Melody Features Summary

This table provides a comprehensive overview of all melody features available in this package.

0 features
Name Pre-existing Implementations Further References Description Type Notes
Absolute Interval Range FANTASTIC The range between the largest and smallest absolute interval size. Descriptor
Amount Of Arpeggiation jSymbolic The proportion of pitch intervals in the melody that constitute triadic movements. Descriptor
Amount Of Staccato jSymbolic The proportion of notes with a duration shorter than 0.1 seconds. Descriptor
Average Interval Span By Melodic Arcs jSymbolic The average interval span of melodic arcs. Descriptor
Average Length Of Melodic Arcs jSymbolic The average number of notes that separate peaks and troughs in melodic arcs. Descriptor
Average Note Duration jSymbolic The average note duration in seconds. Descriptor
Basic Pitch Histogram jSymbolic A histogram of pitch values within the range of input pitches. Sequence We use the histogram in the range of input pitches to reduce the output size. An implementation that is truer to the original jSymbolic implementation would return 128 bins (0-127) regardless of how any different pitches are present. However, we believe our approach is more concise and easier to understand for many purposes.
Chromatic Motion jSymbolic The proportion of chromatic motion in the melody. Chromatic motion is defined as a melodic interval of 1 semitone. Descriptor
Comb Contour Matrix MIDI Toolbox Marvin & Laprade (1987) The Marvin & Laprade (1987) comb contour matrix. For a melody with n notes, returns an n x n binary matrix where C[i][j] = 1 if pitch of note j is higher than pitch of note i (p[j] > p[i]) for i >= j (lower triangle including diagonal), and 0 otherwise. Descriptor
Combined Strength Of Two Strongest Rhythmic Pulses jSymbolic Sum of the magnitudes of the two strongest rhythmic pulses. Descriptor
Combined Strength Of Two Strongest Rhythmic Pulses Tempo Standardized jSymbolic Sum of the magnitudes of the two strongest rhythmic pulses using tempo-standardized histogram. Descriptor
Complebm Optimal MIDI Toolbox Eerola & North (2000) Expectancy-based melodic complexity calculated using an optimal combination of pitch patterns and rhythmic features, according to Eerola & North (2000). The complexity score is normalized against the Essen folksong collection, where a score of 5 represents average complexity. Descriptor
Complebm Pitch MIDI Toolbox Eerola & North (2000) Expectancy-based melodic complexity calculated using pitch patterns only, according to Eerola & North (2000). The complexity score is normalized against the Essen folksong collection, where a score of 5 represents average complexity. Descriptor
Complebm Rhythm MIDI Toolbox Eerola & North (2000) Expectancy-based melodic complexity calculated using rhythmic features only, according to Eerola & North (2000). The complexity score is normalized against the Essen folksong collection, where a score of 5 represents average complexity. Descriptor
Complete Rests Fraction jSymbolic The fraction of the total duration during which no pitched notes are sounding. Descriptor
Compltrans MIDI Toolbox Simonton (1984) The melodic originality measure, according to Simonton (1984). Calculated based on 2nd order pitch-class distribution derived from 15,618 classical music themes. Higher values indicate higher melodic originality (less predictable transitions). Descriptor
Difference Between Most Common Rhythmic Values jSymbolic The absolute difference in bins between most and second most common rhythmic values. Descriptor
Direction Of Melodic Motion jSymbolic The proportion of upward melodic motions with regards to the total number of melodic motions. Descriptor
Distance Between Most Prevalent Melodic Intervals jSymbolic The absolute difference between the two most common interval sizes. Descriptor
Dominant Spread jSymbolic The longest sequence of pitch classes separated by perfect 5ths that each appear >9% of the time. Descriptor
Dotted Duration Transitions FANTASTIC Steinbeck (1982) The proportion of duration transitions that are dotted. Descriptor
Duration Accent MIDI Toolbox Parncutt (1994) Calculate duration accent for each note based on Parncutt (1994). Duration accent represents the perceptual salience of notes based on their duration. Sequence The MIDI toolbox implementation uses defaults of 0.5 for tau (saturation duration) and 2.0 for accent_index (minimum discriminable duration).
Duration Accent Std MIDI Toolbox Parncutt (1994) The standard deviation of duration accents. Duration accent represents the perceptual salience of notes based on their duration, as defined by Parncutt (1994). Descriptor
Duration Entropy FANTASTIC The zeroth-order base-2 entropy of the duration distribution in quarter notes. Descriptor
Duration Histogram jSymbolic A histogram of note durations in quarter notes. Sequence
Duration Range FANTASTIC The range between the longest and shortest note duration in quarter notes. Descriptor
Duration Standard Deviation Novel The standard deviation of note durations in quarter notes. Descriptor
Equal Duration Transitions FANTASTIC Steinbeck (1982) The proportion of duration transitions that are equal in length. Descriptor
First Pitch jSymbolic The first pitch number in the melody. Descriptor
First Pitch Class jSymbolic The first pitch class in the melody. Descriptor
Folded Fifths Pitch Class Histogram jSymbolic A histogram of pitch classes arranged according to the circle of fifths. Sequence
Global Duration FANTASTIC, jSymbolic The total duration in seconds of the melody. Descriptor This feature is named 'Duration in Seconds' in JSymbolic.
