PitchMelodia¶

standard mode | Pitch category

Inputs¶

signal (vector_real) - the input signal

Outputs¶

pitch (vector_real) - the estimated pitch values [Hz]

pitchConfidence (vector_real) - confidence with which the pitch was detected

Parameters¶

binResolution (real ∈ (0, ∞), default = 10) :
salience function bin resolution [cents]

filterIterations (integer ∈ [1, ∞), default = 3) :
number of iterations for the octave errors / pitch outlier filtering process

frameSize (integer ∈ (0, ∞), default = 2048) :
the frame size for computing pitch saliecnce

guessUnvoiced (bool ∈ {false, true}, default = false) :
estimate pitch for non-voiced segments by using non-salient contours when no salient ones are present in a frame

harmonicWeight (real ∈ (0, 1), default = 0.8) :
harmonic weighting parameter (weight decay ratio between two consequent harmonics, =1 for no decay)

hopSize (integer ∈ (0, ∞), default = 128) :
the hop size with which the pitch salience function was computed

magnitudeCompression (real ∈ (0, 1], default = 1) :
magnitude compression parameter for the salience function (=0 for maximum compression, =1 for no compression)

magnitudeThreshold (integer ∈ [0, ∞), default = 40) :
spectral peak magnitude threshold (maximum allowed difference from the highest peak in dBs)

maxFrequency (real ∈ [0, ∞), default = 20000) :
the maximum allowed frequency for salience function peaks (ignore contours with peaks above) [Hz]

minDuration (integer ∈ (0, ∞), default = 100) :
the minimum allowed contour duration [ms]

minFrequency (real ∈ [0, ∞), default = 40) :
the minimum allowed frequency for salience function peaks (ignore contours with peaks below) [Hz]

numberHarmonics (integer ∈ [1, ∞), default = 20) :
number of considered harmonics

peakDistributionThreshold (real ∈ [0, 2], default = 0.9) :
allowed deviation below the peak salience mean over all frames (fraction of the standard deviation)

peakFrameThreshold (real ∈ [0, 1], default = 0.9) :
per-frame salience threshold factor (fraction of the highest peak salience in a frame)

pitchContinuity (real ∈ [0, ∞), default = 27.5625) :
pitch continuity cue (maximum allowed pitch change during 1 ms time period) [cents]

referenceFrequency (real ∈ (0, ∞), default = 55) :
the reference frequency for Hertz to cent convertion [Hz], corresponding to the 0th cent bin

sampleRate (real ∈ (0, ∞), default = 44100) :
the sampling rate of the audio signal [Hz]

timeContinuity (integer ∈ (0, ∞), default = 100) :
time continuity cue (the maximum allowed gap duration for a pitch contour) [ms]

Description¶

This algorithm estimates the fundamental frequency corresponding to the melody of a monophonic music signal based on the MELODIA algorithm. While the algorithm is originally designed to extract the predominant melody from polyphonic music [1], this implementation is adapted for monophonic signals. The approach is based on the creation and characterization of pitch contours, time continuous sequences of pitch candidates grouped using auditory streaming cues. To this end, PitchSalienceFunction, PitchSalienceFunctionPeaks, PitchContours, and PitchContoursMonoMelody algorithms are employed. It is strongly advised to use the default parameter values which are optimized according to [1] (where further details are provided) except for minFrequency and maxFrequency, which will depend on your application.

The output is a vector of estimated melody pitch values and a vector of confidence values.

It is recommended to apply EqualLoudness on the input signal (see [1]) as a pre-processing stage before running this algorithm.

References:

[1] J. Salamon and E. Gómez, “Melody extraction from polyphonic music signals using pitch contour characteristics,” IEEE Transactions on Audio, Speech, and Language Processing, vol. 20, no. 6, pp. 1759–1770, 2012.

[2] http://mtg.upf.edu/technologies/melodia

[3] http://www.justinsalamon.com/melody-extraction

Source code¶

C++ source code

C++ header file