Piano performance, measured

How pianists differ, measured

624 recordings of 19 pieces were turned into lists of notes — every note's start, end, loudness, and both pedals — and compared. This page is the measurements first, then what they show. No musical training is assumed.

On this pagePart 1 · What is being measured — twelve things you can hearPart 2 · The rest of the measurementsPart 3 · What the recordings showPart 4 · What to trust

Part 1 · What is being measured

Each measurement below comes with two clips of the same performance of the same bars, with one quantity changed and nothing else touched. That is the point of them: if the two sound different, the difference is that one quantity. They are played by a computer from the notes, which is why they sound a little flat — that is deliberate, so nothing else distracts.

Here is the starting point everything is changed from: the notes played dead straight, and then the same bars set to the middle of what real pianists do.

Perfectly even — every note the same length and loudness0:11
The same bars at the middle of 31 real recordings0:10

After each pair there are the two real recordings that sit furthest apart on that measurement. They are harder to compare, because between two real recordings everything differs at once — which is the whole reason for measuring one thing at a time.

Timing — How the music sits in time.

Arch depthSchubert, Impromptu in G flat, bars 1–4

Does the music speed up and slow down across a long phrase, the way a sentence rises and falls — or does it hold one steady pace?

Barely any rise and fall0:18
A lot of rise and fall0:17

The second clip breathes: it presses forward in the middle of the phrase and eases at the end. The first stays level.

In 43 real recordings of this piece the measurement runs from 10.3 (Eric Lu 2013) to 28.0 (Maria Joao Pires), in ±%. Those two recordings:
Eric Lu 20130:18
Maria Joao Pires0:15

Beat swayBeethoven, "Pathétique" Sonata, slow movement, bars 1–4

Within the phrase, does the player stretch and squeeze individual beats, or keep them even?

Even beats0:18
Beats pushed and pulled0:18

This is smaller and more local than the last one — single beats leaning long or short, not the whole phrase shape.

In 47 real recordings of this piece the measurement runs from 5.3 (Francois Rene Duchable) to 11.3 (Rudolf Buchbinder), in ±%. Those two recordings:
Francois Rene Duchable0:19
Rudolf Buchbinder0:19

GrainMozart, Sonata in C, K. 545, bars 1–4

Below the level of the beat, are the fast running notes spaced evenly, like a machine, or slightly unevenly?

Evenly spaced0:09
Unevenly spaced0:09

Listen to the rippling left hand underneath, not the tune. In the second clip its notes are not quite evenly spaced.

In 37 real recordings of this piece the measurement runs from 4.3 (Hans Leygraf) to 10.7 (Carl Seemann), in % of beat. Those two recordings:
Hans Leygraf0:09
Carl Seemann0:09

Melody floatChopin, Fantaisie-Impromptu, bars 43–46

When one hand plays a steady accompaniment and the other plays the tune, does the tune land exactly with it, or drift behind?

Tune lands with the accompaniment0:14
Tune hangs behind it0:14

The accompaniment keeps the same time in both. Only the tune moves — in the second clip it hangs back behind the beat.

In 20 real recordings of this piece the measurement runs from -44 (Vladimir Feltsman) to 90 (Valentina Lisitsa), in ms. Those two recordings:
Vladimir Feltsman0:14
Valentina Lisitsa0:14

Vertical — Notes written to sound together almost never do. These measure how they come apart.

Hand dislocationSatie, Gymnopédie No. 1, bars 5–7

When both hands are written to strike at the same instant, do they actually arrive together? Often the left hand lands first, on purpose.

Hands together0:08
Left hand clearly first0:08

A gap of a few hundredths of a second. It does not sound like two events — it sounds like a different kind of warmth.

In 23 real recordings of this piece the measurement runs from -49 (Bertrand Chamayou) to 58 (Roberto Prosseda), in ms. Those two recordings:
Bertrand Chamayou0:08
Roberto Prosseda0:08

Melody leadChopin, Nocturne in C minor, bars 1–2

Inside a single chord played by one hand, does the top note — usually the tune — sound a fraction before the notes underneath it?

Top note with the rest0:12
Top note a little ahead0:12
Exaggerated, well past what anyone does0:12

This one is at the edge of what anyone can hear, which is worth knowing before trusting a description that claims to hear it. A deliberately exaggerated version is included so you know what to listen for.

In 27 real recordings of this piece the measurement runs from 0.0 (Zheyu Li) to 9.4 (Sheng Cai), in ms. Those two recordings:
Zheyu Li0:12
Sheng Cai0:12

Roll widthRachmaninoff, Prelude in C sharp minor, bars 1–2

Is a chord struck as one block, or spread out like a strum? And if spread, does it start from the lowest note or the highest?