Gradus MIDI Toolbox Euler (1739) The degree of melodiousness based on Euler's gradus suavitatis. Descriptor
Half Duration Transitions FANTASTIC Steinbeck (1982) The proportion of duration transitions that are halved or doubled. Descriptor
Harmonicity Of Two Strongest Rhythmic Pulses jSymbolic The ratio of higher to lower bin index of the two strongest rhythmic pulses. Descriptor
Harmonicity Of Two Strongest Rhythmic Pulses Tempo Standardized jSymbolic The ratio of higher to lower bin index of the two strongest rhythmic pulses (120-BPM standardized histogram). Descriptor
Honore's H FANTASTIC Honoré (1979) Honoré's H measure corresponds to the observation that the number of tokens occuring exactly once in a sequence is logarithmically related to the total number of tokens in the sequence. Descriptor
Huron Contour Class Label FANTASTIC Huron (1996) The contour classification for the melody, according to Huron's system. Descriptor
IOI IDyOM The time between consecutive onsets (inter-onset interval). Sequence
IOI Contour Novel The sequence of IOI contour values (-1: shorter, 0: same, 1: longer). Sequence
IOI Contour Mean Novel The arithmetic mean of IOI contour values. Descriptor
IOI Contour Standard Deviation Novel The standard deviation of IOI contour values. Descriptor
IOI Histogram Novel A histogram of inter-onset intervals. Sequence
IOI Mean IDyOM, jSymbolic The arithmetic mean of inter-onset intervals. Descriptor This is called average_time_between_attacks in jSymbolic.
IOI Range Novel The range of inter-onset intervals. Descriptor
IOI Ratio IDyOM The sequence of inter-onset interval ratios. Sequence
IOI Ratio Mean Novel The arithmetic mean of inter-onset interval ratios. Descriptor
IOI Ratio Standard Deviation Novel The standard deviation of inter-onset interval ratios. Descriptor
IOI Standard Deviation IDyOM, jSymbolic The standard deviation of inter-onset intervals. Descriptor This is called variability_of_time_between_attacks in jSymbolic.
Importance Of Bass Register jSymbolic The proportion of pitch numbers in the melody that are between 0 and 54. Descriptor
Importance Of High Register jSymbolic The proportion of pitch numbers in the melody that are between 73 and 127. Descriptor
Importance Of Middle Register jSymbolic The proportion of pitch numbers in the melody that are between 55 and 72. Descriptor
Initial Tempo FANTASTIC, jSymbolic The first tempo of the melody. Descriptor
Inscale IDyOM For each pitch in the melody, returns 1 if the pitch is in the estimated key's scale, or 0 if it deviates from the scale. Sequence
Interpolation Contour Class Label FANTASTIC Classify an interpolation contour into gradient categories. The contour is sampled at 4 equally spaced points and each gradient is normalized to units of pitch change per second (scaled to 1 semitone per 0.25 seconds.) The result is then classified into one of 5 categories: - 'a': Strong downward (-2) - normalized gradient <= -1.45 - 'b': Downward (-1) - normalized gradient between -1.45 and -0.45 - 'c': Flat (0) - normalized gradient between -0.45 and 0.45 - 'd': Upward (1) - normalized gradient between 0.45 and 1.45 - 'e': Strong upward (2) - normalized gradient >= 1.45 Descriptor
Interpolation Contour Direction Changes FANTASTIC The proportion of interpolated gradient values that consistute a change in direction. For instance, a gradient value of -0.5 to 0.25 is a change in direction. Descriptor
Interpolation Contour Global Direction FANTASTIC The sign of the sum of all contour values. Descriptor
Interpolation Contour Gradient Std FANTASTIC The standard deviation of the interpolation contour gradients. Descriptor
Interpolation Contour Mean Gradient FANTASTIC The absolute mean gradient of the interpolation contour. Descriptor
Interval Between Most Prevalent Pitch Classes jSymbolic The number of semitones between the two most prevalent pitch classes. Descriptor
Interval Between Most Prevalent Pitches jSymbolic The number of semitones between the two most prevalent pitches. Descriptor
Interval Direction SIMILE The sequence of interval directions in the melody. Sequence
Interval Direction Mean Novel The mean of the direction of each interval in the melody. Descriptor
Interval Direction Std Novel The standard deviation of the direction of each interval in the melody. Descriptor
Interval Entropy FANTASTIC The zeroth-order base-2 entropy of the interval distribution. Descriptor
Ivdirdist1 MIDI Toolbox The proportion of upward intervals for each interval size (1-12 semitones). Returns the proportion of upward intervals for each interval size in the melody as a dictionary mapping interval sizes to their directional bias values. Sequence
