGreaterThan(3);
expect(strictlyMonotone(anchors)).toBe(true);
const err = recoveryErrors(smf, anchors, D.toMidi, durOf(song.mix));
debug(`coarse fallback: ${autos.length} autos, median err ${(median(err) * 1000).toFixed(1)} ms, p90 ${(p90(err) * 1000).toFixed(1)} ms, fit ${fit.matchRate?.toFixed(3)}`);
debug(`coarse fallback: ${autos.length} autos, median err ${(median(err) * 1000).toFixed(1)} ms, p90 ${(p90(err) * 1000).toFixed(1)} ms, fit ${fit.precision?.toFixed(3)}`);
expect(median(err)).toBeLessThan(0.06); // 10 Hz resolution: coarser than the fine pass, still hand-correctable
expect(p90(err)).toBeLessThan(0.12);
}, BIG);
test("fitFromOnsets with cached recordingOnsets equals alignmentFit", () => {
test("fitFromCues with cached recordingCues equals alignmentFit", () => {
const smf = smfFrom(song.truth.tracks, song.song.tracks.map((t) => t.program), song.song.bpm, (t) => t);
const roles = rolesOf(song.truth.tracks);
const anchors: Anchor[] = [{ midiSec: 1, audioSec: 1.05, kind: "manual" }, { midiSec: 20, audioSec: 20.1, kind: "manual" }];
const onsets = recordingOnsets(song.mix);
expect(onsets.length).toBeGreaterThan(10);
expect(fitFromOnsets(onsets, smf, roles, anchors, durOf(song.mix))).toEqual(alignmentFit(song.mix, smf, roles, anchors));
const cues = recordingCues(song.mix);
expect(cues.onsets.length).toBeGreaterThan(10);
expect(cues.chroma.length).toBeGreaterThan(cues.durSec * cues.chromaRate - 2);
expect(fitFromCues(cues, smf, roles, anchors)).toEqual(alignmentFit(song.mix, smf, roles, anchors));
});
// ---- ruling A7: calibrated fit, beat-shift check, constant-offset baseline ----
test("fit precision: correct alignment ≥ 0.8, a 0.12 s off-grid shift < 0.5 (and flagged)", () => {
const smf = smfFrom(song.truth.tracks, song.song.tracks.map((t) => t.program), song.song.bpm, (t) => t);
const roles = rolesOf(song.truth.tracks);
const good = alignmentFit(song.mix, smf, roles, []);
const off = alignmentFit(song.mix, smf, roles, [{ midiSec: 10, audioSec: 10.12, kind: "manual" }]);
debug(`precision: correct ${good.precision?.toFixed(3)} (lift ${good.lift?.toFixed(3)}, audible ${good.audibleRate?.toFixed(3)}), +0.12 s ${off.precision?.toFixed(3)} (lift ${off.lift?.toFixed(3)})`);
expect(good.precision!).toBeGreaterThanOrEqual(0.8);
expect(good.lift!).toBeGreaterThanOrEqual(0.25);
expect(good.windows.some((w) => w.flagged)).toBe(false);
expect(off.precision!).toBeLessThan(0.5);
expect(off.windows.filter((w) => w.precision !== null).every((w) => w.flagged)).toBe(true);
});
test("beat-shift check flags an alignment that is one beat late, though onset precision cannot see it", () => {
const smf = smfFrom(song.truth.tracks, song.song.tracks.map((t) => t.program), song.song.bpm, (t) => t);
const roles = rolesOf(song.truth.tracks);
const beat = 60 / song.song.bpm;
const late = alignmentFit(song.mix, smf, roles, [{ midiSec: 10, audioSec: 10 + beat, kind: "manual" }]);
const good = alignmentFit(song.mix, smf, roles, []);
debug(`beat shift: late precision ${late.precision?.toFixed(3)}, windows ${JSON.stringify(late.windows.map((w) => [w.precision?.toFixed(2), w.lift?.toFixed(2), w.beatShift]))}`);
expect(good.windows.some((w) => w.beatShift)).toBe(false);
const shifted = late.windows.filter((w) => w.beatShift);
expect(shifted.length).toBeGreaterThan(0);
expect(shifted.every((w) => w.flagged && w.reasons.some((r) => r.startsWith("beat shift suspected: −")))).toBe(true);
});
test("constantOffsetBaseline grid-searches −2..+2 s for the offset with the best precision", () => {
const smf = smfFrom(song.truth.tracks, song.song.tracks.map((t) => t.program), song.song.bpm, (t) => t + 0.27);
const b = constantOffsetBaseline(recordingCues(song.mix), smf, rolesOf(song.truth.tracks));
expect(b.offsetSec).toBeCloseTo(-0.27, 1);
expect(Math.round(b.offsetSec * 100)).toBe(b.offsetSec * 100); // 10 ms grid
expect(b.precision!).toBeGreaterThanOrEqual(0.8);
});
// ---- ruling A8: aligner guards ----
