MIR workshop 2014

From CCRMA Wiki
Jump to: navigation, search

Intelligent Audio Systems: Foundations and Applications of Music Information Retrieval


Logistics

Workshop Title: Intelligent Audio Systems: Foundations and Applications of Music Information Retrieval

SEE 2015 WORKSHOP FOR THE LATEST INFORMATION: https://ccrma.stanford.edu/wiki/MIR_workshop_2014

Abstract

How would you "Google for audio", provide music recommendations based your MP3 files, or have a computer "listen" and understand what you are playing? This workshop will teach the underlying ideas, approaches, technologies, and practical design of intelligent audio systems using Music Information Retrieval (MIR) algorithms.

MIR is a highly-interdisciplinary field bridging the domains of digital audio signal processing, pattern recognition, software system design, and machine learning. Simply put, MIR algorithms allow a computer to "listen" and "understand or make sense of" audio data, such as MP3s in a personal music collection, live streaming audio, or gigabytes of sound effects, in an effort to reduce the semantic gap between high-level musical information and low-level audio data. In the same way that listeners can recognize the characteristics of sound and music - tempo, key, chord progressions, genre, or song structure - MIR algorithms are capable of recognizing and extracting this information, enabling systems to perform extensive sorting, searching, music recommendation, metadata generation, transcription, and even aiding/generating real-time performance.

This workshop is intended for: students, researchers, and industry audio engineers who are unfamiliar with the field of Music Information Retrieval (MIR). We will demonstrate the myriad of exciting technologies enabled by the fusion of basic signal processing techniques with machine learning and pattern recognition. Lectures will cover topics such as low-level feature extraction, generation of higher-level features such as chord estimations, audio similarity clustering, search, and retrieval techniques, and design and evaluation of machine classification systems. The presentations will be applied, multimedia-rich, overview of the building blocks of modern MIR systems. Our goal is to make the understanding and application of highly-interdisciplinary technologies and complex algorithms approachable.

Knowledge of basic digital audio principles is required. Familiarity with Matlab is desired. Students are highly encouraged to bring their own audio source material for course labs and demonstrations.

Workshop structure: The workshop will consist of half-day lectures, half-day supervised lab sessions, demonstrations, and discussions. Labs will allow students to design basic ground-up "intelligent audio systems", leveraging existing MIR toolboxes, programming environments, and applications. Labs will include creation and evaluation of basic instrument recognition, transcription, and real-time audio analysis systems.

Schedule: Lectures & Labs

Day 1: Introduction to MIR, Signal Analysis and Feature Extraction

Presenters: Jay LeBoeuf, Leigh Smith

Glossary of Terms to be used in this course <work in progress>


Day 1: Part 1 Lecture 1 Slides

  • Introductions
  • CCRMA Introduction - (Nette, Carr, Fernando).
  • Introduction to MIR (What is MIR? Why are people interested? Commercial Applications of MIR)
  • Overview of a basic MIR system architecture
  • Timing and Segmentation: Frames, Onsets
  • Demo: Using simple heuristics and thresholds (i.e. "Why do we need machine learning?")
  • Classification: Instance-based classifiers (k-NN)
  • Information Retrieval Basics (Part 1)
    • Classifier evaluation (Cross-validation, training and test sets)


Day 1: Part 2 Lecture 2 Slides

  • Overview: Signal Analysis and Feature Extraction for MIR Applications
  • Windowed Feature Extraction
    • I/O and analysis loops
  • Feature-vector design (Overview: http://www.create.ucsb.edu/~stp/PostScript/PopeHolmKouznetsov_icmc2.pdf)
    • Kinds/Domains of Features
    • Application Requirements (labeling, segmentation, etc.)
  • Time-domain features (MPEG-7 Audio book ref)
    • RMS, Peak, LP/HP RMS, Dynamic range, ZCR
  • Frequency-domain features
    • Spectrum, Spectral bins
    • Spectral measures (Spectral statistical moments)
    • Pitch-estimation and tracking
    • MFCCs
  • Spatial-domain features
    • M/S Encoding, Surround-sound Processing Frequency-dependent spatial separation, LCR sources

MFCCs Sonified
Original track ("Chewing Gum"): [1]
MFCCs only [2]



Lab 1:

  • Application: Instrument recognition and drum transcription / Using simple heuristics and thresholds (i.e. "Why do we need machine learning?")
  • From your home directory, simply type the following to obtain a copy of the repository: git clone https://github.com/stevetjoa/ccrma.git
    • To receive an up-to-date version of the repository, from your repository folder: git pull
  • REMINDER: Save all your work, because you may want to build on it in subsequent labs.