Ivdist1 MIDI Toolbox The distribution of intervals in the melody, weighted by their durations. Sequence
Ivsizedist1 MIDI Toolbox The distribution of interval sizes (0-12 semitones). Returns the distribution of interval sizes by combining upward and downward intervals of the same absolute size. The first component represents a unison (0) and the last component represents an octave (12). Sequence
Key Novel Krumhansl (1990) The key of the melody, either read from the MIDI file or estimated using the specified key finding algorithm, depending on the key estimation strategy. Sequence
Last Pitch jSymbolic The last pitch number in the melody. Descriptor
Last Pitch Class jSymbolic The last pitch class in the melody. Descriptor
Length FANTASTIC The total number of notes. Descriptor
Longest Complete Rest jSymbolic The longest uninterrupted complete rest in quarter-note units (ignoring rests shorter than 0.1 QN). Descriptor
Longest Conjunct Scalar Passage Novel The longest sequence of consecutive notes that fit within the estimated key's scale. For example, a melody estimated to be in C major with notes C, D, E, F, G would have a longest conjunct scalar passage of 5. Descriptor
Longest Monotonic Conjunct Scalar Passage Novel The longest sequence of consecutive notes that fit within the estimated key's scale that move in the same direction. Descriptor
Longest Rhythmic Value jSymbolic The longest rhythmic value (in quarter notes) among non-empty bins. Descriptor
Max Log DF FANTASTIC Calculate maximum log document frequency across all n-grams. Descriptor
Maximum Note Duration jSymbolic The maximum note duration in seconds. Descriptor
Mean Absolute Interval FANTASTIC, jSymbolic The arithmetic mean of the absolute intervals in the melody. Descriptor This feature is named 'Mean Melodic Interval' in JSymbolic.
Mean Cloud Diameter Partitura Herremans & Chew (2016) Mean cloud diameter from the tonal tension model. Cloud Diameter provides a measure of the maximal tonal distance of the notes in a chord, following the definition in Partitura. Descriptor
Mean Cloud Momentum Partitura Herremans & Chew (2016) Mean cloud momentum from the tonal tension model. Cloud momentum captures movement of pitch sets in the spiral array space, weighted by note durations, following the definition in Partitura. Descriptor
Mean Complete Rest Duration jSymbolic The mean duration of complete rests in quarter-note units (ignoring rests shorter than 0.1 QN). Descriptor
Mean Duration Novel The mean note duration in quarter notes. Descriptor
Mean Duration Accent MIDI Toolbox Parncutt (1994) The mean duration accent across all notes. Duration accent represents the perceptual salience of notes based on their duration, as defined by Parncutt (1994). Descriptor
Mean Entropy FANTASTIC Calculate the zeroth-order base-2 entropy of m-types across all n-gram lengths. Descriptor
Mean Global Local Weight FANTASTIC Calculate mean global-local weight using inverse entropy weighting. Descriptor
Mean Global Weight FANTASTIC Calculate mean global weight using inverse entropy weighting. Descriptor
Mean Log DF FANTASTIC Calculate mean log document frequency across all n-grams. Descriptor
Mean Log TFDF FANTASTIC Calculate mean log TF-DF score across all n-grams. Descriptor
Mean Melodic Accent MIDI Toolbox Thomassen (1982) The arithmetic mean of the melodic accent values across all notes. Melodic accent is defined by Thomassen's model (1982) according to the possible melodic contours arising in 3-pitch windows. Descriptor
Mean Melodic Attraction MIDI Toolbox Lerdahl (1996) The arithmetic mean of the melodic attraction values across all notes. Descriptor
Mean Mobility MIDI Toolbox The arithmetic mean of the mobility values across all notes. Descriptor
Mean Pitch jSymbolic The arithmetic mean of the pitch numbers in the melody. Descriptor
Mean Pitch Class jSymbolic The arithmetic mean of the pitch classes in the melody. Descriptor
Mean Productivity FANTASTIC Mean productivity is defined as the mean of the number of types occurring only once divided by the total number of tokens. The types occurring only once in a sequence are known as hapax legomena. Descriptor
Mean Rhythmic Value jSymbolic The mean rhythmic value (in quarter notes) using the normalized histogram, weighted by the frequency of the rhythmic value. Descriptor
Mean Rhythmic Value Offset jSymbolic The mean quantized offset from the nearest ideal rhythmic value (in quarter notes). Descriptor
Mean Rhythmic Value Run Length jSymbolic The mean run length of identical rhythmic values across the melody. Run length is the number of consecutive notes with the same rhythmic value. Returns 0.0 if there are fewer than 1 notes. Descriptor
Mean Tempo jSymbolic The mean tempo of the melody. Descriptor