Struck as a block0:14
Spread wide0:14
Spread from the bottom up0:14
Spread from the top down0:14

Four clips: narrow against wide, then upward against downward. The direction is a much clearer difference than the width.

The number that comes back out of a rolled chord is about twice the setting that went in, because the measurement spans the whole chord and so also picks up whatever the two hands are doing apart from each other. These four captions name the setting, not a measurement.

In 29 real recordings of this piece the measurement runs from 34 (Dubravka Tomsic) to 76 (Boris Giltburg), in ms. Those two recordings:
Dubravka Tomsic0:14
Boris Giltburg0:16

Dynamics — Loudness. It arrives as a number from 0 to 127 for how hard each key was struck — a "velocity unit" below. Roughly four units make a quarter of a decibel's difference; what matters is that it is only ever compared inside one recording.

Melody liftBrahms, Intermezzo in A, bars 1–3

How far above the other notes of its chord is the tune played — how much louder is the note you are meant to follow?

Tune no louder than the chord — nobody plays like this0:10
Tune a little above the chord0:10
Tune well above the chord0:10

The first clip has the tune at exactly the same loudness as everything under it. It is the thing no pianist does, and hearing it explains why.

In 28 real recordings of this piece the measurement runs from 12.5 (Michael Shilyaev) to 25.9 (Wilhelm Kempff), in vel. Those two recordings:
Michael Shilyaev0:11
Wilhelm Kempff0:08

Dynamic rangeDebussy, Clair de lune, bars 40–42

How far apart are the quietest and loudest notes — the distance the player uses between soft and loud.

Narrow — soft and loud close together0:10
Wide — soft and loud far apart0:10

Same notes, same speed. Only the distance between soft and loud changes.

In 27 real recordings of this piece the measurement runs from 39 (Monique Haas) to 63 (Lang Lang), in vel. Those two recordings:
Monique Haas0:11
Lang Lang0:11

Articulation — How long each note is held before the finger lets go.

Finger legatoBach, Prelude in C, bars 1–3

Does each note carry on until the next one starts, so the line is joined up — or is there a gap between them?

Gaps between the notes0:12
Notes overlapping into each other0:12

Neither clip uses the pedal, so the fingers are the only thing joining the notes. The first leaves audible gaps; the second overlaps them.

In 27 real recordings of this piece the measurement runs from -0.02 (Glenn Gould) to 1.30 (Pierre Laurent Aimard), in ratio. Those two recordings:
Glenn Gould0:13
Pierre Laurent Aimard0:13

Pedal — The feet.

Pedal rateChopin, Nocturne in E flat, bars 2–3

The right pedal lets strings keep ringing after the fingers leave the keys. Is it lifted and re-pressed at every new chord, keeping things clear, or held across several so they blur together?

No pedal0:14
Changed at every chord — clear0:14
Held across chords — blurred0:14

Three clips: no pedal at all, pedal changed at every chord, and pedal held so the harmonies run into one another.

In 32 real recordings of this piece the measurement runs from 2.53 (Daniel Barenboim) to 4.53 (Aldo Ciccolini), in /bar. Those two recordings:
Daniel Barenboim0:16
Aldo Ciccolini0:17

Pedal lagAphex Twin, Avril 14th, bars 1–3

The pedal is almost never pressed at the same instant as the chord. It comes just after, which catches the new chord and drops the old one. How long after?

Pedal caught quickly after the chord0:11
Pedal caught later0:11

Every pianist measured here does this. Only the delay differs, and it changes how cleanly one harmony gives way to the next.

In 5 real recordings of this piece the measurement runs from 98 (Josh Cohen) to 204 (Olga Scheps), in ms. Those two recordings:
Josh Cohen0:11
Olga Scheps0:09

Part 2 · The rest of the measurements

Twelve of about thirty. The others are listed here in plain words; each links to its own page, which has the same two-ended audio.

