# MultiPitchMelodia¶

standard mode | Pitch category

## Inputs¶

`signal`

(vector_real) - the input signal

## Outputs¶

`pitch`

(vector_vector_real) - the estimated pitch values [Hz]

## 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 multiple fundamental frequency contours from an audio signal. It is a multi pitch version of the MELODIA algorithm described in [1]. While the algorithm is originally designed to extract melody in polyphonic music, this implementation is adapted for multiple sources. 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 PitchContoursMultiMelody 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, maxFrequency, and voicingTolerance, which will depend on your application.

The output is a vector of vectors of estimated pitch values for each frame.

- 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.

## Source code¶

## See also¶

MultiPitchMelodia (streaming) PitchContours (standard) PitchContours (streaming) PitchContoursMultiMelody (standard) PitchContoursMultiMelody (streaming) PitchSalience (standard) PitchSalience (streaming) PitchSalienceFunction (standard) PitchSalienceFunction (streaming) PitchSalienceFunctionPeaks (standard) PitchSalienceFunctionPeaks (streaming)