Mean Tensile Strain Partitura Herremans & Chew (2016) Mean tensile strain from the tonal tension model. Tensile strain provides a measure of the distance between the local and global tonal context, following the definition in Partitura. Descriptor
Mean Tessitura MIDI Toolbox The arithmetic mean of the sequence of tessitura values. Descriptor
Median Complete Rest Duration jSymbolic The median duration of complete rests in quarter-note units (ignoring rests shorter than 0.1 QN). Descriptor
Median Rhythmic Value Offset jSymbolic The median quantized offset from the nearest ideal rhythmic value (in quarter notes). Descriptor
Median Rhythmic Value Run Length jSymbolic The median run length of identical rhythmic values across the melody. Run length is the number of consecutive notes with the same rhythmic value. Descriptor
Melodic Accent MIDI Toolbox Thomassen (1982) Calculate melodic accent salience according to Thomassen's model. Implementation based on MIDI toolbox "melaccent.m" In Thomassen's approach, melodic accents are determined based on the melodic contour formed by each group of three consecutive pitches. The accent strength ranges from 0 (no salience) to 1 (maximum salience). Sequence
Melodic Accent Std MIDI Toolbox Thomassen (1982) The standard deviation of the melodic accent values across all notes. Descriptor
Melodic Attraction MIDI Toolbox Lerdahl (1996) The melodic attraction according to Lerdahl (1996). Each tone in a key has certain anchoring strength ("weight") in tonal pitch space. Melodic attraction strength is affected by the distance between tones and directed motion patterns. Sequence
Melodic Attraction Std MIDI Toolbox Lerdahl (1996) The standard deviation of the melodic attraction values across all notes. Descriptor
Melodic Embellishment jSymbolic The proportion of melodic embellishments in the melody. Melodic embellishments are identified by notes that are surrounded on both sides by notes with durations at least 3 times longer than the central note. Descriptor
Melodic Interval Histogram jSymbolic A histogram of interval sizes. Sequence
Melodic Large Intervals jSymbolic The proportion of intervals >= 13 semitones. Descriptor
Melodic Octaves jSymbolic The proportion of intervals that are octaves (12 semitones). Descriptor
Melodic Perfect Fifths jSymbolic The proportion of intervals that are perfect fifths (7 semitones). Descriptor
Melodic Perfect Fourths jSymbolic The proportion of intervals that are perfect fourths (5 semitones). Descriptor
Melodic Pitch Variety jSymbolic The average number of notes that pass before a pitch is repeated. Descriptor
Melodic Sevenths jSymbolic The proportion of intervals that are sevenths (10 or 11 semitones). Descriptor
Melodic Sixths jSymbolic The proportion of intervals that are sixths (8 or 9 semitones). Descriptor
Melodic Thirds jSymbolic The proportion of intervals that are thirds (3 or 4 semitones). Descriptor
Melodic Tritones jSymbolic The proportion of intervals that are tritones (6 semitones). Descriptor
Meter Accent MIDI Toolbox Phenomenal accent synchrony measure, calculated as the negative mean of the product of metric hierarchy, melodic accent, and durational accent for each note. Higher values indicate stronger accent synchrony. Implementation based on MIDI toolbox meteraccent.m. Descriptor
Meter Denominator jSymbolic Time signature denominator for the melody. Descriptor
Meter Numerator jSymbolic Time signature numerator for the melody. Descriptor
Metric Hierarchy MIDI Toolbox Metric hierarchy values for each note, indicating the strength of each note position within the known or estimated meter. Higher values indicate stronger metric positions (e.g., downbeat = 5, beat = 4, half-beat = 3, etc.). Implementation based on MIDI toolbox metrichierarchy.m. Descriptor
Min Log DF FANTASTIC Calculate minimum log document frequency across all n-grams. Descriptor
Minimum Note Duration jSymbolic The minimum note duration in seconds. Descriptor
Minor Major Third Ratio jSymbolic The ratio of minor thirds to major thirds. Descriptor
Mobility MIDI Toolbox von Hippel (2000) The melodic mobility for each note based on von Hippel (2000). Mobility describes why melodies change direction after large skips by observing that they would otherwise run out of the comfortable melodic range. It uses lag-one autocorrelation between successive pitch heights. Sequence
Mobility Std MIDI Toolbox The standard deviation of the mobility values across all notes. Descriptor
Modal Duration FANTASTIC, jSymbolic The most common note duration in quarter notes. Descriptor
Modal Interval FANTASTIC, jSymbolic The most common interval size in the melody. Descriptor This feature is named 'Most Common Interval' in JSymbolic.