MeasurementWhat it is
Basic tempoHow fast the piece goes overall.
LingerHow long the longest hesitations are, measured against the player's own pulse.
Section contrastWhether a player presses on into a contrasting section or draws back.
Coda fadeHow much the closing bars are broadened relative to the music just before them.
Repeat fidelityWhen a passage comes back, how closely its timing repeats the first statement.
Bass anticipationHow often the bass is placed clearly ahead of the melody.
Rolled fractionHow often block chords are rolled at all.
Roll directionWhen a chord is rolled, whether it starts from the bottom or the top.
Third liftThe same lift, but measured only among the notes of the right hand.
Hand balanceHow much louder the right hand is than the left.
Top-loudest rateHow reliably the top note is the loudest note of its chord.
Climax spanHow much louder the piece's high point is than its opening.
High-loud slopeWhether higher notes are played louder.
Contour smoothnessHow smoothly the melody's loudness changes from note to note.
Melody roughnessThe opposite view of the same thing: note-to-note jumps in melody loudness.
Detachment rateHow often the melody is detached rather than joined.
Accompaniment legatoThe same overlap measure, applied to the accompaniment.
Pedal densityHow much of the time the sustain pedal is down.
BlurHow many changes of harmony are allowed to overlap under one pedal.
Soft-pedal shareHow much of the time the una corda is down.
Emergent voiceHow often a player brings out a line that the other players of the same piece leave inside the texture.

Part 3 · What the recordings show

The list does not collapse into two or three things

A fair objection: maybe these thirty measurements are really three or four things wearing different labels — perhaps everyone who spreads chords widely also plays loudly. That can be tested by asking how much of the difference between recordings survives if you keep only a few combined measurements. The best single combination captures 18 % of it; the best two together 35 %. The rest is spread thinly across everything else.

So there is no small hidden set of master dials. To describe what separates one pianist from another you need most of the list.

The numbers can identify a pianist in music they have never been heard playing

Two versions of the question, with very different answers.

The easy one. Given a few seconds of a recording the computer has heard other parts of, name the pianist out of 27 candidates. Guessing gets 4 %. Four bars of music gets about 39 % if it may use every measurement — but only 8–14 % if restricted to one family at a time. No single aspect of playing carries someone's identity.

The hard one, and the real one. Work out a pianist's habits from their other recordings, then show the computer a piece by a different composer that this pianist has never been heard in, and ask who it is. Across 221 such tests it names the right person 43 % of the time, against 7 % for guessing — six times better than chance. Allowed three guesses, the right pianist is on the list 66 % of the time.

That is the substantive claim: a pianist's habits are portable enough to survive a change of composer. It is not reliable identification, and it is nothing like what an experienced listener does — but it is a long way from guessing.

Some habits belong to the pianist; others are decided fresh for each piece

For every pianist appearing in more than one piece, does being high on a measurement in one piece predict being high on it in another? The correlation runs from 0 (nothing carries over) to 1 (it carries over completely).

MeasurementCarries overReading
Melody lead+0.49travels with the person
Dynamic range+0.39travels with the person
Roll direction+0.38travels with the person
Hand dislocation+0.34travels with the person
Melody float+0.33travels with the person
Pedal changes / bar+0.32travels with the person
Hand balance+0.26partly
Roll width+0.25partly
Pedal lag+0.24partly
Melody lift+0.23partly
Beat sway+0.18set by the piece
Emergent voice+0.17set by the piece
Soft pedal+0.14set by the piece
Finger legato+0.14set by the piece
Section contrast+0.07set by the piece
Grain+0.07set by the piece

The pattern rearranges the usual vocabulary. What belongs to the person is how the notes of a chord come apart and how the two hands are weighed against each other. What is mostly decided for the piece includes the one that gets praised most — how far the tune is lifted above its chord. How evenly someone spaces fast notes carries over not at all.

Two of the weakest entries here are measurements the transcription is bad at (see Part 4). A measurement made badly cannot show a habit even when there is one, so for those the honest conclusion is "this cannot tell you", not "it does not carry over".

Hard pieces leave pianists less room, not more

For each piece: how far apart its recordings sit, in real units, against how far apart pianists sit in general. 1.0 would mean "as varied as pianists anywhere"; 0.5 means these players agree twice as closely.

Most variedLeast varied
Bach Prelude in C0.64Schubert Op. 142/30.30
Träumerei0.63Chopin Ballade 40.32
Nocturne Op. 9/20.62Chopin Étude 10/10.35

The whole range is narrow — every piece leaves roughly the same amount of room. But the order runs against intuition: the pieces at the bottom are the hard ones, and the pieces at the top are ones a student meets in the first year or two. The clearest version is inside one composer — Ravel wrote both the Pavane, which a beginner can hold, and Ondine, which pianists work at for years. They sit two places apart out of nineteen.

One explanation is attention: a piece that does not threaten the notes leaves the player nothing to do but decide how it should go. Another is simpler — a hard piece is hard partly because the composer specified a great deal, and specification is what leaves no room. Nothing here separates the two.

