streaming mode | Tonal category
- pcp (vector_real) - the pitch class profile from which to detect the chord
- chords (string) - the resulting chords, from A to G
- strength (real) - the strength of the chord
- hopSize (integer ∈ (0, ∞), default = 2048) :
- the hop size with which the input PCPs were computed
- sampleRate (real ∈ (0, ∞), default = 44100) :
- the sampling rate of the audio signal [Hz]
- windowSize (real ∈ (0, ∞), default = 2) :
- the size of the window on which to estimate the chords [s]
This algorithm estimates chords given an input sequence of harmonic pitch class profiles (HPCPs). It finds the best matching major or minor triad and outputs the result as a string (e.g. A#, Bm, G#m, C). The following note names are used in the output: "A", "Bb", "B", "C", "C#", "D", "Eb", "E", "F", "F#", "G", "Ab". Note:
- The algorithm assumes that the sequence of the input HPCP frames has been computed with framesize = 2*hopsize
- The algorithm estimates a sequence of chord values corresponding to the input HPCP frames (one chord value for each frame, estimated using a temporal window of HPCPs centered at that frame).
Quality: experimental (prone to errors, algorithm needs improvement)
 E. Gómez, "Tonal Description of Polyphonic Audio for Music Content Processing," INFORMS Journal on Computing, vol. 18, no. 3, pp. 294–304, 2006.
 D. Temperley, "What's key for key? The Krumhansl-Schmuckler key-finding algorithm reconsidered", Music Perception vol. 17, no. 1, pp. 65-100, 1999.