Mode FANTASTIC Calculate the mode (major/minor) of a melody, either read from the MIDI file or estimated using the specified key finding algorithm. Sequence
Most Common Pitch jSymbolic The most frequently occurring pitch number in the melody. Descriptor
Most Common Pitch Class jSymbolic The most frequently occurring pitch class in the melody. Descriptor
Most Common Rhythmic Value jSymbolic The modal rhythmic value (in quarter notes). Descriptor
NPVI MIDI Toolbox Patel & Daniele (2003) The normalized Pairwise Variability Index (NPVI) of note durations in quarter notes. The NPVI measures the durational variability of events, originally developed for language research to distinguish stress-timed vs. syllable-timed languages. Applied to music by Patel & Daniele (2003) to study the prosodic influences on musical rhythm. Descriptor
Narmour Closure IDyOM, MIDI Toolbox Narmour (1990) A score of 1 is given if the last three notes in a melody constitute a change in direction. Another score of 1 is given if the final interval is more than one tone smaller than the penultimate. As such, this returns integer values between 0 and 2. Descriptor
Narmour Intervallic Difference IDyOM, MIDI Toolbox Narmour (1990) If a large interval is followed by a smaller interval, returns 1 if either: - The smaller interval continues in the same direction and is at least 3 semitones smaller - The smaller interval changes direction and is at least 2 semitones smaller Additionally, returns 1 if a small interval is followed by another interval of the same size. Otherwise returns 0. Descriptor
Narmour Proximity IDyOM, MIDI Toolbox Narmour (1990) Proximity is defined as 6 minus the absolute interval between the last two notes. Descriptor
Narmour Registral Direction IDyOM, MIDI Toolbox Narmour (1990) The score is set to zero. If an interval greater than a perfect fifth is followed by a direction change, a score of 1 is given. If an interval smaller than a perfect fourth continues in the same direction, a score of 1 is given. This feature returns either 0 or 1 accordingly. Descriptor
Narmour Registral Return IDyOM, MIDI Toolbox Narmour (1990) If the last three notes move away from and then back to the same pitch, a score of 3 is returned. If the pitch returned to is 1 semitone away from the initial, returns 2. If the pitch returned to is 2 semitones away from the initial, returns 1. Otherwise, a score of 0 is returned. Descriptor
Norm Log Dist FANTASTIC Calculate normalized log distance between TF and DF distributions. Descriptor
Note Density FANTASTIC, jSymbolic The average number of notes per second. Descriptor
Note Density Per Quarter Note jSymbolic The average number of note onsets per unit of time corresponding to an idealized quarter note duration based on the tempo. Descriptor
Note Density Per Quarter Note Variability jSymbolic The standard deviation of note density per quarter note. Divides the melody into 8-quarter-note windows and calculates the standard deviation of note density across these windows. Descriptor Our tests indicate a certain discrepancy between our outputs and JSymbolic's outputs, which may be a consequence of JSymbolic's tick-based approach, or perhaps its idiosyncratic windowing approach.
Note Density Variability jSymbolic The standard deviation of note density across 5-second windows. Descriptor Our tests indicate a certain discrepancy between our outputs and JSymbolic's outputs, which may be a consequence of JSymbolic's tick-based approach, or perhaps its idiosyncratic windowing approach.
Number Of Common Melodic Intervals jSymbolic The number of intervals that appear in at least 9% of melodic transitions. Descriptor
Number Of Common Pitches jSymbolic The number of unique pitch numbers that appear in at least 9% of total notes. Descriptor
Number Of Common Pitches Classes jSymbolic The number of pitch classes that appear in at least 20% of total notes. Descriptor
Number Of Common Rhythmic Values Present jSymbolic The number of rhythmic value bins with normalized proportion >= 0.15. Descriptor
Number Of Different Rhythmic Values Present jSymbolic The number of distinct rhythmic value bins that are present in the melody (non-zero). Descriptor
Number Of Moderate Rhythmic Pulses jSymbolic The number of beat histogram peaks with normalized magnitudes over 0.01. Descriptor
Number Of Moderate Rhythmic Pulses Tempo Standardized jSymbolic The number of tempo-standardized beat histogram peaks with normalized magnitudes over 0.01. Descriptor
Number Of Relatively Strong Rhythmic Pulses jSymbolic The number of peaks at least 30% of the max magnitude. Descriptor
Number Of Relatively Strong Rhythmic Pulses Tempo Standardized jSymbolic The number of tempo-standardized peaks at least 30% of the max magnitude. Descriptor
Number Of Strong Rhythmic Pulses jSymbolic The count of BPM bins with pulses greater than 0.001. Descriptor
Number Of Strong Rhythmic Pulses Tempo Standardized jSymbolic The count of BPM bins with pulses greater than 0.001 using the tempo-standardized beat histogram. Descriptor
Number Of Unique Durations Novel The number of unique note durations, measured in quarter notes. Descriptor
Number Of Unique Pitch Classes jSymbolic The number of unique pitch classes in the melody. Descriptor
Number Of Unique Pitches jSymbolic The number of unique pitch numbers in the melody. Descriptor
Number Of Unique Time Signatures jSymbolic The number of unique time signatures in the melody. Descriptor This feature is named "Metrical Diversity" in jSymbolic.
