Period detection: silence is not dissent but an absent period is — the agreement denominator is the probes that carried signal
This commit is contained in:
@@ -125,7 +125,7 @@ PeriodEstimate detectPeriod(const std::vector<AudioSample>& pcm, int sampleRate,
|
||||
if (sampleRate <= 0 || spanCount == 0) return {};
|
||||
if (spanFrom > pcm.size() || spanCount > pcm.size() - spanFrom) return {};
|
||||
const double rate = static_cast<double>(sampleRate);
|
||||
std::size_t lagHi = static_cast<std::size_t>(rate / kPeriodDetectMinHz);
|
||||
std::size_t lagHi = longestLagFrames(sampleRate);
|
||||
const std::size_t lagLo = static_cast<std::size_t>(rate / kPeriodDetectMaxHz);
|
||||
if (lagLo < 2) return {}; // a rate so low the whole search band collapses
|
||||
|
||||
@@ -145,10 +145,14 @@ PeriodEstimate detectPeriod(const std::vector<AudioSample>& pcm, int sampleRate,
|
||||
|
||||
std::vector<double> periods;
|
||||
std::vector<double> confidences;
|
||||
// Probes that carried signal — the agreement denominator. A silent block is no evidence
|
||||
// either way and is excluded; every other outcome, a period found or not, is evidence.
|
||||
std::size_t evidence = 0;
|
||||
for (std::size_t p = 0; p < probes; ++p) {
|
||||
// (probes - 1) * stride <= room by construction, so the last block always fits.
|
||||
const std::size_t from = spanFrom + p * stride;
|
||||
if (from + block > spanFrom + spanCount) break;
|
||||
if (blockRms(pcm, from, block) < kSilenceRms) continue;
|
||||
++evidence;
|
||||
|
||||
const std::vector<double> small = decimate(pcm, from, block);
|
||||
const std::size_t smallHi = lagHi / kDecimate;
|
||||
@@ -177,16 +181,17 @@ PeriodEstimate detectPeriod(const std::vector<AudioSample>& pcm, int sampleRate,
|
||||
|
||||
if (periods.empty()) return {};
|
||||
|
||||
// ONE surviving probe: the span could not host a second probe position, so there is no
|
||||
// second estimate for the majority rule below to rule on — it would be deciding on an
|
||||
// empty comparison. The accept rests on pickPeriod's absolute threshold, which is a real
|
||||
// test and not an absence of one: the block genuinely repeats at this lag across its whole
|
||||
// analysis window. Refusing instead would deny every short one-shot a period, and a period
|
||||
// that turns out wrong costs a mis-centred correlation search at the splice, not an
|
||||
// unrefined one (pitch_shift.cpp's splice searches +/- maxLag around whichever jump it is
|
||||
// handed). Do not "unify" this back into the majority test — at size 1 that test accepts
|
||||
// unconditionally, which is the same behaviour with none of the reasoning.
|
||||
if (periods.size() == 1) {
|
||||
// ONE piece of evidence in the whole span — either it hosted a single probe position, or
|
||||
// every other probe was silent. Nothing can rule against this estimate, so the accept rests
|
||||
// on pickPeriod's absolute threshold, which is a real test and not an absence of one: the
|
||||
// block genuinely repeats at this lag across its whole analysis window. Refusing instead
|
||||
// would deny every short one-shot a period, and a period that turns out wrong costs a
|
||||
// mis-centred correlation search at the splice, not an unrefined one (pitch_shift.cpp's
|
||||
// splice searches +/- maxLag around whichever jump it is handed). Do not "unify" this back
|
||||
// into the majority test — at one piece of evidence that test accepts unconditionally, which
|
||||
// is the same behaviour with none of the reasoning. Nor key it on how many probes SURVIVED:
|
||||
// one survivor out of four that all carried signal is not this case at all.
|
||||
if (evidence == 1) {
|
||||
PeriodEstimate lone;
|
||||
lone.frames = periods[0];
|
||||
lone.confidence = confidences[0];
|
||||
@@ -208,12 +213,15 @@ PeriodEstimate detectPeriod(const std::vector<AudioSample>& pcm, int sampleRate,
|
||||
confSum += confidences[i];
|
||||
++agree;
|
||||
}
|
||||
// A STRICT MAJORITY of the valid probes must agree, not merely two of them: a source whose
|
||||
// first half is one period and second half another gives two probes each way, and taking
|
||||
// either as "the" period would misalign every splice in the other half. Refusing is the
|
||||
// right answer there — the fixed-window fallback is what a source with no ONE period gets.
