Difference between revisions of "MIR workshop 2015"

From CCRMA Wiki
Jump to: navigation, search
m
(Attendees)
 
(30 intermediate revisions by 2 users not shown)
Line 1: Line 1:
Under construction.
+
''' Intelligent Audio Systems: Foundations and Applications of Music Information Retrieval '''
  
<b>Intelligent Audio Systems: Foundations and Applications of Music Information Retrieval</b>
+
== News ==
  
 +
'''Wednesday, July 15'''
 +
 +
8:48 am:
 +
 +
* Today: Zafar Rafii, Jeff Scott, Aneesh Vartakavi, et al. of Gracenote will join us for lunch and for guest lectures in the afternoon.
 +
* If you checked out https://github.com/stevetjoa/stanford-mir onto your local machine, be sure to '''git checkout gh-pages''' before working.
 +
 +
'''Tuesday, July 14'''
 +
 +
9:31 am:
 +
 +
* Don't forget '''%matplotlib inline''' at the top of your notebooks.
 +
 +
'''Monday, July 13'''
 +
 +
2:18 pm: dependencies:
 +
 +
* apt-get install: git, python-dev, pip, python-scipy, python-matplotlib
 +
* Python packages: pip, boto, boto3, matplotlib, ipython, numpy, scipy, scikit-learn, librosa, mir_eval, seaborn, requests
 +
* (Anaconda)
 +
 +
11:11 am: Your post-it notes:
 +
 +
* content-based analysis e.g. classifying violin playing style (vibrato, bowing)
 +
* MIR overview; music recommendation
 +
* feature extraction; dimensionality reduction; prediction
 +
* source separation techniques
 +
* chord estimation; "split" musical instruments; find beats in a song
 +
* audio-to-midi; signal/source/speaker separation; programming audio in Python (in general)
 +
* acoustic fingerprinting
 +
* machine learning; turn analysis -> synth; music characterization
 +
* beat tracking; ways of identifying timbre
 +
* mood recognition
 +
* instrument separation; real-time processing
 +
* Marsyas?
 +
* speed of retrieval
 +
* what's possible and what's not in music information retrieval; how to use MIR toolbox for fast realization of ideas
 +
* machine learning techniques for more general audio problems i.e. language detection or identifying sound sources
 +
* networking and getting to know you all
 +
 +
== Attendees ==
 +
 +
Eric Raymond <lowlifi@gmail.com>, Stelios Andrew Stavroulakis, Richard Mendelsohn, Naithan Bosse, Alessio Bazzica, Karthik Yadati, Martha Larson, Stephen Hartzog, Philip Lee, Jaeyoung Choi, Matthew Gallagher, Yule Wu, Mark Renker, Rohit Ainapure, Eric Tarr <erictarr@gmail.com>, Allen Wu, Aaron Hipple
  
 
== Logistics ==
 
== Logistics ==
Workshop Title: '''Intelligent Audio Systems: Foundations and Applications of Music Information Retrieval'''
+
* Monday, July 13, through Friday, July 17, 2015. 9 AM to 5 PM every day.
* Monday, June 23, through Friday, June 27, 2014. 9:30 AM to 5 PM every day.
+
 
* Location: The Knoll, CCRMA, Stanford University. http://goo.gl/maps/nNKx
 
* Location: The Knoll, CCRMA, Stanford University. http://goo.gl/maps/nNKx
 
* Instructors:  
 
* Instructors:  
** [http://www.linkedin.com/in/jayleboeuf/ Jay LeBoeuf], [http://www.izotope.com iZotope, Inc.],  
+
** [https://stevetjoa.com Steve Tjoa]
** [http://stevetjoa.com Steve Tjoa]
+
** [http://www.linkedin.com/in/jayleboeuf/ Jay LeBoeuf], [http://www.realindustry.com Real Industry.],
** [http://www.leighsmith.com/Research Leigh Smith]
+
  
 
== Abstract ==  
 
== 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?
+
How would you "Google for audio", provide music recommendations based on 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 will teach such underlying ideas, approaches, technologies, and practical design of intelligent audio systems using music information retrieval (MIR) algorithms.
  