Onset Autocorr Peak MIDI Toolbox The maximum onset autocorrelation value (excluding lag 0). Descriptor
Onset Autocorrelation MIDI Toolbox The autocorrelation function of onset times weighted by duration accents. This is calculated by weighting the onset times by the duration accents, as defined by Parncutt (1994). Sequence
Pcdist1 MIDI Toolbox The distribution of pitch classes in the melody, weighted by the duration of the notes. Sequence
Pitch Class Kurtosis jSymbolic The sample excess kurtosis of the pitch class histogram. Descriptor
Pitch Class Kurtosis After Folding jSymbolic The sample excess kurtosis of the pitch class histogram, after arranging the pitch classes according to the circle of fifths. Descriptor
Pitch Class Skewness jSymbolic The skewness of the pitch class histogram, using Pearson's median skewness formula. Descriptor
Pitch Class Skewness After Folding jSymbolic The skewness of the pitch class histogram, using Pearson's median skewness formula, after arranging the pitch classes according to the circle of fifths. Descriptor
Pitch Class Variability jSymbolic Standard deviation of all pitch classes in the melody. Descriptor
Pitch Class Variability After Folding jSymbolic Standard deviation of all pitch classes after arranging the pitch classes by perfect fifths. Provides a measure of how close the pitch classes are as a whole from the mean pitch class from a dominant-tonic perspective. Descriptor
Pitch Entropy FANTASTIC The zeroth-order base-2 entropy of the pitch distribution. Descriptor
Pitch Interval SIMILE The intervals (in semitones) between consecutive pitches in the melody. Sequence
Pitch Kurtosis jSymbolic The sample excess kurtosis of the pitch histogram. Descriptor
Pitch LTM Mean Information Content IDyOM Pearce, M. (2005) The average information content across all notes in a melody, calculated using IDyOM's long-term model (LTM). Information content is perceptually related to surprise, and can be calculated for pitches or rhythms. Descriptor
Pitch Range FANTASTIC, jSymbolic Subtract the lowest pitch number in the melody from the highest. Descriptor
Pitch STM Mean Information Content IDyOM Pearce, M. (2005) The average information content across all notes in a melody, calculated using IDyOM's prediction-by-partial-matching (PPM) algorithm. Information content is perceptually related to surprise, and can be calculated for pitches or rhythms. Descriptor
Pitch Skewness jSymbolic The skewness of the pitch histogram, using Pearson's median skewness formula. Descriptor
Pitch Spelling Partitura Meredith (2006) Pitch spelling using the ps13s1 algorithm. Sequence
Pitch Standard Deviation FANTASTIC, jSymbolic Standard deviation of all pitch numbers in the melody. Descriptor This feature is named 'Pitch Variability' in JSymbolic.
Polynomial Contour Coefficients FANTASTIC The first 3 non-constant coefficients of the polynomial contour. Sequence
Polyrhythms jSymbolic The fraction of beat histogram peaks that are not integer multiples/factors of the highest peak. Descriptor
Polyrhythms Tempo Standardized jSymbolic The fraction of beat histogram peaks that are not integer multiples/factors of the highest peak using tempo-standardized histogram. Descriptor
Prevalence Of Dotted Notes jSymbolic The sum of dotted rhythmic bins: 3, 5, 7, 9, 11. Descriptor
Prevalence Of Long Rhythmic Values jSymbolic The sum of rhythmic bins 6 to 11 (half notes to dotted double whole notes or more). Descriptor
Prevalence Of Medium Rhythmic Values jSymbolic The sum of rhythmic bins 2 to 6 (8th notes to half notes). Descriptor
Prevalence Of Most Common Melodic Interval jSymbolic The proportion of intervals that are the most common interval. Descriptor
Prevalence Of Most Common Pitch jSymbolic The proportion of pitches that are the most common pitch with regards to the total number of pitches in the melody. Descriptor
Prevalence Of Most Common Pitch Class jSymbolic The proportion of pitch classes that are the most common pitch class with regards to the total number of pitch classes in the melody. Descriptor
Prevalence Of Most Common Rhythmic Value jSymbolic The proportion (0.0 - 1.0) of the modal rhythmic bin. Descriptor
Prevalence Of Short Rhythmic Values jSymbolic The sum of the three shortest rhythmic bins (indexes 0, 1, and 2). Descriptor
Prevalence Of Very Long Rhythmic Values jSymbolic The sum of rhythmic bins 9 to 11 (dotted whole notes to dotted double whole notes or more). Descriptor
Prevalence Of Very Short Rhythmic Values jSymbolic The sum of the two shortest rhythmic bins (indexes 0 and 1). Descriptor
Proportion Conjunct Scalar Novel The proportion of notes that form conjunct scalar sequences. Descriptor
Proportion Inscale Novel The proportion of notes in the melody that are in the scale of the estimated key. Descriptor
Proportion Of Time In First Meter Novel The proportion of time spent in the first time signature. Descriptor
Proportion Scalar Novel The proportion of all notes that form scalar sequences. Descriptor
Range Of Rhythmic Values jSymbolic The range of rhythmic values located within the 12-bin PPQN-based histogram. Durations are converted to quarter notes and mapped to 12 fixed rhythmic bins using midpoints. The returned value is the difference between the highest and lowest non-empty bins. Descriptor