test("rejectOffsetOutliers drops bars > ¼ beat from the robust median of ±3 neighbours (slope-transported), iterating until stable", () => {
const bars = Array.from({ length: 20 }, (_, k) => ({ midiSec: k * 2, off: 0.1 + k * 0.004, beatSec: 0.5 }));
bars[5]!.off = 0.6; // a beat out
bars[6]!.off = 0.55; // its neighbour, also out
bars[15]!.off = -0.3;
const kept = rejectOffsetOutliers(bars).map((b) => b.midiSec / 2);
expect(kept).toEqual(Array.from({ length: 20 }, (_, k) => k).filter((k) => k !== 5 && k !== 6 && k !== 15));
// a smooth ramp (genuine tempo change) is kept whole
const ramp = Array.from({ length: 20 }, (_, k) => ({ midiSec: k * 2, off: k * 0.05, beatSec: 0.5 }));
expect(rejectOffsetOutliers(ramp)).toHaveLength(20);
// ... also a steep one (10% tempo difference: 0.2 s per 2 s bar), whose ends a plain one-sided median would erode
// bar by bar; neighbours are transported along their median (Theil–Sen) slope
const steep = Array.from({ length: 20 }, (_, k) => ({ midiSec: k * 2, off: k * 0.2, beatSec: 0.5 }));
expect(rejectOffsetOutliers(steep)).toHaveLength(20);
// a beat jump inside the steep ramp is still rejected
steep[10]!.off += 0.5;
expect(rejectOffsetOutliers(steep).map((b) => b.midiSec / 2)).toEqual(Array.from({ length: 20 }, (_, k) => k).filter((k) => k !== 10));
});
test("meterGrid: beats and bars from tempo/time signatures; the final bar is partial when the MIDI ends mid-bar", () => {
const smf: Smf = { durationSec: 9, tracks: [], tempoMap: [{ sec: 0, bpm: 120 }, { sec: 4, bpm: 60 }], timeSigs: [{ sec: 0, num: 4, den: 4 }, { sec: 4, num: 3, den: 4 }] };
const g = meterGrid(smf);
expect(g.bars).toEqual([0, 2, 4, 7]);
expect(g.beats).toEqual([0, 0.5, 1, 1.5, 2, 2.5, 3, 3.5, 4, 5, 6, 7, 8, 9]);
expect(g.lastBarPartial).toBe(true); // bar 7..10 ends after 9
expect(meterGrid({ ...smf, durationSec: 10 }).lastBarPartial).toBe(false);
expect(beatTimes({ durationSec: 3, tracks: [], tempoMap: [{ sec: 0, bpm: 120 }], timeSigs: [{ sec: 0, num: 6, den: 8 }] })).toEqual([0, 0.25, 0.5, 0.75, 1, 1.25, 1.5, 1.75, 2, 2.25, 2.5, 2.75]);
});
test("no auto anchor in the final partial bar", () => {
const D = distortion(song.song.bpm);
const smf = smfFrom(song.truth.tracks, song.song.tracks.map((t) => t.program), song.song.bpm, D.toAudio);
const g = meterGrid(smf);
const last = g.bars[g.bars.length - 1]!;
const cut: Smf = { ...smf, durationSec: last + 0.5 * (last - g.bars[g.bars.length - 2]!) }; // ends half-way into the last bar
expect(meterGrid(cut).lastBarPartial).toBe(true);
const { anchors } = autoAlign(song.mix, cut, rolesOf(song.truth.tracks), [], SF2);
expect(anchors.some((a) => a.midiSec >= last - 1e-9)).toBe(false);
}, BIG);
test("12 s of extra outro in the recording: open-end DTW, no ramp at the end", () => {
const D = distortion(song.song.bpm);
const smf = smfFrom(song.truth.tracks, song.song.tracks.map((t) => t.program), song.song.bpm, D.toAudio);
const sr = song.mix.sampleRate, extra = 12 * sr;
// the outro repeats the first 12 s of the song (material that DTW could be tempted to match)
const mix: Audio = { sampleRate: sr, channels: song.mix.channels.map((c) => { const o = new Float32Array(c.length + extra); o.set(c); o.set(c.subarray(0, extra), c.length); return o; }) };
const { anchors, chosen } = autoAlign(mix, smf, rolesOf(song.truth.tracks), [], SF2);
expect(chosen).toBe("dtw");
const autos = anchors.filter((a) => a.kind === "auto");
const tail = autos.slice(-4).map((a) => a.audioSec - D.toMidi(a.midiSec));
debug(`outro: last anchor offsets vs truth ${tail.map((e) => (e * 1000).toFixed(0)).join(", ")} ms`);
expect(tail.every((e) => Math.abs(e) < 0.06)).toBe(true);
const w = makeWarp(anchors);
const endErr = Math.abs(w.toAudio(smf.durationSec) - D.toMidi(smf.durationSec));
expect(endErr).toBeLessThan(0.1);
const err = recoveryErrors(smf, anchors, D.toMidi, durOf(song.mix));
expect(median(err)).toBeLessThan(0.04);
}, BIG);