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.
+
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 to, understand, and 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 sort, search, recommend, tag, and transcribe music, possibly in real time.
  
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.
+
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 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.
  
'''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.
+
Knowledge of basic digital audio principles is required. Familiarity with Python is desired but not required. Students are highly encouraged to bring their own audio source material for course labs and demonstrations.
  
== Schedule: Lectures & Labs ==
+
'''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 audio analysis systems.
  
=== Day 1: Introduction to MIR, Signal Analysis and Feature Extraction ===
+
== Schedule  ==
Presenters: Jay LeBoeuf, Leigh Smith
+
  
'''Glossary of Terms to be used in this course <work in progress>'''
+
Instructional material can be found at [http://musicinformationretrieval.com musicinformationretrieval.com] (read only) or on [https://github.com/stevetjoa/stanford-mir GitHub] (full source).
  
<br><u>Day 1: Part 1</u> [http://ccrma.stanford.edu/workshops/mir2014/CCRMA_MIR2014_Lecture1.pdf Lecture 1 Slides]
+
=== Day 1: Introduction to MIR, Signal Analysis, and Feature Extraction ===
  
* Introductions
+
'''Lecture'''
* CCRMA Introduction - (Nette, Carr, Fernando).   
+
 
* Introduction to MIR (What is MIR? Why are people interested? Commercial Applications of MIR)   
+
Introductions
* Overview of a basic MIR system architecture     
+
* CCRMA Introduction - (Nette, Fernando).   
 +
* Introduction to MIR (What is MIR? Why MIR? Commercial applications)   
 +
* Basic MIR system architecture     
 
* Timing and Segmentation: Frames, Onsets       
 
* 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)   
 
* Classification: Instance-based classifiers (k-NN)   
* Information Retrieval Basics (Part 1)
 
** Classifier evaluation (Cross-validation, training and test sets)
 
 
<br><u>Day 1: Part 2</u> [http://ccrma.stanford.edu/workshops/mir2014/CCRMA_MIR2014_Lecture2.pdf Lecture 2 Slides]
 
  
* Overview: Signal Analysis and Feature Extraction for MIR Applications
+
Overview: Signal Analysis and Feature Extraction for MIR Applications
 
* Windowed Feature Extraction
 
* Windowed Feature Extraction
** I/O and analysis loops
 
 
* Feature-vector design (Overview: http://www.create.ucsb.edu/~stp/PostScript/PopeHolmKouznetsov_icmc2.pdf)
 
* Feature-vector design (Overview: http://www.create.ucsb.edu/~stp/PostScript/PopeHolmKouznetsov_icmc2.pdf)
** Kinds/Domains of Features
+
* Time-domain 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
 
* 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<br>
+
MFCCs sonified
Original track ("Chewing Gum"): [https://myspace.com/anniemusic/music/song/chewing-gum-28101163-14694] <br>
+
* Original track ("Chewing Gum") [https://myspace.com/anniemusic/music/song/chewing-gum-28101163-14694]
MFCCs only [http://www.cs.princeton.edu/~mdhoffma/icmc2008/] <br>
+
* MFCCs only [http://www.cs.princeton.edu/~mdhoffma/icmc2008/]
  
  
<br><u>Lab 1:</u> <br>
+
'''Lab'''
 
+
* Application: Instrument recognition and drum transcription / Using simple heuristics and thresholds (i.e. "Why do we need machine learning?")
+
 
   
 
   
* [http://nbviewer.ipython.org/github/stevetjoa/stanford-mir/blob/master/Table_of_Contents.ipynb Lab 1 - Basic Feature Extraction and Classification] <br>
+
[http://musicinformationretrieval.com/feature_sonification.html Understanding Audio Features Through Sonification]
 
+
* From your home directory, simply type the following to obtain a copy of the repository: <code>git clone https://github.com/stevetjoa/ccrma.git</code>
+
** To receive an up-to-date version of the repository, from your repository folder: <code>git pull</code>
+
 
+
* Background for students needing a refresher:
+
** [http://ccrma.stanford.edu/workshops/mir2009/juans_lecture/2_fft.pdf Fundamentals of Digital Audio Signal Processing (lecture slides from Juan Bello)]
+
  
* REMINDER: Save all your work, because you may want to build on it in subsequent labs.
+
* Background for students needing a refresher: [http://ccrma.stanford.edu/workshops/mir2009/juans_lecture/2_fft.pdf Fundamentals of Digital Audio Signal Processing (lecture slides from Juan Bello)]
 +
* ''Reminder'': Save all your work, because you may want to build on it in subsequent labs.
  