|
||||
// Reached only with two or more probes; the lone-probe case returned above.
|
||||
if (agree * 2 <= periods.size()) return {};
|
||||
// A STRICT MAJORITY of the probes that carried signal must agree, not merely two of them: a
|
||||
// source whose first half is one period and second half another gives two probes each way,
|
||||
// and taking either as "the" period would misalign every splice in the other half. Refusing
|
||||
// is the right answer there — the fixed-window fallback is what a source with no ONE period
|
||||
// gets. The denominator is `evidence` and not `periods.size()` because once probes overlap
|
||||
// a straddling block finds no period at all rather than a third one, and counting only the
|
||||
// survivors turned that two-and-two split into a two-of-three accept.
|
||||
// Reached only with two or more pieces of evidence; the lone case returned above.
|
||||
if (agree * 2 <= evidence) return {};
|
||||
|
||||
PeriodEstimate est;
|
||||
est.frames = sum / static_cast<double>(agree);
|
||||
@@ -235,8 +243,7 @@ AnalysisSpan periodAnalysisSpan(std::size_t frameCount, std::int64_t loopStart,
|
||||
const std::size_t length = static_cast<std::size_t>(loopEnd - loopStart);
|
||||
// One full probe block. Below it detectPeriod shortens lagHi to fit, which raises the
|
||||
// lowest findable fundamental — the one thing the narrower span may never cost.
|
||||
const std::size_t minimum =
|
||||
2 * static_cast<std::size_t>(static_cast<double>(sampleRate) / kPeriodDetectMinHz);
|
||||
const std::size_t minimum = 2 * longestLagFrames(sampleRate);
|
||||
if (length < minimum) return whole;
|
||||
return AnalysisSpan{static_cast<std::size_t>(loopStart), length};
|
||||
}
|
||||
|
||||
@@ -21,8 +21,8 @@ using audio::AudioSample;
|
||||
struct PeriodEstimate {
|
||||
double frames = 0.0; // 0 = no single period (inharmonic, polyphonic, percussive, noise)
|
||||
// 1 - the accepted dissimilarity, [0,1]; 0 when frames == 0. Diagnostic: the accept decision
|
||||
// is `valid()` alone and the loader takes `.frames` without reading this — its consumers are
|
||||
// the tests and the measurement harness. It is deliberately NOT a second accept gate: every
|
||||
// is `valid()` alone and the loader takes `.frames` without reading this — its only reader is
|
||||
// tests/test_period_detect.cpp. It is deliberately NOT a second accept gate: every
|
||||
// accepted probe already cleared kPeriodDetectThreshold, so confidence > 0.88 holds by
|
||||
// construction and any gate below that is a no-op while any gate above it is a tuned number
|
||||
// with nothing to derive it from.
|
||||
@@ -44,6 +44,14 @@ inline constexpr double kPeriodDetectMaxHz = 2000.0;
|
||||
// global minimum — the difference between "quiet but real" and "the least bad of nothing".
|
||||
inline constexpr double kPeriodDetectThreshold = 0.12;
|
||||
|
||||
// The longest lag searched, in frames — THE one derivation of it. A probe block is twice this,
|
||||
// and `periodAnalysisSpan`'s minimum is one block; both read this rather than re-deriving the
|
||||
// same expression, so "choosing the loop never narrows the search band" is a fact and not a
|
||||
// coincidence between two literals.
|
||||
inline std::size_t longestLagFrames(int sampleRate) {
|
||||
return static_cast<std::size_t>(static_cast<double>(sampleRate) / kPeriodDetectMinHz);
|
||||
}
|
||||
|
||||
// How many blocks across the sample are estimated independently, and how far apart two of them
|
||||
// may land and still be called the same period. Agreement is what separates a genuinely
|
||||
// periodic source from one whose opening happens to look periodic.
|
||||
@@ -53,8 +61,6 @@ inline constexpr double kPeriodDetectThreshold = 0.12;
|
||||
// whole cycle of the lowest frequency in the band, so neither can be a trivially shifted copy
|
||||
// of the other at any period searched. Requiring DISJOINT blocks instead left every source
|
||||
// under ~4x the longest lag with a single probe and so with no agreement to check at all.
|
||||
// One probe survives as an irreducible case below `block + longest lag` frames and is accepted
|
||||
// on the absolute threshold alone — see detectPeriod's contract.