Referent IDyOM Calculate the referent (root note) of a melody. Descriptor
Relative Prevalence Of Most Common Melodic Intervals jSymbolic The ratio of the frequency of the second most common interval to the frequency of the most common interval. Descriptor
Relative Prevalence Of Most Common Rhythmic Values jSymbolic The ratio of the second-most-common rhythmic bin to the most common bin. Descriptor
Relative Prevalence Of Top Pitch Classes jSymbolic The ratio of the frequency of the second most common pitch class to the frequency of the most common pitch class. Descriptor
Relative Prevalence Of Top Pitches jSymbolic The ratio of the frequency of the second most common pitch to the frequency of the most common pitch. Descriptor
Repeated Notes jSymbolic The proportion of repeated notes in the melody. Descriptor
Rhythm LTM Mean Information Content IDyOM Pearce, M. (2005) The average rhythmic information content across all notes in a melody, calculated using IDyOM's long-term model (LTM). Information content is perceptually related to surprise, and can be calculated for pitches or rhythms. Descriptor
Rhythm STM Mean Information Content IDyOM Pearce, M. (2005) The average rhythmic information content across all notes in a melody, calculated using IDyOM's short-term model (STM). Information content is perceptually related to surprise, and can be calculated for pitches or rhythms. Descriptor
Rhythmic Looseness jSymbolic The average width of beat histogram peaks. Width is defined as the distance between points at 30% of the peak height. Descriptor
Rhythmic Looseness Tempo Standardized jSymbolic The average width of beat histogram peaks using tempo-standardized histogram. Width is defined as the distance between points at 30% of the peak height. Descriptor
Rhythmic Variability jSymbolic The standard deviation of the beat histogram bin magnitudes, excluding the first 40 bins. Descriptor
Rhythmic Variability Tempo Standardized jSymbolic The standard deviation of the tempo-standardized beat histogram bin magnitudes, excluding the first 40 bins. Descriptor
Second Strongest Rhythmic Pulse jSymbolic The bin index (BPM) of the second-highest magnitude in the beat histogram. Descriptor
Second Strongest Rhythmic Pulse Tempo Standardized jSymbolic The bin index (BPM) of the second-highest magnitude in the 120-BPM standardized beat histogram. Descriptor
Shortest Rhythmic Value jSymbolic The shortest rhythmic value (in quarter notes) among non-empty bins. Descriptor
Sichel's S FANTASTIC Sichel (1975) Sichel's S measure corresponds to the proportion of m-types that occur exactly twice in a sequence. Higher values indicate a greater amount of m-types that occur exactly twice. Descriptor
Simpson's D FANTASTIC Simpson (1949) Simpson's D measure of diversity. This feature measures the rate of m-type repetition in a similar way to Yule's K. Descriptor
Standard Deviation Absolute Interval FANTASTIC The standard deviation of the absolute intervals in the melody. Descriptor
Std Cloud Diameter Partitura Herremans & Chew (2016) Standard deviation of cloud diameter from the tonal tension model. Cloud Diameter provides a measure of the maximal tonal distance of the notes in a chord, following the definition in Partitura. Descriptor
Std Cloud Momentum Partitura Herremans & Chew (2016) Standard deviation of cloud momentum from the tonal tension model. Cloud Momentum provides a measure of movement of pitch sets in the spiral array space, weighted by note durations, following the definition in Partitura. Descriptor
Std Global Local Weight FANTASTIC Calculate standard deviation of global-local weight using inverse entropy weighting. Descriptor
Std Global Weight FANTASTIC Calculate standard deviation of global weight using inverse entropy weighting. Descriptor
Std Tensile Strain Partitura Herremans & Chew (2016) Standard deviation of tensile strain from the tonal tension model. Tensile strain provides a measure of the distance between the local and global tonal context, following the definition in Partitura. Descriptor
Step Contour Global Direction FANTASTIC The correlation between the step contour vector and an ascending linear function y = x. Descriptor
Step Contour Global Variation FANTASTIC The standard deviation of the step contour vector. Descriptor
Step Contour Local Variation FANTASTIC The mean absolute difference between adjacent values of the step contour vector. Descriptor
Stepwise Motion jSymbolic The proportion of stepwise motion in the melody. Stepwise motion is defined as a melodic interval of 1 or 2 semitones. Descriptor
Strength Of Second Strongest Rhythmic Pulse jSymbolic The magnitude of the beat histogram bin with the second-highest magnitude. Descriptor
Strength Of Second Strongest Rhythmic Pulse Tempo Standardized jSymbolic The magnitude of the tempo-standardized beat histogram bin with the second-highest magnitude. Descriptor
Strength Of Strongest Rhythmic Pulse jSymbolic The magnitude of the beat histogram bin with the highest magnitude. Descriptor
Strength Of Strongest Rhythmic Pulse Tempo Standardized jSymbolic The magnitude of the tempo-standardized beat histogram bin with the highest magnitude. Descriptor