=== Day 2: Beat, Rhythm, Pitch and Chroma Analysis ===
+
=== Day 2: Pitch and Chroma Analysis; Machine Learning, Clustering and Classification ===
Presenters: Leigh Smith, Steve Tjoa
+
  
<br><u>Day 2: Part 1 Beat-finding and Rhythm Analysis</u> [http://ccrma.stanford.edu/workshops/mir2014/CCRMA_MIR2014_Lecture3.pdf Lecture 3 Slides]
+
'''Lecture'''
[http://ccrma.stanford.edu/workshops/mir2011/BeatReferences.pdf A list of beat tracking references cited]
+
  
Demo: MediaMined Discover ([https://discover.izotope.com/ Rhythmic Similarity])
+
Classification: Unsupervised vs. Supervised, k-means, GMM, SVM
* 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
+
  
<br><u>Day 2, Part 2: Pitch and Chroma Analysis</u> [http://ccrma.stanford.edu/workshops/mir2013/CCRMA_MIR2013_pitch.pdf Lecture 4 Slides]
+
Pitch and Chroma
 
* Features:  
 
* Features:  
 
** Monophonic Pitch Detection  
 
** Monophonic Pitch Detection  
Line 121: Line 120:
 
** Query-by-humming  
 
** Query-by-humming  
 
** Music Transcription  
 
** Music Transcription  
 +
'''Lab'''
  
CCRMA Tour
+
[http://musicinformationretrieval.com/knn_instrument_classification.html K-NN Instrument Classification]
  
'''Lab 2:'''
+
[http://musicinformationretrieval.com/kmeans_instrument_classification.html MFCC, K-Means Clustering]
Part 1: Tempo Extraction
+
Part 2: Add in MFCCs to classification and test w Cross validation
+
* [https://github.com/stevetjoa/ccrma#lab-2 Lab 2 description]
+
*  See [https://github.com/stevetjoa/ccrma/blob/master/odf_of_file.m Onset Detection Function example] within the MIR matlab codebase in Octave/Matlab.
+
  
* Bonus Slides: Temporal & Harmony Analysis
+
* [http://ccrma.stanford.edu/workshops/mir2012/2012-ClusterLab.pdf K-Means (2012)]
** [http://ccrma.stanford.edu/workshops/mir2009/juans_lecture/4_rhythm.pdf Temporal Analysis (lecture slides from Juan Bello)]
+
** [http://ccrma.stanford.edu/workshops/mir2009/juans_lecture/6_harmony.pdf Harmony Analysis (lecture slides from Juan Bello)]
+
** [http://ccrma.stanford.edu/workshops/mir2009/references/klee-ieee-taslp08-print.pdf Chord recognition using HMMs (Kyogu Lee)]
+
** [http://ccrma.stanford.edu/workshops/mir2009/references/klee-lncs08.pdf Genre-specific chord recognition using HMMs (Kyogu Lee)]
+
  
=== Day 3: Machine Learning, Clustering and Classification ===
+
Bonus Slides: Temporal & Harmony Analysis
Demo: iZotope Discover (Sound Similarity Search, jay) [http://www.izotope.com/tech/cloud/mediamined.asp  Video]  
+
* [http://ccrma.stanford.edu/workshops/mir2009/juans_lecture/4_rhythm.pdf Temporal Analysis (lecture slides from Juan Bello)]
 +
* [http://ccrma.stanford.edu/workshops/mir2009/juans_lecture/6_harmony.pdf Harmony Analysis (lecture slides from Juan Bello)]
 +
* [http://ccrma.stanford.edu/workshops/mir2009/references/klee-ieee-taslp08-print.pdf Chord recognition using HMMs (Kyogu Lee)]
 +
* [http://ccrma.stanford.edu/workshops/mir2009/references/klee-lncs08.pdf Genre-specific chord recognition using HMMs (Kyogu Lee)]
  
