Evaluation of the Audio Beat Tracking System BeatRoot By Simon Dixon (JNMR 2007) Presentation by Yading Song Centre for Digital Music [email protected]QMUL ELE021 Music & Speech Processing 27 February 2012
17
Embed
Evaluation of the Audio Beat Tracking System BeatRoot By Simon Dixon (JNMR 2007) Presentation by Yading Song Centre for Digital Music [email protected].
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Slide 1
Slide 2
Evaluation of the Audio Beat Tracking System BeatRoot By Simon
Dixon (JNMR 2007) Presentation by Yading Song Centre for Digital
Music [email protected] QMUL ELE021 Music & Speech
Processing 27 February 2012
Slide 3
Identifying and synchronizing with the basic rhythmic pulse of
a piece of music An interactive beat tracking and metrical
annotation system[1] It uses a multiple agent architecture with
different hypotheses Rate Placement of musical beats Accurate
tracking Quick recovery from errors Graceful degradation
BeatRoot
Slide 4
Tempo induction Find the rate of beat Beat tracking Synchronize
a quasi-regular pulse sequence with music Steps
Slide 5
Architecture of BeatRoot System Onset Detection Tempo Induction
Beat Tracking
Slide 6
Detection function Spectral flux (used by Dixon) Weighted phase
deviation Complex domain detection function Spectral Flux The
square of the difference between the normalized magnitude of
successive frames How quickly the power spectrum of the a signal is
changing Peak-picking algorithm is used to find the local maxima
Onset detection function Onset Detection
Slide 7
Spectral Flux Example of spectral flux vivaldi.wav, implemented
in MIRtoolbox
Slide 8
It calculates onsets times to compute clusters of inter-onset
intervals (IOIs) IOI = the time interval between any pair of onsets
Use clustering algorithm to find groups of similar IOIs Represents
various musical units (e.g. half notes) Tempo Induction
Slide 9
1. Clustering Various of IOIs Greedy algorithms 2. Combining
Along with the No. of IOIs To weight the clusters A ranked list of
tempo hypotheses is produced Pass it to beat tracking sub-system
Two steps
Slide 10
It uses a multiple agent architecture to find sequence of
events Match various tempo hypotheses Rate each sequence Determine
the most likely one The music is processed sequentially from
beginning to end At any point the agents Represent various
hypotheses about the rate and timing of beat Make prediction of
next beats based on current states Beat Tracking
Slide 11
Each agent at the beginning Is initialized with a tempo
hypothesis An onset time which is taken from the first few onsets,
which defines the agents first beat time Make prediction with given
tempo and first beat time with a tolerance window Onsets In inner
window taken as actual beat time, stored and updated In outer
window taken as possible beat times or not Beat Tracking
Slide 12
Solid circle: predicted beat times which correspond to onset
Hollow circle: predicted beat times which dont correspond to
onset
Slide 13
Each agent is equipped with an evaluation function which rates
how well the predicted and actual beat correspond The agent with
the highest score outputs sequence of beats as the solution to the
beat tracking problem Beat Tracking
Slide 14
User Interface
Slide 15
Slide 16
Tempo Induction is correct in the most case Estimation of beat
times are robust [2] Evaluation
Slide 17
[1] S. Dixon, "Evaluation of audio beat tracking system
beatroot," Journal of New Music Research, vol. 36, no. 1, pp.
39-51, 2007. [2] MIREX, Music Information Retrieval Evaluation
eXchange Reference