A spread measured on few recordings reads low. The three at the bottom have the fewest recordings; corrected for that they come out level with each other rather than lowest. The direction of the finding survives, but no single position in the middle of the table should be read closely.

Amateurs use the same vocabulary, less far and less consistently

83 of the recordings are by people who are not professionals. The expectation is that they differ the way a beginner's handwriting differs from a calligrapher's: the same letters, worse. That is half right.

The half that holds is scatter. Their note-to-note consistency is far wider — lead scatter 2.4×, pedal changes / bar 2.3×, melody roughness 2.2×, articulation scatter 2.1× the professionals' spread.

The half that fails is the expressive measurements. On those the home recordings are not more varied but less, and sit toward the modest end of every one: narrower between soft and loud, less lift on the tune, less separation between the hands. They do not have a different vocabulary. They use less of the same one, with more noise around each word.

On this evidence skill is not a style. It is the tightness of the scatter around a style, and separately the confidence to move a measurement far from the middle.

A piano with sensors shows a quarter of the pedalling is invisible

111 of the recordings did not come from listening to audio at all. They are from a competition whose entrants play a piano with a sensor under every key and pedal, so the instrument wrote the file as it was played.

A transcription reports the sustain pedal as a switch — down or up. The sensors report its position continuously, and show these pianists holding it part-way down about 26 % of the time: catching some of the ringing and letting the rest go. It is something pianists discuss constantly and it is entirely absent from every audio transcription here, which has only two positions to describe it with.

So the pedal measurements on this page are real, but they are a continuous gesture seen through a switch.

The same pianist, years apart, changes some things and not others

One pianist is in the corpus twice: as a fifteen-year-old competitor in 2013 and in commercial recordings of the same two pieces in 2018. What did not move in either piece is the group of habits above — how far the tune is lifted, how the hands are weighed, how much the fingers overlap, how often the foot changes (identical to one decimal place, five years apart).

What moved, and moved the same way in both pieces: slower, chords spread wider, hands closer together, pedal later, phrases arched a little more. A second pianist, recorded fourteen years apart, shows the same split — but moved in the opposite direction on two of them. Whatever the years did, it was not a general law of growing up.

Two pianists prove nothing general. It is the shape a real answer would have.

Part 4 · What to trust

The measurements come from software listening to a recording. That can be checked: a sensor recording was played back through a synthesiser, handed to the same software as if it were audio, and re-measured — the same performance, once known exactly and once guessed. The error is shown below as a fraction of how far pianists actually differ. Below about 0.4 the error is small next to the thing being measured; above 1.0 the error is bigger than the signal.

MeasurementError ÷ real spread
Bass anticipation0.04trustworthy
Basic tempo0.06trustworthy
Linger0.06trustworthy
Arch depth0.06trustworthy
Section contrast0.07trustworthy
Melody float0.09trustworthy
Coda fade0.13trustworthy
Beat sway0.16trustworthy
Repeat fidelity0.27trustworthy
Melody lead0.32trustworthy
Roll direction0.35trustworthy
Hand dislocation0.35trustworthy
Roll width0.39trustworthy
Emergent voice0.51usable
Pedal density0.54usable
Rolled fraction0.57usable
Pedal lag0.73usable
Third lift0.86usable
Grain1.00do not rely on
Melody roughness1.07do not rely on
Soft-pedal share1.20do not rely on
Blur1.24do not rely on
Top-loudest rate1.31do not rely on
Pedal rate1.43do not rely on
Accompaniment legato1.60do not rely on
Finger legato1.60do not rely on
Melody lift1.62do not rely on
High-loud slope1.62do not rely on
Climax span1.95do not rely on
Detachment rate1.96do not rely on
Hand balance1.98do not rely on
Dynamic range2.08do not rely on
Contour smoothness2.47do not rely on

Everything built from when a note starts survives almost intact — the timing measurements on this page are essentially exact. Everything built from when a note stops, how loud it was, or where the foot was is worse than the differences it is being used to measure.

Two things soften that and one sharpens it. The errors are mostly consistent biases rather than random noise — the software compresses everyone's loudness by about the same amount — and a bias shared by everyone largely cancels when the question is who is wider than whom. But noise also pushes correlations toward zero, so where a badly-measured quantity still showed a habit carrying over, the real effect is probably stronger than stated.

This test is a floor, not an estimate. The audio was synthesised cleanly, with no room, no audience and no tape hiss, so real recordings are harder than this and the true errors are larger.