Guest Lecture: Stephen Pope (SndsLike, BirdGenie)
 
[https://ccrma.stanford.edu/workshops/mir2014/MAT_MIR4-update.pdf MAT_MIR4-update slides]
 
[https://ccrma.stanford.edu/workshops/mir2014/BirdsEar.pdf BirdGenie Slides]
 
[https://ccrma.stanford.edu/workshops/mir2014/SndsLike.pdf SndsLike Slides]
 
  
Lecture 5: Classification: Unsupervised vs. Supervised, k-means, GMM, SVM - Steve [http://ccrma.stanford.edu/workshops/mir2014/CCRMA_MIR2014_ML.pdf Lecture 5 Slides]
+
=== Day 3: Deep Belief Networks; Pitch Transcription ===
  
 +
Introduction to Deep Learning [https://ccrma.stanford.edu/workshops/mir2013/CCRMA_MIR2013_DBN.pdf Slides]
  
'''Lab 3'''
+
[ https://ccrma.stanford.edu/workshops/mir2014/fann_en.pdf Neural Networks made easy]
Topic: MFCC + k-Means, Clustering
+
 
* [http://ccrma.stanford.edu/workshops/mir2012/2012-ClusterLab.pdf K-Means]
+
Pitch Transcription Exercise
 +
 
 +
Guest lectures by Gracenote
 +
 
 +
Catch-up from yesterday
  
Matlab code for key estimation, chord recognition:
 
* [http://ccrma.stanford.edu/workshops/mir2009/Lab3/lab3.tgz Lab - download lab3.tgz]
 
* [http://ccrma.stanford.edu/workshops/mir2009/Lab3/lab3.html Lab - Key estimation, chord recognition]
 
  
 
=== Day 4: Music Information Retrieval in Polyphonic Mixtures ===
 
=== Day 4: Music Information Retrieval in Polyphonic Mixtures ===
  
Lecture 6: Steve Tjoa, [http://ccrma.stanford.edu/workshops/mir2013/ccrma20130627.pdf Lecture 6 Slides]
+
'''Lecture'''
  
* Music Transcription and Source Separation
+
Music Transcription and Source Separation
 
* Nonnegative Matrix Factorization
 
* Nonnegative Matrix Factorization
 
* Sparse Coding
 
* Sparse Coding
  
Guest Lecture 7: Andreas Ehmann, MIREX <br>
+
Evaluation Metrics for Information Retrieval
 
+
Lecture 8: Evaluation Metrics for Information Retrieval - Leigh Smith [https://ccrma.stanford.edu/workshops/mir2014/CCRMA_MIR2014_IR.pdf Slides]
+
  
 +
'''Lab'''
  
'''Lab 4'''
+
[https://github.com/stevetjoa/ccrma#lab-4 Lab 4 Description]
* [https://github.com/stevetjoa/ccrma#lab-4 Lab 4 Description]
+
  
 
References:  
 
References:  
Line 176: Line 167:
 
** [http://ccrma.stanford.edu/workshops/mir2009/references/ROCintro.pdf ROC Analysis]
 
** [http://ccrma.stanford.edu/workshops/mir2009/references/ROCintro.pdf ROC Analysis]
  
=== Day 5: Deep Belief Networks and Wavelets ===
 
  
Lecture 10: Steve Tjoa, Introduction to Deep Learning [https://ccrma.stanford.edu/workshops/mir2013/CCRMA_MIR2013_DBN.pdf Slides]
+
=== Day 5: Hashing for Music Search and Retrieval  ===
  
Lecture 11: Leigh Smith, An Introduction to Wavelets [https://ccrma.stanford.edu/workshops/mir2014/CCRMA_MIR2014_Wavelets.pdf Slides]
+
Locality Sensitive Hashing ([http://musicinformationretrieval.com/lsh_fingerprinting.html notebook])
 
+
[ https://ccrma.stanford.edu/workshops/mir2014/fann_en.pdf Neural Networks made easy]
+
  
 
Lunch at [http://en.wikipedia.org/wiki/Homebrew_Computer_Club The Oasis]
 
