Real-time recognition of percussive sounds by a model-based method

Authors:
Umut Şimşekli;Antti Jylhä;Cumhur Erkut;A. Taylan Cemgil
Affiliations:
Department of Computer Engineering, Boğaziçi University, İstanbul, Turkey;Department of Signal Processing and Acoustics, Aalto University School of Science and Technology, Aalto, Finland;Department of Signal Processing and Acoustics, Aalto University School of Science and Technology, Aalto, Finland;Department of Computer Engineering, Boğaziçi University, İstanbul, Turkey
Venue:
EURASIP Journal on Advances in Signal Processing - Special issue on musical applications of real-time signal processing
Year:
2011

Citing 10
Cited 1

Automatic Extraction of Drum Tracks from Polyphonic Music Signals

CW '02 Proceedings of the First International Symposium on Cyber Worlds (CW'02)
Introduction to Machine Learning (Adaptive Computation and Machine Learning)

Introduction to Machine Learning (Adaptive Computation and Machine Learning)
Inference in Hidden Markov Models (Springer Series in Statistics)

Inference in Hidden Markov Models (Springer Series in Statistics)
Toward Robotic Musicianship

Computer Music Journal
B-Keeper: a beat-tracker for live performance

NIME '07 Proceedings of the 7th international conference on New interfaces for musical expression
A hand clap interface for sonic interaction with the computer

CHI '09 Extended Abstracts on Human Factors in Computing Systems
Bayesian inference for nonnegative matrix factorisation models

Computational Intelligence and Neuroscience
Self-produced sound: tightly binding haptics and audio

HAID'07 Proceedings of the 2nd international conference on Haptic and audio interaction design
Drum sound detection in polyphonic music with hidden Markov models

EURASIP Journal on Audio, Speech, and Music Processing
Synthesis of Hand Clapping Sounds

IEEE Transactions on Audio, Speech, and Language Processing

Rhythmic walking interactions with auditory feedback: an exploratory study

Proceedings of the 7th Audio Mostly Conference: A Conference on Interaction with Sound

Quantified Score

Hi-index	0.00

Visualization

Abstract

Interactive musical systems require real-time, low-latency, accurate, and reliable event detection and classification algorithms. In this paper, we introduce a model-based algorithm for detection of percussive events and test the algorithm on the detection and classification of different percussive sounds. We focus on tuning the algorithm for a good compromise between temporal precision, classification accuracy and low latency. The model is trained offline on different percussive sounds using the expectation maximization approach for learning spectral templates for each sound and is able to run online to detect and classify sounds from audio stream input by a Hidden Markov Model. Our results indicate that the approach is promising and applicable in design and development of interactive musical systems.