Realtime Recognition of Orchestral Instruments

Slides:



Advertisements
Similar presentations
Applications of one-class classification
Advertisements

CS6800 Advanced Theory of Computation
1 CS 391L: Machine Learning: Instance Based Learning Raymond J. Mooney University of Texas at Austin.
Content-based retrieval of audio Francois Thibault MUMT 614B McGill University.
Overview What : Stroke type Transformation: Timbre Rhythm When: Stroke timing Resynthesis.
Content-Based Classification, Search & Retrieval of Audio Erling Wold, Thom Blum, Douglas Keislar, James Wheaton Presented By: Adelle C. Knight.
MACHINE LEARNING 9. Nonparametric Methods. Introduction Lecture Notes for E Alpaydın 2004 Introduction to Machine Learning © The MIT Press (V1.1) 2 
Classification of Music According to Genres Using Neural Networks, Genetic Algorithms and Fuzzy Systems.
Data Mining Techniques Outline
1 Abstract This paper presents a novel modification to the classical Competitive Learning (CL) by adding a dynamic branching mechanism to neural networks.
Neural Optimization of Evolutionary Algorithm Strategy Parameters Hiral Patel.
Face Recognition Using Neural Networks Presented By: Hadis Mohseni Leila Taghavi Atefeh Mirsafian.
DSP-FPGA Based Image Processing System Final Presentation Jessica Baxter  Sam Clanton Simon Fung-Kee-Fung Almaaz Karachi  Doug Keen Computer Integrated.
Comparison of machine and human recognition of isolated instrument tones Ichiro Fujinaga McGill University.
Kumar Srijan ( ) Syed Ahsan( ). Problem Statement To create a Neural Networks based multiclass object classifier which can do rotation,
Cristian Urs and Ben Riveira. Introduction The article we chose focuses on improving the performance of Genetic Algorithms by: Use of predictive models.
COMMON EVALUATION FINAL PROJECT Vira Oleksyuk ECE 8110: Introduction to machine Learning and Pattern Recognition.
MUMT611: Music Information Acquisition, Preservation, and Retrieval Presentation on Timbre Similarity Alexandre Savard March 2006.
Line detection Assume there is a binary image, we use F(ά,X)=0 as the parametric equation of a curve with a vector of parameters ά=[α 1, …, α m ] and X=[x.
Comparison of machine and human recognition of isolated instrument tones Ichiro Fujinaga McGill University.
Singer similarity / identification Francois Thibault MUMT 614B McGill University.
Performance Comparison of Speaker and Emotion Recognition
Chapter1: Introduction Chapter2: Overview of Supervised Learning
What is Unsupervised Learning? Learning without a teacher. No feedback to indicate the desired outputs. The network must by itself discover the relationship.
Unsupervised Learning Networks 主講人 : 虞台文. Content Introduction Important Unsupervised Learning NNs – Hamming Networks – Kohonen’s Self-Organizing Feature.
Realtime Recognition of Orchestral Instruments Ichiro Fujinaga McGill University.
Fast Query-Optimized Kernel Machine Classification Via Incremental Approximate Nearest Support Vectors by Dennis DeCoste and Dominic Mazzoni International.
Automatic Transcription System of Kashino et al. MUMT 611 Doug Van Nort.
Recognition of Isolated Instrument Tones by Conservatory Students Asha Srinivasan, David Sullivan, and Ichiro Fujinaga Peabody Conservatory of Music Johns.
Example Apply hierarchical clustering with d min to below data where c=3. Nearest neighbor clustering d min d max will form elongated clusters!
Instance-Based Learning Evgueni Smirnov. Overview Instance-Based Learning Comparison of Eager and Instance-Based Learning Instance Distances for Instance-Based.
Computational Intelligence: Methods and Applications Lecture 26 Density estimation, Expectation Maximization. Włodzisław Duch Dept. of Informatics, UMK.
ISA Kim Hye mi. Introduction Input Spectrum data (Protein database) Peptide assignment Peptide validation manual validation PeptideProphet.
Mustafa Gokce Baydogan, George Runger and Eugene Tuv INFORMS Annual Meeting 2011, Charlotte A Bag-of-Features Framework for Time Series Classification.
A Presentation on Adaptive Neuro-Fuzzy Inference System using Particle Swarm Optimization and it’s Application By Sumanta Kundu (En.R.No.
Evolutionary Design of the Closed Loop Control on the Basis of NN-ANARX Model Using Genetic Algoritm.
March 1, 2016Introduction to Artificial Intelligence Lecture 11: Machine Evolution 1 Let’s look at… Machine Evolution.
DOWeR Detecting Outliers in Web Service Requests Master’s Presentation of Christian Blass.
Chapter 12 Case Studies Part B. Control System Design.
Automatic Classification of Audio Data by Carlos H. L. Costa, Jaime D. Valle, Ro L. Koerich IEEE International Conference on Systems, Man, and Cybernetics.
Chapter 5 Unsupervised learning
Action-Grounded Push Affordance Bootstrapping of Unknown Objects
Genetic-Algorithm-Based Instance and Feature Selection
School of Computer Science & Engineering
Rule Induction for Classification Using
HyperNetworks Engın denız usta
Instance Based Learning
Ichiro Fujinaga McGill University
CSSE463: Image Recognition Day 11
Ch8: Nonparametric Methods
Unsupervised Learning Networks
Nearest-Neighbor Classifiers
Optical Music Recognition
Instance Based Learning
An Improved Neural Network Algorithm for Classifying the Transmission Line Faults Slavko Vasilic Dr Mladen Kezunovic Texas A&M University.
Introduction to Artificial Intelligence Lecture 11: Machine Evolution
Department of Electrical Engineering
X.4 Genetic Algorithms Understand the basic design architecture underpinning genetic algorithms Role of the Fitness function Repopulation based on genetic.
The Naïve Bayes (NB) Classifier
Boltzmann Machine (BM) (§6.4)
Ichiro Fujinaga Peabody Conservatory of Music Johns Hopkins University
Model generalization Brief summary of methods
Review NNs Processing Principles in Neuron / Unit
CSSE463: Image Recognition Day 11
CSSE463: Image Recognition Day 11
Realtime Recognition of Orchestral Instruments
Evolutionary Ensembles with Negative Correlation Learning
Ichiro Fujinaga McGill University
Data Mining CSCI 307, Spring 2019 Lecture 11
INFORMATION RETRIEVAL TECHNIQUES BY DR. ADNAN ABID
Presentation transcript:

Realtime Recognition of Orchestral Instruments Ichiro Fujinaga McGill University

Overview Introduction Lazy learning (exemplar-based learning) Results k-NN classifier Genetic algorithm Features Results Conclusions

Introduction Realtime recognition of isolated monophonic orchestral instruments Spectrum analysis by Miller Puckette’s fiddle~ Adaptive system based on a exemplar-based classifier and a genetic algorithm

Overall Architecture Off-line Live mic Input Sound file Input Data Acquisition & Data Analysis (fiddle) Recognition K-NN Classifier Output Instrument Name Knowledge Base Feature Vectors Genetic Algorithm K-NN Classifier Best Weight Vector Off-line

Exemplar-based learning The exemplar-based learning model is based on the idea that objects are categorized by their similarity to one or more stored examples There is much evidence from psychological studies to support exemplar-based categorization by humans This model differs both from rule-based or prototype-based (neural nets) models of concept formation in that it assumes no abstraction or generalizations of concepts This model can be implemented using k-nearest neighbor classifier and is further enhanced by application of a genetic algorithm

Exemplar-based categorization Objects are categorized by their similarity to one or more stored examples No abstraction or generalizations, unlike rule-based or prototype-based models of concept formation Can be implemented using k-nearest neighbor classifier Slow and large storage requirements?

Exemplar-based learning The exemplar-based learning model is based on the idea that objects are categorized by their similarity to one or more stored examples There is much evidence from psychological studies to support exemplar-based categorization by humans This model differs both from rule-based or prototype-based (neural nets) models of concept formation in that it assumes no abstraction or generalizations of concepts This model can be implemented using k-nearest neighbor classifier and is further enhanced by application of a genetic algorithm

K-nearest-neighbor classifier Determine the class of a given sample by its feature vector: Distances between feature vectors of an unclassified sample and previously classified samples are calculated The class represented by the majority of k-nearest neighbors is then assigned to the unclassified sample

Example of k-NN classifier

Example of k-NN classifier

Example of k-NN classifier

Example of k-NN classifier

Distance measures The distance in a N-dimensional feature space between two vectors X and Y can be defined as: A weighted distance can be defined as:

Genetic algorithms Optimization based on biological evolution Maintenance of population using selection, crossover, and mutation Chromosomes = weight vectors Fitness function = recognition rate Leave-one-out cross validation

Features Static features (per window) Dynamic features pitch mass or the integral of the curve (zeroth-order moment) centroid (first-order moment) variance (second-order central moment) skewness (third-order central moment) amplitudes of the harmonic partials number of strong harmonic partials spectral irregularity tristimulus Dynamic features means and velocities of static features over time

Data Original source: McGill Master Samples Over 1300 notes from 39 different timbres (23 orchestral instruments) Spectrum analysis by fiddle (2048 points) First 46–232ms of attack (1–9 windows) Each analysis window (46 ms) consists of a list of amplitudes and frequencies of the peaks in the spectra

Results Experiment I SHARC data static features Experiment II fiddle dynamic features Experiment III more features redefinition of attack point

Conclusions Realtime timbre recognition system Analysis by Puckette’s fiddle Recognition using dynamic features Adaptive recognizer by k-NN classifier enhanced with genetic algorithm A successful implementation of exemplar-based classifier in a time-critical environment

Future research Performer identification Speaker identification Tone-quality analysis Multi-instrument recognition Expert recognition of timbre

Recognition rate for different lengths of analysis window

Comparison with Human Performance