Lunch at [http://en.wikipedia.org/wiki/Homebrew_Computer_Club The Oasis]
  
Klapuri eBook:  http://link.springer.com/book/10.1007%2F0-387-32845-9
+
== Software Libraries ==
 
+
Afternoon: CCRMA Lawn BBQ
+
 
+
== software, libraries, examples ==
+
Applications & Environments
+
* [http://www.mathworks.com/products/matlab/ MATLAB]
+
* [http://www.cs.waikato.ac.nz/ml/weka/ Weka Machine Learning and Data Mining Toolbox (Standalone app / Java)]
+
  
Machine Learning Libraries & Toolboxes
+
* [https://www.python.org/ Python]
* [http://www.ncrg.aston.ac.uk/netlab/ Netlab Pattern Recognition and Clustering Toolbox (Matlab)]
+
* [http://www.numpy.org/ NumPy]
* [http://www.csie.ntu.edu.tw/~cjlin/libsvm/#matlab libsvm SVM toolbox (Matlab)]  
+
* [http://www.scipy.org/ SciPy]
* [http://www.jyu.fi/hum/laitokset/musiikki/en/research/coe/materials/mirtoolbox/Download/fg_base_view MIR Toolboxes (Matlab)]
+
* [http://ipython.org/ IPython]
* [http://cosmal.ucsd.edu/cal/projects/CATbox/catbox.htm UCSD CatBox]
+
* [http://scikit-learn.org/stable/ scikit-learn]
Optional Toolboxes
+
* [http://bmcfee.github.io/librosa/ librosa]
* [http://www.ofai.at/~elias.pampalk/ma/ MA Toolbox]
+
* [http://craffel.github.io/mir_eval/ mir_eval]
* [http://www.jyu.fi/hum/laitokset/musiikki/en/research/coe/materials/miditoolbox MIDI Toolbox]
+
* [http://essentia.upf.edu/ Essentia]
* [see also below references]
+
* [http://www.vamp-plugins.org/vampy.html VamPy]
* [http://marsyas.sness.net/ Marsyas]
+
* CLAM
+
* Genetic Algorithm: http://www.ise.ncsu.edu/mirage/GAToolBox/gaot/
+
* Spider http://www.kyb.tuebingen.mpg.de/bs/people/spider/
+
* HTK http://htk.eng.cam.ac.uk/
+
  
 
== Supplemental papers and information for the lectures...==
 
== Supplemental papers and information for the lectures...==
Line 215: Line 191:
  
 
== Past CCRMA MIR Workshops and lectures==  
 
== Past CCRMA MIR Workshops and lectures==  
 +
* [https://ccrma.stanford.edu/wiki/MIR_workshop_2014 CCRMA MIR Summer Workshop 2014]
 
* [https://ccrma.stanford.edu/wiki/MIR_workshop_2013 CCRMA MIR Summer Workshop 2013]
 
* [https://ccrma.stanford.edu/wiki/MIR_workshop_2013 CCRMA MIR Summer Workshop 2013]
 
* [http://ccrma.stanford.edu/wiki/MIR_workshop_2012 CCRMA MIR Summer Workshop 2012]
 
* [http://ccrma.stanford.edu/wiki/MIR_workshop_2012 CCRMA MIR Summer Workshop 2012]
Line 222: Line 199:
 
* [http://cm-wiki.stanford.edu/wiki/MIR_workshop_2008 CCRMA MIR Summer Workshop 2008]
 
* [http://cm-wiki.stanford.edu/wiki/MIR_workshop_2008 CCRMA MIR Summer Workshop 2008]
  
== References for additional info ==  
+
== Additional References ==  
 +
 
 
Recommended books:  
 
Recommended books:  
 
* Data Mining: Practical Machine Learning Tools and Techniques, Second Edition by Ian H. Witten , Eibe Frank (includes software)
 
* Data Mining: Practical Machine Learning Tools and Techniques, Second Edition by Ian H. Witten , Eibe Frank (includes software)
Line 230: Line 208:
 
* Speech and Audio Signal Processing:Processing and perception of speech and music Ben Gold & Nelson Morgan, Wiley 2000  
 