Day 2: Beat, Rhythm, Pitch and Chroma Analysis

Presenters: Leigh Smith, Steve Tjoa


Day 2: Part 1 Beat-finding and Rhythm Analysis Lecture 3 Slides A list of beat tracking references cited

Demo: MediaMined Discover (Rhythmic Similarity)

  • Onset-detection: Many Techniques
    • Time-domain differences
    • Spectral-domain differences
    • Perceptual data-warping
    • Adaptive onset detection
  • Beat-finding and Tempo Derivation
    • IOIs and Beat Regularity, Rubato
      • Tatum, Tactus and Meter levels
      • Tempo estimation
    • Onset-detection vs Beat-detection
      • The Onset Detection Function
    • Approaches to beat tracking & Meter estimation
      • Autocorrelation
      • Beat Spectrum measures
      • Multi-resolution (Wavelet)
    • Beat Histograms
    • Fluctuation Patterns
    • Joint estimation of downbeat and chord change


Day 2, Part 2: Pitch and Chroma Analysis Lecture 4 Slides

  • Features:
    • Monophonic Pitch Detection
    • Polyphonic Pitch Detection
    • Pitch representations (Tuning Histograms, Pitch and Pitch Class Profiles, Chroma)
  • Analysis:
    • Dynamic Time Warping
    • Hidden Markov Models
    • Harmonic Analysis/Chord and Key Detection
  • Applications
    • Audio-Score Alignment
    • Cover Song Detection
    • Query-by-humming
    • Music Transcription

CCRMA Tour

Lab 2: Part 1: Tempo Extraction Part 2: Add in MFCCs to classification and test w Cross validation

Day 3: Machine Learning, Clustering and Classification

Demo: iZotope Discover (Sound Similarity Search, jay) Video

Guest Lecture: Stephen Pope (SndsLike, BirdGenie) MAT_MIR4-update slides BirdGenie Slides SndsLike Slides

Lecture 5: Classification: Unsupervised vs. Supervised, k-means, GMM, SVM - Steve Lecture 5 Slides


Lab 3 Topic: MFCC + k-Means, Clustering

Matlab code for key estimation, chord recognition:

Day 4: Music Information Retrieval in Polyphonic Mixtures

Lecture 6: Steve Tjoa, Lecture 6 Slides

  • Music Transcription and Source Separation
  • Nonnegative Matrix Factorization
  • Sparse Coding

Guest Lecture 7: Andreas Ehmann, MIREX

Lecture 8: Evaluation Metrics for Information Retrieval - Leigh Smith Slides


Lab 4

References:

Day 5: Deep Belief Networks and Wavelets

Lecture 10: Steve Tjoa, Introduction to Deep Learning Slides

Lecture 11: Leigh Smith, An Introduction to Wavelets Slides

[ https://ccrma.stanford.edu/workshops/mir2014/fann_en.pdf Neural Networks made easy]

Lunch at The Oasis

Klapuri eBook: http://link.springer.com/book/10.1007%2F0-387-32845-9

Afternoon: CCRMA Lawn BBQ

software, libraries, examples

Applications & Environments

Machine Learning Libraries & Toolboxes

Optional Toolboxes

Supplemental papers and information for the lectures...

Past CCRMA MIR Workshops and lectures

References for additional info

Recommended books:

  • Data Mining: Practical Machine Learning Tools and Techniques, Second Edition by Ian H. Witten , Eibe Frank (includes software)
  • Netlab by Ian T. Nabney (includes software)
  • Signal Processing Methods for Music Transcription, Klapuri, A. and Davy, M. (Editors)
  • Computational Auditory Scene Analysis: Principles, Algorithms, and Applications, DeLiang Wang (Editor), Guy J. Brown (Editor)
  • Speech and Audio Signal Processing:Processing and perception of speech and music Ben Gold & Nelson Morgan, Wiley 2000

Prerequisite / background material:

Papers:

Other books:

  • Pattern Recognition and Machine Learning (Information Science and Statistics) by Christopher M. Bishop
  • Neural Networks for Pattern Recognition, Christopher M. Bishop, Oxford University Press, 1995.
  • Pattern Classification, 2nd edition, R Duda, P Hart and D Stork, Wiley Interscience, 2001.
  • "Artificial Intelligence: A Modern Approach" Second Edition, Russell R & Norvig P, Prentice Hall, 2003.
  • Machine Learning, Tom Mitchell, McGraw Hill, 1997.

Interesting Links:

Audio Source Material

OLPC Sound Sample Archive (8.5 GB) [3]

http://www.tsi.telecom-paristech.fr/aao/en/category/database/

RWC Music Database (n DVDs) [available in Stanford Music library]

RWC - Sound Instruments Table of Contents

http://staff.aist.go.jp/m.goto/RWC-MDB/rwc-mdb-i.html

Univ or Iowa Music Instrument Samples

https://ccrma.stanford.edu/wiki/MIR_workshop_2008_notes#Research_Databases_.2F_Collections_of_Ground_truth_data_and_copyright-cleared_music

MATLAB Utility Scripts

http://ccrma.stanford.edu/~kglee/kaist_summer2008_special_lecture/

MIR_workshop_2014

Bonus Lab Material from Previous Years (Matlab)

for i in *.mp3; do echo $i; afconvert -d BEI16@44100 -f AIFF "$i"; done

  • Extract CAL 500 per-song features to .mat or .csv using features from today. This will be used on lab for Friday. Copy it from the folder ccrma-gate.stanford.edu:/usr/ccrma/workshops/mir2011/cal500.tar (beware it's a 2Gb .tar file!) or grab the AIFF versions from ccrma-gate.stanford.edu:/usr/ccrma/workshops/mir2011/cal500_aiffs.tar (that's 16 GB)