• Corpus ID: 15972862

Musical Key Extraction from Audio Using Profile Training

  title={Musical Key Extraction from Audio Using Profile Training},
  author={Steven van de Par and Martin F. McKinney and Andr{\'e} Redert},
A new method is presented for extracting the musical key from raw audio data. The method is based on the extraction of chromagrams using a new approach for tonal component selection taking into account auditory masking. The extracted chromagrams were used to train three key profiles for major and three key profiles for minor keys. The three trained key profiles differ in their temporal weighting of information across the duration of the song. One profile is based on uniform weighting while the… 

Tables from this paper

On the Impact of Key Detection Performance for Identifying Classical Music Styles
Improved performance is obtained when using an efficient key detection method for shifting the chroma histograms and the efficiency of four chroma extraction algorithms for classification is tested.
Genre-specific Key Profiles
The pitch chroma distributions for 9 different genres, their distances, and the degree to which these genres can be identified using these distributions when utilizing different strategies for achieving key-invariance are investigated.
A system for acoustic chord transcription and key extraction from audio using hidden Markov models trained on synthesized audio
A probabilistic framework that combines two closely related musical tasks—chord recognition and key extraction from audio—and achieves state-of-the-art performance in both applications is presented, and a solution to a bottleneck problem in machine learning approaches is suggested.
Cover song identification by sequence alignment algorithms
A method that can be used to effectively identify cover songs is described and the beat/chroma-synchronous chromagram, which is insensitive to the variation of the timber or rhythm of songs but sensitive to the melody, is chosen.
Musical key extraction using diffusion maps
Musical Key Estimation with Unsupervised Pattern Recognition
  • Michael Finley, A. Razi
  • Computer Science
    2019 IEEE 9th Annual Computing and Communication Workshop and Conference (CCWC)
  • 2019
This work employs an unsupervised minimization technique to determine both the mode and tonic center of a piece of music in contrast to previous methods that employ supervised learning techniques such as multiple classification models, support vector machines (SVMs), hidden Markov models, multinomial linear regressions, artificial neural networks, convolutional neural networks (CNNs), and other high-complexity machine learning algorithms.
Local key estimation based on harmonic and metric structures
A method for estimating the local keys of an audio signal by investigating the possible combination and extension of different previous proposed global key estimation approaches and introducing key dependency on the harmonic and the metric structures.
Perceptually motivated quasi-periodic signal selection for polyphonic music transcription
  • M. Triki, D. Slock
  • Computer Science
    2009 IEEE International Conference on Acoustics, Speech and Signal Processing
  • 2009
This work proposes a physically-motivated audio signal analysis followed by an auditory-based selection that allows for a better time/frequency resolution tradeoff, while the auditory distance discards the redundant/non-relevant information.
Joint Estimation of Musical Content Information From an Audio Signal. (Estimation conjointe d'information de contenu musical d'un signal audio)
A model that allows the joint estimation of the chords, the keys and the downbeats from polyphonic music recordings is developed and it is intended to show that integrating knowledge of mutual dependencies between several descriptors of musical content improves their estimation.
Cross recurrence quantification for cover song identification
A recurrence quantification analysis measure is proposed that allows the tracking of potentially curved and disrupted traces in cross recurrence plots (CRPs) and it is shown that this method identifies cover songs with a higher accuracy as compared to previously published techniques.


Fuzzy Analysis in Pitch-Class Determination for Polyphonic Audio Key Finding
A fuzzy analysis technique for pitch class determination that improves the accuracy of key finding from audio information and uses fuzzy analysis to reduce the errors caused by noisy detection of lower pitches, and to refine the biased raw frequency data, in order to extract more correct pitch classes.
Detection of Key Change in Classical Piano Music
The performance of the HMM-based approach for segmenting musical signals based on key change and identifying the key of each segment demonstrates the promise of the method.
High-Precision Fourier Analysis of Sounds Using Signal Derivatives
An original method is introduced which greatly improves the precision of the Fourier analysis not only in frequency and amplitude but also in time, thus minimizing the problem of the tradeoff of time
Derivation of auditory filter shapes from notched-noise data
Cognitive Foundations of Musical Pitch
1. Objectives and Methods 2. Quantifying Tonal Hierarchies and Key Distances 3. Musical Correlates of Perceived Tonal Hierarchies 4. A Key-Finding Algorithm Based on Tonal Hierarchies 5. Perceived
Musical key extraction from audio
The realisation and evaluation of a musical key extraction algorithm that works directly on raw audio data is presented. Its implementation is based on models of human auditory perception and music
Perception of the Major/Minor Distinction: IV. Emotional Connotations in Young Children
Thirty-eight children between ages 3 and 12 listened to 12 short musical passages derived from a counterbalanced 2 × 2 arrangement of (1) major versus minor modes and (2) harmonized versus simple