* Speech and Audio Signal Processing:Processing and perception of speech and music Ben Gold & Nelson Morgan, Wiley 2000  
  
Prerequisite / background material:  
+
Background material:  
 
* http://140.114.76.148/jang/books/audioSignalProcessing/
 
* http://140.114.76.148/jang/books/audioSignalProcessing/
* [http://ccrma.stanford.edu/workshops/mir2008/learnmatlab_sp3.pdf The Mathworks' Matlab Tutorial]
 
 
* [http://ismir2007.ismir.net/proceedings/ISMIR2007_tutorial_Lartillot.pdf ISMIR2007 MIR Toolbox Tutorial]
 
* [http://ismir2007.ismir.net/proceedings/ISMIR2007_tutorial_Lartillot.pdf ISMIR2007 MIR Toolbox Tutorial]
  
Line 251: Line 228:
 
* http://www.jyu.fi/hum/laitokset/musiikki/en/research/coe/materials
 
* http://www.jyu.fi/hum/laitokset/musiikki/en/research/coe/materials
 
* http://www.music-ir.org/evaluation/tools.html
 
* http://www.music-ir.org/evaluation/tools.html
* http://140.114.76.148/jang/matlab/toolbox/
 
 
* http://htk.eng.cam.ac.uk/
 
* http://htk.eng.cam.ac.uk/
  
Line 268: Line 244:
  
 
https://ccrma.stanford.edu/wiki/MIR_workshop_2008_notes#Research_Databases_.2F_Collections_of_Ground_truth_data_and_copyright-cleared_music
 
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/~mw/ Mike's scripts]
 
 
* [[Reading MP3 Files]]
 
* [[Low-Pass Filter]]
 
* Steve Tjoa: [http://ccrma.stanford.edu/~kiemyang/software Matlab code] (updated July 9, 2009)
 
 
[[Category: Workshops]]
 
http://ccrma.stanford.edu/~kglee/kaist_summer2008_special_lecture/
 
 
[[MIR_workshop_2014]]
 
 
=== Bonus Lab Material from Previous Years (Matlab) ===
 
* Harmony Analysis Slides / Labs
 
** [http://ccrma.stanford.edu/workshops/mir2009/juans_lecture/6_harmony.pdf Harmony Analysis (lecture slides from Juan Bello)]
 
** [http://ccrma.stanford.edu/workshops/mir2009/references/klee-ieee-taslp08-print.pdf Chord recognition using HMMs (Kyogu Lee)]
 
** [http://ccrma.stanford.edu/workshops/mir2009/references/klee-lncs08.pdf Genre-specific chord recognition using HMMs (Kyogu Lee)]
 
** [http://ccrma.stanford.edu/workshops/mir2009/Lab3/lab3.tgz Lab - download lab3.tgz]
 
** [http://ccrma.stanford.edu/workshops/mir2009/Lab3/lab3.html Lab - Key estimation, chord recognition]
 
 
** [http://ccrma.stanford.edu/workshops/mir2013/Lab5-SVMs.htm  SVM Lab]
 
 
* Overview of Weka & the Wekinator
 
** [http://www.cs.waikato.ac.nz/ml/weka/ Weka home]
 
** [http://code.google.com/p/wekinator/ Wekinator on Google code] and [http://wiki.cs.princeton.edu/index.php/ChucK/Wekinator/Instructions instructions]
 
** [http://ccrma.stanford.edu/workshops/mir2011/weka_lab1.pdf Getting started with Weka]
 
** [https://ccrma.stanford.edu/workshops/mir2011/Wekinator_lab_2011.pdf Wekinator Lab]
 
 
* Downloads
 
**  [https://ccrma.stanford.edu/workshops/mir2011/MAT240F-Reader.zip UCSB MAT 240F Reader]
 
**  [https://ccrma.stanford.edu/workshops/mir2011/MAT240F-Code.zip UCSB MAT 240F Code]
 
**  [https://ccrma.stanford.edu/workshops/mir2011/MAT240F-Sounds.zip UCSB MAT 240F Sounds]
 
 
* A brief history of MIR
 
** See also http://www.ismir.net/texts/Byrd02.html
 
* Notes
 
** CAL500 decoding
 
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)
 

Latest revision as of 14:33, 17 July 2015

Intelligent Audio Systems: Foundations and Applications of Music Information Retrieval

News

Wednesday, July 15

8:48 am:

  • Today: Zafar Rafii, Jeff Scott, Aneesh Vartakavi, et al. of Gracenote will join us for lunch and for guest lectures in the afternoon.
  • If you checked out https://github.com/stevetjoa/stanford-mir onto your local machine, be sure to git checkout gh-pages before working.

