This issue summarizes our wishlist of music descriptors and algorithms to be added in Essenita. You can post your suggestions in comments.

Essentia 2.1

• Implement standard mode and finish testing EBU R128 loudness descriptors (implement EBU R128 loudness measure #94)
• Finish testing PitchYin (unit tests) (PitchYIN error on stationary signals  #230)
• SuperFlux (final clean implementation, review documentation, add unit tests Add unittests for SuperFlux algorithm #226)
• Improved PredominantMelody algorithm (Incorrect outputs for predominant melody algorithm using essentia #42, Predominant Melody - Contours gets drifted to high ranges and some contours missed #62)

Long-term future

• Beat tracker with downbeat detection (Determining first beat in a measure #253)
• Real-time beat tracker
• Algorithm for music segmentation (+ test current algorithm)
• More envelope descriptors (attack start/end time, temporal centroid, temporal increase/decrease, ADSR) (@ffont)
• Constant-Q transform (ConstantQ Transform? #136)
• Histogram streaming algorithm (map input stream of values into a configurable histogram) (Implement generic Histogram algorithm #529)
• Rhythm Patterns, Rhythm Histogram, and SSD (Implement Rhythm Patterns, Rhythm Histogram and Statistical Spectrum Descriptor #532)
• Beatogram and Meter features (currently marked as experimental algorithms) (Meter and Beatogram #486) (@ffont)
• Graham Percival's BPM [1] estimation method (@ffont)
• Audio fingerprinting (Echoprint, AcoustID) (Implement Chromaprint and Echoprint fingerprinting algorithm #474)
• Algorithms for estimation of time signature, bars, downbeat and offbeat (related to Beatogram)
• Melody extraction using source filter model (Improved predominant melody extraction with a Source-Filter model (SIMM) #469) (@juanjobosch)

[1] Graham Percival and George Tzanetakis. Streamlined tempo estimation based on autocorrelation and cross-correlation with pulses. IEEE/ACM Transac- tions on Audio, Speech, and Language Processing, 22(12):1765–1776, 2014.