|
||||
inline constexpr int kPeriodDetectProbes = 4;
|
||||
inline constexpr double kPeriodDetectAgreeTolerance = 0.02; // 2% of the median
|
||||
|
||||
@@ -66,10 +72,21 @@ inline constexpr double kPeriodDetectAgreeTolerance = 0.02; // 2% of the median
|
||||
// Returns an invalid estimate (frames == 0) for silence, noise, and anything whose probes
|
||||
// disagree — the caller's documented fallback is the fixed-window splice geometry.
|
||||
//
|
||||
// Two probes or more must reach a STRICT MAJORITY agreement. A lone probe — which only happens
|
||||
// on a span too short to host a second probe position — is accepted on the absolute threshold
|
||||
// alone, because there is no second estimate for a majority rule to rule on and refusing would
|
||||
// deny every short one-shot a period.
|
||||
// A STRICT MAJORITY of the probes that CARRIED SIGNAL must agree. Silence is excluded from that
|
||||
// denominator and a failure to find a period is not: a silent block is no evidence either way,
|
||||
// whereas a block that carries signal and repeats at no lag is evidence against a single period.
|
||||
// A capture with a silent head or tail therefore still detects, while a mostly-noise source with
|
||||
// one pitched burst is refused rather than accepted on that burst alone. A LONE piece of
|
||||
// evidence — the whole span too short for a second probe position, or every other probe silent —
|
||||
// is accepted on the absolute threshold alone, because there is nothing to rule against it and
|
||||
// refusing would deny every short one-shot a period.
|
||||
//
|
||||
// The answer is NOT monotone in span length, and cannot be made so: no rule that refuses a
|
||||
// two-and-two split at four probes can also accept a lone probe unconditionally, and the probe
|
||||
// count steps at 3x, 4x, 5x and 6x the longest lag before saturating. What IS pinned, by a
|
||||
// length sweep in the tests, is that a STATIONARY source detects at every length — a source
|
||||
// whose period varies by more than kPeriodDetectAgreeTolerance is the only class that moves
|
||||
// with the count, and refusing it is this contract's own answer.
|
||||
PeriodEstimate detectPeriod(const std::vector<AudioSample>& pcm, int sampleRate,
|
||||
std::size_t from, std::size_t count);
|
||||
|
||||
@@ -79,12 +96,20 @@ PeriodEstimate detectPeriod(const std::vector<AudioSample>& pcm, int sampleRate)
|
||||
// The frames detection should analyse for a capture that carries a sustain loop, and the reason
|
||||
// the answer is not simply "all of them": under Gate the loop region is asymptotically ALL the
|
||||
// splicer plays, so a phrase whose head is pitched differently from its sustain would otherwise
|
||||
// disagree its way to none over the whole source. `[loopStart, loopEnd)` is used only when it
|
||||
// is at least `2 * (sampleRate / kPeriodDetectMinHz)` frames — the span below which detectPeriod
|
||||
// starts shortening its own search band — so choosing the narrower span never costs search-band
|
||||
// width and so can never lose a low fundamental that the whole source would have found.
|
||||
// disagree its way to none over the whole source. `[loopStart, loopEnd)` is used only when it is
|
||||
// at least one full probe block — `2 * longestLagFrames(sampleRate)`, the span below which
|
||||
// detectPeriod starts shortening its own search band — so choosing the narrower span never costs
|
||||
// search-band WIDTH. It can still change the ANSWER: the agreement rule rules on content, so a
|
||||
// source periodic over most of its length whose loop region is noisy detects whole and refuses
|
||||
// over the loop. That is the intent — the loop is what a Gate voice plays.
|
||||
// Anything else (no loop, an out-of-range span, a short one) yields the whole source.
|
||||
//
|
||||
// It takes NO play mode, deliberately, even though loop_span's resolveLoop does and refuses the
|
||||
// loop outright under Trigger. A loop edit is structurally reload-bound — it moves the PCM span
|
||||
// this cache was derived from — whereas play mode's exclusion from live delivery is a listed,
|
||||
// reversible decision (deck_groups' isLiveDeckParam). Keying a load-time cache on it would work
|
||||
// today and silently serve a stale period the day that decision is revisited.
|
||||
//
|
||||
// The read path's loop-validity authority is loop_span's resolveLoop; the bounds check here is
|
||||
// on a cache input, not a second validity rule, and it refuses rather than repairs the same way.
|
||||
struct AnalysisSpan {
|
||||
|
||||
Reference in New Issue
Block a user