Tuesday, July 14

9:31 am:

  • Don't forget %matplotlib inline at the top of your notebooks.

Monday, July 13

2:18 pm: dependencies:

  • apt-get install: git, python-dev, pip, python-scipy, python-matplotlib
  • Python packages: pip, boto, boto3, matplotlib, ipython, numpy, scipy, scikit-learn, librosa, mir_eval, seaborn, requests
  • (Anaconda)

11:11 am: Your post-it notes:

  • content-based analysis e.g. classifying violin playing style (vibrato, bowing)
  • MIR overview; music recommendation
  • feature extraction; dimensionality reduction; prediction
  • source separation techniques
  • chord estimation; "split" musical instruments; find beats in a song
  • audio-to-midi; signal/source/speaker separation; programming audio in Python (in general)
  • acoustic fingerprinting
  • machine learning; turn analysis -> synth; music characterization
  • beat tracking; ways of identifying timbre
  • mood recognition
  • instrument separation; real-time processing
  • Marsyas?
  • speed of retrieval
  • what's possible and what's not in music information retrieval; how to use MIR toolbox for fast realization of ideas
  • machine learning techniques for more general audio problems i.e. language detection or identifying sound sources
  • networking and getting to know you all

Attendees

Eric Raymond <lowlifi@gmail.com>, Stelios Andrew Stavroulakis, Richard Mendelsohn, Naithan Bosse, Alessio Bazzica, Karthik Yadati, Martha Larson, Stephen Hartzog, Philip Lee, Jaeyoung Choi, Matthew Gallagher, Yule Wu, Mark Renker, Rohit Ainapure, Eric Tarr <erictarr@gmail.com>, Allen Wu, Aaron Hipple

Logistics

Abstract

How would you "Google for audio", provide music recommendations based on your MP3 files, or have a computer "listen" and understand what you are playing?

This workshop will teach such 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 to, understand, and 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 sort, search, recommend, tag, and transcribe music, possibly in real time.

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 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 Python is desired but not required. 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 audio analysis systems.

Schedule

Instructional material can be found at musicinformationretrieval.com (read only) or on GitHub (full source).

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

Lecture

Introductions

  • CCRMA Introduction - (Nette, Fernando).
  • Introduction to MIR (What is MIR? Why MIR? Commercial applications)
  • Basic MIR system architecture
  • Timing and Segmentation: Frames, Onsets
  • Classification: Instance-based classifiers (k-NN)

Overview: Signal Analysis and Feature Extraction for MIR Applications

MFCCs sonified

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


Lab

Understanding Audio Features Through Sonification

Day 2: Pitch and Chroma Analysis; Machine Learning, Clustering and Classification

Lecture

Classification: Unsupervised vs. Supervised, k-means, GMM, SVM

Pitch and Chroma

  • 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

Lab

K-NN Instrument Classification

MFCC, K-Means Clustering

Bonus Slides: Temporal & Harmony Analysis


Day 3: Deep Belief Networks; Pitch Transcription

Introduction to Deep Learning Slides

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

Pitch Transcription Exercise

Guest lectures by Gracenote

Catch-up from yesterday


Day 4: Music Information Retrieval in Polyphonic Mixtures

Lecture

Music Transcription and Source Separation

  • Nonnegative Matrix Factorization
  • Sparse Coding

Evaluation Metrics for Information Retrieval

Lab

Lab 4 Description

References:


Day 5: Hashing for Music Search and Retrieval

Locality Sensitive Hashing (notebook)

Lunch at The Oasis

Software Libraries

Supplemental papers and information for the lectures...

Past CCRMA MIR Workshops and lectures

Additional References

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

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