Strength Ratio Of Two Strongest Rhythmic Pulses jSymbolic Ratio of the magnitude of the strongest to second-strongest rhythmic pulse. Descriptor
Strength Ratio Of Two Strongest Rhythmic Pulses Tempo Standardized jSymbolic Ratio of the magnitude of the strongest to second-strongest rhythmic pulse (120-BPM standardized histogram). Descriptor
Strong Tonal Centres jSymbolic The number of isolated peaks in the pitch class histogram that each account for at least 9% of notes. Descriptor
Strongest Rhythmic Pulse jSymbolic The bin index (BPM) of the maximum beat histogram magnitude. Descriptor
Strongest Rhythmic Pulse Tempo Standardized jSymbolic The bin index (BPM) of the maximum in the 120-BPM standardized beat histogram. Descriptor
Syncopation Novel Longuet-Higgins & Lee (1984) Calculate the mean syncopation value based on the Longuet-Higgins and Lee (1984) model. This syncopation model assigns metrical weights to each note position based on its position in the metric hierarchy. Syncopation occurs when a rest or tied note is preceded by a sounded note of lower metrical weight. The syncopation value is the difference between the rest weight and the preceding note weight. Descriptor
Syncopicity SIMILE Calculates the sum syncopicity of a melody across metric levels. Syncopicity measures the degree to which notes occur off the main metrical grid but are long enough to span across metric boundaries. This calculates syncopations at four metric levels: 1) Half bar level 2) Beat level 3) First subdivision (half-beat) 4) Second subdivision (quarter-beat) An event is considered syncopated at a given level if: 1) It does not fall on a grid point of this level 2) It falls on a grid point of the next lower level 3) Its IOI extends beyond the lower level time unit (or it's the last note) Descriptor
TFDF Kendall FANTASTIC Calculate Kendall's tau correlation between term frequency and document frequency. Descriptor
TFDF Spearman FANTASTIC Calculate Spearman correlation between term frequency and document frequency. Descriptor
Tempo Variability jSymbolic The variability of tempo of the melody. Descriptor
Tessitura MIDI Toolbox von Hippel (2000). Tessitura is based on standard deviation from median pitch height. The median range of the melody tends to be favoured and thus more expected. Tessitura predicts whether listeners expect tones close to median pitch height. Higher tessitura values correspond to melodies that have a wider range of pitches. Sequence
Tessitura Std MIDI Toolbox The standard deviation of the sequence of tessitura values. Descriptor
Tonal Clarity FANTASTIC Temperley (2007) The ratio between the top two key correlation values. Descriptor
Tonal Entropy Novel The zeroth-order base-2 entropy of all key correlations. Descriptor
Tonal Spike FANTASTIC The ratio between the highest key correlation and the sum of all other correlations. Descriptor
Tonal Tension Partitura Herremans & Chew (2016) Computes tension ribbons using the tonal tension algorithm. Provides a means of comparing Chew's spiral array and the tonal tension profiles produced from Herremans and Chew's tension ribbons. This returns a dictionary containing the cloud diameter, cloud momentum, tensile strain, ordered by onset. Sequence
Tonalness FANTASTIC Krumhansl (1990) The magnitude of the highest correlation with a precomputed key profile. This key profile is established and elaborated on in Krumhansl (1990). Descriptor
Tonalness Histogram Novel Krumhansl (1990) A histogram of Krumhansl-Schmuckler correlation values. Sequence
Total Number Of Notes jSymbolic The total number of notes. Descriptor
Variability In Rhythmic Value Run Lengths jSymbolic The standard deviation of rhythmic value run lengths. Run length is the number of consecutive notes with the same rhythmic value. Descriptor
Variability Of Complete Rest Durations jSymbolic The standard deviation of complete rest durations in quarter notes (ignoring rests shorter than 0.1 QN). Descriptor
Variability Of Note Durations jSymbolic The standard deviation of note durations in seconds. Descriptor
Variability Of Rhythmic Value Offsets jSymbolic The standard deviation of rhythmic value offsets (in quarter notes). Descriptor
Yule's K FANTASTIC Yule (1944) Yule's K measure of lexical richness. This feature measures the rate at which m-types are repeated in a sequence. Higher values indicate more repetitive sequences. Descriptor

Sources

  • FANTASTIC: Müllensiefen, D. (2009). Feature ANalysis Technology Accessing STatistics (In a Corpus): Technical Report v1.5
  • jSymbolic: McKay, C., & Fujinaga, I. (2006). jSymbolic: A Feature Extractor for MIDI Files
  • IDyOM: Pearce, M. T. (2005). The construction and evaluation of statistical models of melodic structure in music perception and composition
  • MIDI Toolbox: Eerola, T., & Toiviainen, P. (2004). MIDI Toolbox: MATLAB Tools for Music Research
  • Melsim: Silas, S., & Frieler, K. (n.d.). Melsim: Framework for calculating tons of melodic similarities
  • Simile: Müllensiefen, D., & Frieler, K. (2004). The Simile algorithms documentation 0.3
  • Novel: Custom features introduced in this package

Feature Types

  • Descriptor: Returns a single scalar value (int, float, bool)
  • Sequence: Returns a collection (list, tuple, dict, etc.)